skill-routing.tsv

# THE skill-routing table — the single source of truth for every routing surface.
#
# Routing a skill used to take six coordinated edits (README's two tables, the runbook row,
# init-project.sh's CLAUDE.local.md heredoc, gate-check.sh's stage map, the agent templates)
# plus a seventh copy inside every project's CLAUDE.local.md that no script could update.
# Measured on 2026-08-18, before this file existed: 17 of 43 skills were routed by NOTHING a
# project agent reads; facts-lock.sh reached 1 of 6 wired projects; agent-roles.md and
# source-triage.md reached 1 each. Every skill added since had silently become the eighteenth.
#
# Edit THIS file, then run:  bin/render-routing.sh
# CI / gate:                 bin/render-routing.sh --check   (exit 2 == a surface has drifted)
#
# Format: TAB-separated, seven columns. Blank lines and #-comments ignored.
#   1 name    stable id (basename without .md/.sh)
#   2 path    repo-relative path of the thing to load
#   3 when    one line: "always relevant for ..." — the trigger, not a description
#   4 agents  comma list of lead|ba|architect|mdl|gate|test|review, or "all" ("all" includes lead).
#             lead = the main session: it dispatches helpers, runs gates, asks the user. It has
#             no agents/*.md stub, so a lead-only row renders into no stub on purpose. Helpers
#             never read a row that does not name them — the project baseline view carries a
#             Role(s) column for exactly that (added 2026-10-05: before it, the view filtered by
#             stage only, so a Stage 5 page helper was pointed at the lead's, the tester's and
#             the reviewer's rows too — process/context-cost-research-2026-09-30.md §1).
#             "<role>?" (e.g. "mdl?", or "all,mdl?") keeps a baseline row on demand for that one
#             role: in its stub's on-demand rows, out of its always-read set and word count
#             (added 2026-10-14; bin/lib/skill-routing.sh _routing_role_tier). Baseline rows only.
#   5 stages  comma list of P,0,1,2,3,4,5,6,7 (conversion-runbook stages), or "-" for none
#   6 tier    baseline     (always-on: goes into every project's CLAUDE.local.md)
#             ondemand     (situational: load when the task calls for it)
#             experimental (under trial: routed and discoverable, but _routing_stage_arm skips
#                          it on purpose, so a skill nobody has proven yet can never be the
#                          reason a gate fails)
#   7 group   which question the skill answers, NOT what kind of thing it is. One of:
#               spine         what am I doing, who decides, how do I ask
#               source        reading a legacy system (migration entry mode only)
#               requirements  what must be built
#               architecture  how it is shaped
#               design        how it looks, before any MDL
#               build         authoring the model — the loop itself
#               build/mdl     the MDL language and tool reference
#               build/pages   page-building patterns
#               build/agents  Mendix AI agents — the agent document, tools, KBs, chat UI
#               build/workflow / build/integration / build/security   (declared, still empty)
#               verify        does it work
#               diagnose      something is broken and it may be the tooling
#               reference     lookup tables, not method
#             The set is CLOSED — routing_validate_groups() rejects anything else, because a
#             typo would otherwise render as a real fourteenth group nobody notices.
#
#             Added 2026-08-20. Several build/* groups started empty on purpose: a flat list of
#             62 skills hid the fact that this toolkit said nothing at all about workflows,
#             REST, agents, grids or build-time security. The empty group is the finding — and
#             it works: build/workflow, build/integration and build/agents were each filled by
#             a skill written because the empty heading made the hole visible.
#
#             Groups order the RENDERED tables (ROUTING.md, README's situational table). The
#             baseline views are NOT grouped by this column — sub-headings would imply a
#             selectivity the group column does not carry for baseline rows. They ARE sliced by
#             column 5 (stages): the rendered baseline table carries a Stage(s) column, and a
#             session reads a row only when its stage cell says "every stage" (column 5 was "-")
#             or names the stage the project's register says it is in. That slicing comes from
#             the stages column already on every row, so adding it did not require touching a
#             single baseline row — only the renderer.
#
# TSV rather than a markdown ROUTING.md because a renderer has to parse this in bash 3.2 on
# macOS, and several "when" strings contain the "|" that a markdown table uses as its column
# separator. ROUTING.md at the repo root is the human-readable view — rendered FROM here, so
# it can never disagree with what the scripts install. Kept in bin/lib/ next to
# install-manifest.sh (the same one-manifest-N-readers precedent) and deliberately NOT in
# skills/, which gate-check.sh treats as PROTOCOL_PATHS: a data file there would trip a
# protocol-staleness ack on every routing edit.
#
# name	path	when	agents	stages	tier	group
conversion-runbook	skills/conversion-runbook.md	Any pipeline work at all — every session, before producing any stage artifact: read §1b plus your own stage's section, not the whole file (gate-check.sh prints the line spans); READMEs and the guide are orientation only	lead,ba,architect	P,0,1,2,3,4,5,6,7	baseline	spine
runbook-slice	bin/runbook-slice.sh	Any pipeline work at all, as a helper — every dispatch, before producing anything: run the toolkit's bin/runbook-slice.sh <stage>, which prints §1b plus your stage's section of the conversion runbook; never open skills/conversion-runbook.md whole	mdl,gate,test,review	P,0,1,2,3,4,5,6,7	baseline	spine
query-the-model	skills/query-the-model.md	Any question before asking the user or writing anything — query the model, then read the source, then ask the human, in that order	all	P,0,1,2,3,4,5,6,7	baseline	spine
skills-over-scripts	skills/skills-over-scripts.md	Script or skill? Before writing any .js or bash/.sh for a check, checker, linter, gate or report, or adding a rule or regex to an existing one — judgement goes in a skill, code only fetches facts a reader cannot	all,mdl?,review?	-	baseline	spine
degrade-to-judgement	skills/degrade-to-judgement.md	Any pass whose input is missing, stale or unresolvable — before recording UNMEASURED, N/A or a silent skip: name what was missing, say what you assessed against instead, still deliver a verdict	all	-	baseline	spine
interview-protocol	skills/interview-protocol.md	Putting a question TO the user — any gate, any stage: ask in chat not in a file, two named options plus your recommendation, one batch per gate then end the turn	lead,ba,architect	P,0,1,2,3,4,5,6,7	baseline	spine
change-intake	skills/change-intake.md	The user gives feedback or asks for a change mid-project — "change X", "it also needs Y" (a field, a column, a button), a remark on a screenshot or the running app, a stakeholder's ask relayed in chat: log a CR row in PROJECT.md ## Change log BEFORE any edit, size it, then edit the highest artifact it alters (BRD, decision, architecture, wireframe), never the MDL first	lead,ba	2,3,4,5,6,7	baseline	spine
change-intake-detail	skills/change-intake-detail.md	Applying or proving a change request (CR row), a change whose class, size or status is unclear, or a "Change log:" gate line to explain: full class/size/ask tables, the wrong-vs-right example, apply and prove steps, the owners table and what the warn-only gate check counts	lead,ba,architect	2,3,4,5,6,7	ondemand	spine
grill-mode	skills/grill-mode.md	Deep, adaptive interview on one topic, on demand, when a checkpoint's 2+1 or a single question batch isn't enough	ba,architect	P,0,1,2,3,4,5,6,7	ondemand	spine
checkpoints	skills/checkpoints/checkpoint-template.md	Any stage transition — the 2+1 format every CAC uses, and the one-register rule (answers land in PROJECT.md, never in a separate state file). The seven CACs themselves are routed per stage in the situational table	lead,ba,architect	0,1,2,3,4,6,7	baseline	spine
checkpoint-scope	skills/checkpoints/checkpoint-scope.md	CAC-1, closing Stage 0 in EVERY entry mode — scope IN: full scope or a slice, and in what order. Opens with a brainstorm, not options	ba,architect	0	ondemand	spine
checkpoint-extraction	skills/checkpoints/checkpoint-extraction.md	CAC-1b, after Stage 1 — scope OUT: is what extraction produced what you meant. No gate stops you; run it late against the BRDs if it was skipped	ba	1	ondemand	spine
checkpoint-brd	skills/checkpoints/checkpoint-brd.md	CAC-2, after BRD scaffolding and before enrichment — capability grouping and enrichment order	ba	2	ondemand	spine
checkpoint-architecture	skills/checkpoints/checkpoint-architecture.md	CAC-3, after BRD validation and before architecture locks — the hidden business rules that are expensive to discover later	ba,architect	2	ondemand	spine
checkpoint-design	skills/checkpoints/checkpoint-design.md	CAC-4, after rearchitect sign-off and before any design artifact — branding and UI direction. Opens with a brainstorm	architect	3	ondemand	spine
checkpoint-build	skills/checkpoints/checkpoint-build.md	CAC-5, after design sign-off and before the build plan — build order and slice boundaries. Opens with a brainstorm	architect,mdl	4	ondemand	spine
checkpoint-cutover	skills/checkpoints/checkpoint-cutover.md	Going live / cutover: CAC-6, after Stage 6 passes and before any cutover or old-data migration step — migration mode only, and a hard gate: every answer lands CONFIRMED, no ASSUMED defaults	gate,test	6,7	ondemand	spine
agent-roles	skills/agent-roles.md	Setting up or completing a project's dev-process subagents — once, at project start, not "on demand"	lead	P,4,5	baseline	spine
dispatching	skills/dispatching.md	Starting a subagent, sending it a fix round, or reading an agent-stop notice — name the model, fresh not fork, fresh fixer not resume, coalesce notices	lead	P,1,2,3,4,5,6	baseline	spine
source-triage	skills/source-triage.md	Deciding whether to extract at all, before any BRD gets generated	ba	0	baseline	source
source-sufficiency	bin/source-sufficiency.sh	Taking in a new source — before generating anything from it. Grades what the source can support; nothing else in this toolkit reads a source	ba	0,1	baseline	source
source-ledger	bin/source-ledger.sh	Closing Stage 1, or adding files to a source folder — every inventoried file must name the artifact that consumed it (text AND embedded diagrams), or carry a waiver; blocks Stages 1–2 until it does	ba	0,1,2	baseline	source
html-to-md	bin/html-to-md.sh	HTML in the source corpus — convert once before anyone reads it: `bin/html-to-md.sh <project>` writes each page as Markdown under analysis/knowledge-base/text/ (3–10× fewer tokens than the raw export; inline images decoded to files; section list with line numbers as the read's denominator) plus documents-index.md over EVERY file, which one ledger glob mark points at. A session that opens a .html itself has skipped this	ba	0,1	baseline	source
images-to-md	bin/images-to-md.sh	Pictures in the source corpus — decks, Word files, PDFs, screenshots: one worklist of unique images with context, one description file each, coverage checked	ba	0,1,2	baseline	source
image-transcription	skills/image-transcription.md	Images to read listed by images-to-md or the documents index — describe each unique picture once, into its own file, before Stage 2 closes	all	0,1,2	ondemand	source
small-project-tier	skills/small-project-tier.md	Stage 0 sign-off when the inventory is at or under 1 module / 8 screens / 25 use cases, or the user says the app is small — declare the tier, then apply its per-stage caps and the three artifact waivers	ba,architect	0,1,2,3,4	ondemand	spine
triage-report	bin/triage-report.sh	Rendering a filled triage.md for review — the triage.html surface Stage 0 names. Renders only; the Stage 0 verdict stays with gate-check and the judgement with source-triage.md	ba	0	ondemand	source
extraction-report	bin/extraction-report.sh	Reviewing what the extraction actually produced — the Stage 1 surface, and the file the Stage 1 gate looks for. Renders a code-extracted and a document knowledge base alike, so a requirements-driven project gets the surface too; prints no zero that a second record does not agree with	ba	1	ondemand	source
question-kinds	bin/question-kinds.sh	Deciding who answers a question — before putting any batch to the user. gap/conflict/choice/user-only is what keeps a gate batch at four questions instead of 127	ba	1,2,3	baseline	spine
facts-lock	bin/facts-lock.sh	Writing BRDs, especially several in parallel — "build" before the fan-out, "check" before any BRD is called done	ba	2	baseline	requirements
brd-report	bin/brd-report.sh	Reviewing what the BRDs actually say — the Stage 2 surface, for BRDs from any source. Reads every knowledge base at once, and keeps a section that is absent-because-not-applicable apart from one that is absent-because-expected	ba	2	ondemand	requirements
module-brief	skills/module-brief.md	Building any module — before the first script. The mdl-agent's single per-module input	ba,mdl	4,5	baseline	requirements
learned-mdl-preflight	skills/learned-mdl-preflight.md	Writing ANY MDL script — before the first line. Step 0 picks the write mode, then the STOP table overrides it for corrupting operations	mdl?	5	baseline	build/mdl
mdl-rules	bin/mdl-rules.sh	Writing ANY MDL script — before the first line: run bin/mdl-rules.sh <kinds> (page, microflow, access, workflow, entity) or --for <draft.mdl>, or read skills/generated/rules-<kind>.md, and read ALL of it — the STOP rows, gotchas and preflight sections for the statement kinds the script writes; your PREFLIGHT reports "STOP rows for kinds K: n/n checked"	mdl	5,6	baseline	build/mdl
module-folder-convention	skills/module-folder-convention.md	Placing any document in a module — before the first `create`. Feature group, then Pages/Microflows/Services/Resources; the path comes from the brief's folder plan, and the table says which types mxcli can actually place	architect,mdl	4,5	baseline	architecture
learned-microflow-patterns	skills/learned-microflow-patterns.md	Writing or fixing any microflow — MDL gotchas plus annotation discipline	mdl	5	ondemand	build/mdl
microflow-preflight	skills/microflow-preflight.md	Writing a microflow with any loop, a retrieve/commit/call inside a loop, nested or multiple loops, >20 activities counting loop bodies, or a list built from a list — post the checklist before the first MDL line	mdl	5	ondemand	build/mdl
mendix-best-practices-index	skills/mendix-best-practices-index.md	Asked "is there a Mendix best practice for this", or mapping a lint rule that rose in the ratchet back to the practice and the skill that prevents it — one row per area: Mendix docs page, bundled assess-quality section, toolkit skill before the write, lint rule after exec	all	3,5,6	ondemand	reference
ui-preflight-pages	skills/ui-preflight-pages.md	Building any page or snippet — before the first widget. Wireframe, tokens, gallery reuse, cross-check; no wireframe means STOP	mdl	5	ondemand	design
design-spacing	skills/design-spacing.md	Writing or reviewing any page or snippet — the spacing scale (8/16/24/32/48), section rhythm, and the page-header scaffold every full page starts with; sections at 0px apart and pages with no H1 are the defects it retires	mdl?,review	5	baseline	design
learned-stylegallery	skills/learned-stylegallery.md	Building or using the in-app design gallery	mdl	5	ondemand	design
ui-loop	skills/ui-loop.md	After every page-building script, and any time the UI looks wrong — the cheap repeatable look during the build: one page, one screenshot, four questions, scored when a wireframe exists. Feeds Gate: UI, never replaces it	mdl?,review	5	baseline	design
check-design-portability	project-bin/check-design-portability.sh	Before porting ds.css into SCSS, and at the Stage-3 gate — greps the stylesheet for rules that cannot match the HTML Mendix emits (rem against the real root, table/th/td selectors, positional row selectors). mx check, mxcli check and mxcli lint are all blind to CSS	architect,mdl,gate	3,5	ondemand	design
check-design-reaches-app	project-bin/check-design-reaches-app.sh	After the FIRST build that follows any design-system port, and before any page is built on it — reads the BUILT stylesheet and reports how many framework knobs point at a design token, how many tokens arrived, how many component classes arrived, each with its denominator. Measured on a real run: 55 tokens ported correctly into the right file, 0 of 35 knobs bound and 0 of 20 classes present, two build phases shipped in the framework's default blue with mx check, mxcli lint, the MDL suite and two e2e journeys all green	architect,mdl,gate,review	3,5	baseline	design
check-page-shell	project-bin/check-page-shell.sh	Before exec'ing ANY page script — compares the drafted MDL's shell against the wireframe's: page column, layout/nav shell, one H1. Measured 0/10 pages on a real first build, repaired wholesale 47 scripts later	mdl,gate,review	5	baseline	design
page-fidelity	project-bin/page-fidelity.js	After drafting and again after exec'ing any page script — scores the page MDL (or `mxcli describe` output on stdin) against its wireframe: headings/actions/content/classes, weighted. The scored companion to check-page-shell's binary gate; 32% median measured without it, 90% first-draft with it. Every run is appended to the project's docs/PAGE-FIDELITY.tsv — first non-stub row per page = first-build score of record vs the ≥80% target (forward-reference stubs score with --stub, exempt)	mdl,gate,review	5	baseline	design
assemble-prototype	project-bin/assemble-prototype.js	After every wireframe edit: assembles design/wireframes/*.html into design/prototype.html, one hash-routed page a stakeholder can click through instead of twenty separate files. Generated, never edited (design-artifacts.md Step 3). Before the Stage 3 sign-off question, review-agent LOOKs at its output at 390/360/320/1280 px (design-artifacts.md Step 3d, obligation prototype-look)	architect,review	3	ondemand	design
check-prototype-links	project-bin/check-prototype-links.js	Before wireframes pass to the build loop, and with --brd before a BRD is signed off: dead #/route links, orphan screens, controls with no data-bind and no data-cut, BRD routes no screen has, screens no use case walks (design-artifacts.md Step 3c, brd-validation.md check 8)	architect,review	3	ondemand	design
module-review	skills/module-review.md	Is the module done? Reviewing any module before calling it done — the ONE pass, the once-over: build, gate, prove, LOOK (is it logical, does it look right, does it match our design, over every page not just the tested ones), confirm with the denominator stated	mdl?,review,test	5,6	baseline	build
exec-approval	bin/exec-approval.sh	Before any mxcli exec / exec.sh / --mcp write — ask or run? the knob decides	mdl,gate	5,6	baseline	build
context-pack	project-bin/context-pack.sh	Dispatching a build step to a helper — generate its one-file pack (the brief's Build steps row, mxcli brain brief, live DESCRIBEs, example, folder) and hand over the path instead of a reading list. Measured: 25-38% fewer tool calls and 30-41% less time, same quality; the token saving is not proven	mdl	5	ondemand	build
testing-shape	skills/testing-shape.md	Before calling any module tested, or before re-running tests after a change — what testing a module means, which re-runs a change owes (UI-only vs logic lane), and the false-green register of confirmed ways a test reports green over a broken feature	test,gate,review	5,6	baseline	verify
verify-module	project-bin/verify-module.sh	Finishing any module — before calling it done. One command that runs every instrument and keeps "instrument faulted" apart from "feature failed"; in a wired project run the installed copy at bin/verify-module.sh	mdl,gate,test,review	5,6	baseline	verify
mxcli-bugs	bug-logs/mxcli-bugs.md	Reading a whole class of tool defects (a retest, a new mxcli release, an audit) — for one CE code or symptom use bin/bug-lookup.sh instead; the ledger is too large to read whole	mdl,gate	5,6	ondemand	diagnose
bootstrap-project	skills/bootstrap-project.md	Generating a new project's CLAUDE.md — baseline routing plus project-specific facts	ba	P	ondemand	spine
cloud-dev-environment	skills/cloud-dev-environment.md	Setting up or resuming an mxcli project in a cloud/ephemeral container — the one-time setup order (mxcli download → mxcli init → init-project.sh → sources decision → push) and the commit-and-push loop that survives container reclaim	all	P	ondemand	spine
existing-app-assurance	skills/existing-app-assurance.md	Auditing or regression/e2e-testing an EXISTING app — no intake, no stages, no gates	test,review	6	ondemand	verify
existing-app-change	skills/existing-app-change.md	Changing an EXISTING Mendix app — adding a feature, altering a flow, restructuring a module — when it has no BRDs, no architecture doc and no wireframes: the knowledge base comes from the live model (Path D), stages 2–4 run over what changes plus what it touches, nothing more, and the Track B regression baseline is the precondition; audit-only stays in existing-app-assurance	ba,architect	P,0	ondemand	spine
decompose-app	skills/decompose-app.md	Splitting an existing Mendix monolith into several apps — strangler, "move module X into its own app", carving out a slice, microservices from one .mpr; choosing the cut, moving a slice by MPK, accounting for every crossing edge, or reporting the level a slice reached	lead,architect,mdl	0,3,5,6	ondemand	spine
mendix-service-seam	skills/mendix-service-seam.md	Wiring a service seam between two Mendix apps — one app's OData or REST consumed by another, replacing a stub by an external entity, joining data that lives in the other app, or choosing keys and auth for an app-to-app service	lead,architect,mdl	3,5	ondemand	build/integration
app-facts	project-bin/app-facts.sh	Collecting the facts an app dossier is written from: forces a full catalog build, module edges through the real module column, strongly connected components, describes every loop-containing microflow and parses the loop bodies; exit 2 on a stale, fast-mode or schema-incomplete catalog, never a verdict	architect,review	0,6	ondemand	architecture
app-analysis	skills/app-analysis.md	Building or refreshing the standing dossier of an EXISTING app before changing it: inventory, module dependency shape, loop risk patterns, each section with a verdict and a fault where nothing was measured (a standing document; nothing else in the toolkit reads it yet)	ba,architect,review	P,0,6	ondemand	architecture
layering-review	skills/layering-review.md	Checking whether an EXISTING app's module boundaries still hold: the layer map (bin/app-layer-map.sh) computes the order the modules would stack in and draws only the edges that point back up, so one tangle of N mutually reachable modules becomes a named list of edges with a weight and a ref kind; Stage 3 in existing-app-change mode, and the honest blast radius for a slice	architect,ba	0,3	ondemand	architecture
module-dependency-review	skills/module-dependency-review.md	Judging module tangles, bidirectional pairs, cohesion and hubs from analysis/app-facts/dependencies.json; stock graph_module_* views split names on the first dot and are not trusted	architect,review	0,6	ondemand	architecture
microflow-loop-antipatterns	skills/microflow-loop-antipatterns.md	Reading what loop bodies do (LOOP_TQ, deferred commit, nested loop, REST in loop, transaction control per item, scheduled-event reachability) from described MDL; the catalog holds top-level activities only and cannot see inside a loop	architect,review,mdl	0,5,6	ondemand	build/mdl
assess-migration	skills/assess-migration.md	Assessing or planning a migration up front, before any pipeline is chosen	ba	0	ondemand	source
migration-pipeline	skills/migration-pipeline.md	Running the extraction pipeline	ba	0,1	ondemand	source
rehost-app	skills/rehost-app.md	Rehosting an existing Mendix .mpr into a fresh app — "port this app to a clean Mendix 11 project", re-platforming or rebuilding a whole app from its own model, running pipelines/mendix-mpr/rehost-extract.sh or reading its fidelity ledger	lead,ba,mdl	0,1,5,6	ondemand	source
migrate-general	skills/migrate-general.md	Migrating from a stack that has no dedicated pipeline	ba	0	ondemand	source
migrate-outsystems	skills/migrate-outsystems.md	Migrating an OutSystems app	ba	0	ondemand	source
source-os11	skills/source-os11.md	Understanding OutSystems 11 source	ba	0,1	ondemand	source
os-xml-schema	skills/os-xml-schema.md	Reading the OutSystems XML export schema	ba	0,1	ondemand	source
source-node-express-react	skills/source-node-express-react.md	Understanding Node/Express+React source, its layout assumptions and its gaps	ba	0,1	ondemand	source
document-discovery	skills/document-discovery.md	Scanning or classifying an unstructured document folder	ba	0,1	ondemand	source
extractor-quality-loop	skills/extractor-quality-loop.md	Validating an extractor's output before its BRDs are trusted	ba	0,1	ondemand	source
qa-loop-goal-pattern	skills/qa-loop-goal-pattern.md	Validating a new stack pipeline's extraction quality	ba	0,6	ondemand	requirements
kb-generation	skills/kb-generation.md	Extracting Excel/Word/PDF specs into a knowledge base	ba	1,2	ondemand	source
brd-generation	skills/brd-generation.md	Writing or enriching a BRD JSON	ba	2	ondemand	requirements
brd-validation	skills/brd-validation.md	Validating BRDs against the code and document KB	ba	2	ondemand	requirements
architecture-blueprint	skills/architecture-blueprint.md	Diagramming target architecture — module defs, wiring, fit-gap, marketplace, security, NFRs, integrations	architect	3	ondemand	architecture
modularize-domain	skills/modularize-domain.md	Deciding module boundaries before "create module"	architect	3	ondemand	architecture
design-artifacts	skills/design-artifacts.md	Designing the brand and ONE ANNOTATED WIREFRAME PER SCREEN before building pages — the design system alone is half the deliverable	architect	3	ondemand	design
process-map	skills/process-map.md	At Stage 2 close (draft, before the questions are raised) and again after the wireframes (Stage 3 re-render), when a reviewer cannot tell where the open questions and ASSUMED decisions fit: one swimlane map per process, each step on its wireframe, every question pinned to a step (project-bin/process-map.js validate, anchor, build)	architect,review	3	ondemand	design
interaction-model	skills/interaction-model.md	Stage 3, after the role model is CONFIRMED and BEFORE THE FIRST WIREFRAME — and any time a page shows ONE object, a menu item or home page is added, or a data source retrieves the current/first record: role homes, inboxes, and per page how it is reached and which object it takes as parameter	lead,ba,architect	3	ondemand	design
brd-to-build-plan	skills/brd-to-build-plan.md	Turning BRDs plus architecture into a numbered, dependency-ordered build plan	architect	3,4	ondemand	requirements
coverage-ledger	skills/coverage-ledger.md	Building the Stage 4 coverage ledger — every requirement either claimed by a build-plan row or catalogued with a reason, never invisible	architect,gate	4	ondemand	requirements
coverage-check	bin/coverage-check.sh	Checking a coverage ledger against its BRD — every scalar leaf CLAIMED, LEDGERED, UNCLAIMED, PHANTOM or DOUBLE-CLAIMED, so coverage is measured rather than remembered	architect,gate	4	ondemand	requirements
iterative-build-loop	skills/iterative-build-loop.md	An exec.sh guard refused a write (not a permission prompt), or building a module with mxcli — verified, iterative, coverage-checklist gated; on a refusal: commit, wait or stop, never FORCE_EXEC	mdl,gate	5	ondemand	build
mdl-cookbook-microflows	skills/mdl-cookbook-microflows.md	Writing MDL microflow scripts — worked recipes	mdl	5	ondemand	build/mdl
oneshot-mdl-method	skills/build/mdl/oneshot-mdl-method.md	Writing a single MDL script that takes a project from nothing to a working vertical slice — execution order, why it is deliberately non-idempotent, the instrument hierarchy, and the silent failures that pass every check	mdl	5	ondemand	build/mdl
learned-page-patterns	skills/learned-page-patterns.md	Building and auditing Mendix pages, or starting a UI fix round across many pages — widget patterns, datasource shapes; for a round: SCSS first, four regressions to check	mdl	5	ondemand	build/pages
learned-multilingual-app	skills/learned-multilingual-app.md	Adding a second language, a language picker or a translation script — and the moment a language picker errors, shows a blank label or changes nothing: source language, enabled languages, the user's starting language, a switch a non-admin role can use	architect,mdl,review	3,5,6	ondemand	build
oneshot-page-structure-patterns	skills/oneshot-page-structure-patterns.md	Generating a whole page tree in one script — the structure patterns that survive it	mdl	5	ondemand	build/pages
mendix-agents	skills/mendix-agents.md	Building a Mendix AI agent — the agent is runtime data not a model document, so JSON import, tool microflows, knowledge base chunk loading and the runtime wiring all sit outside MDL, and mxbuild stays green when they are wrong	mdl,architect	5	ondemand	build/agents
mendix-agent-ui	skills/mendix-agent-ui.md	Embedding a copilot chat panel — the frame is yours, ConversationalUI owns the conversation; wireframe to tokens to snippet to page placement	mdl	5	ondemand	build/agents
mendix-agent-setup	skills/mendix-agent-setup.md	Standing up a project's GenAI agents in any environment — MxCloud key import, model-to-agent binding, KB indexing and the agent-answers-a-question proof are all UI-only (no MDL/SQL path), driven with Playwright; you need the resource keys handed to you as env vars first	mdl,test	5,6	ondemand	build/agents
conformance-check	project-bin/conformance-check.sh	Running the ledger rung alone — recompute every stored ledger status against the live model and catch the STALE rows that claim built for something the model no longer has	gate,review	5,6	ondemand	verify
graph-sweep	project-bin/graph-sweep.sh	Running the wiring rung alone — a module imported but never reached, an element built but wired to nothing, a boundary crossed; mxbuild and e2e are blind to all three	review,gate	5,6	ondemand	verify
test-stack-up	project-bin/test-stack-up.sh	Before any runtime test — brings the stack up unattended and PROVES the thing that answered is this project's app; --check makes it report-only	test,gate	5,6	ondemand	verify
e2e-harness-base	skills/e2e-harness-base.md	Standing up or extending the Playwright e2e harness	test	6	ondemand	verify
learned-db-assertions	skills/learned-db-assertions.md	Writing DB assertion tests that cross-check UI state against the database	test	6	ondemand	verify
fixture-seeding	skills/fixture-seeding.md	Seed data, test data, demo data or fixtures are needed, or pages come up empty — BEFORE a journey run. Explore the data structure, choose rows by use case, scan for reset/delete actions, derive and measure with project-bin/fixture-manifest.sh, interview only the residue, never seed from inside the harness	test,review	5,6	ondemand	verify
journey-proof	skills/journey-proof.md	Proving a module's user journey end-to-end — the deep form of step 3 PROVE; use whenever an instrument reports green and you cannot say what would have made it red	test,review	5,6	ondemand	verify
unhappy-path-testing	skills/unhappy-path-testing.md	Writing or running e2e cases beyond the happy journeys (blank/whitespace required fields, over-length, duplicates, cancel, double submit, wrong state, wrong role, backend down, stale write, empty search) — every case cites a requirement first, UNSPECIFIED is re-scored against house rules, GAP counts carry the denominator; runs after journey-proof and before monkey-test	test,review	5,6	ondemand	verify
monkey-test	skills/monkey-test.md	Running the fuzz/crash net on a module whose journeys are already green — and reading the result, which is NOT evidence the module works	test,review	5,6	ondemand	verify
load-test	skills/load-test.md	Load, performance or stress testing a page ("will it hold 1000 users", concurrent users, k6, JMeter) — record the real /xas/ calls with Playwright and replay them instead of correlating tokens by hand, and report what the number does NOT prove (requests vs users, empty data, whose limit was hit)	lead,test,review	5,6	ondemand	verify
unit-test	skills/unit-test.md	Writing or running a microflow unit test (.test.mdl, mxcli test, @expect) once the project or the user has decided a flow gets one — what is worth a test, equality-only asserts, --list before any run, a scratch copy so the live app survives, and a positive control that must fail	lead,mdl,test,review	5,6	ondemand	verify
e2e-locators-that-lie	skills/e2e-locators-that-lie.md	An e2e rung reports a UI defect (widget never appeared, click did nothing, screen contradicts the data, fixture count wrong) — check the locator before blaming the app: :visible, click order, poll, derived fixtures	test,review	5,6	ondemand	diagnose
learned-skill-ux-audit	skills/learned-skill-ux-audit.md	UX audit and screenshot-loop discipline	review	6	ondemand	verify
learned-skill-scope-delta	skills/learned-skill-scope-delta.md	Tracking scope delta between the BRD and the built state	review	6	ondemand	verify
company-brain	skills/company-brain.md	Setting up or wiring a COMPANY BRAIN — the private tier between the toolkit and a project for own skills, conventions, lint rules, MDL snippets and approved MPKs; and deciding whether something goes to the toolkit, the company brain or docs/brain/	all	-	ondemand	spine
close-the-loop	skills/close-the-loop.md	Cutover and retrospective — promoting proven patterns back into the toolkit	all	7	ondemand	spine
report-schema	skills/report-schema.md	Writing or reading docs/report.json — the append-only contract every instrument writes to and every renderer reads; open BEFORE building a new instrument or a second renderer	test,review,gate	5,6	ondemand	verify
harness-architecture	skills/harness-architecture.md	Installing, extending, debugging or porting the verification harness — which part owns what, which parts run standalone, and what a missing part must report	test,review	5,6	ondemand	verify
measured-claims	skills/measured-claims.md	Before citing ANY behavioural claim about the harness, the Mendix runtime or a test tool as evidence, or counting tokens from transcripts — a claim not in the register may not be cited	all	-	ondemand	spine
tool-output-is-not-ground-truth	skills/tool-output-is-not-ground-truth.md	Any time an exit code, a tool's output or a subagent's report is about to become a stated finding — verify before you conclude	all	-	baseline	diagnose
agent-permission-friction	skills/agent-permission-friction.md	Any refused, denied or blocked command — BEFORE rewriting a permission rule and before telling the user a tool is blocked. A rule matches the START of the command line, so an allowlisted tool prefixed with cd matches nothing	all	-	ondemand	diagnose
process-coherence-pass	skills/process-coherence-pass.md	Checking whether the whole journey hangs together rather than each piece — finds correctly-built components nothing reaches, which per-element conformance and UI tests both miss	review	5,6	ondemand	verify
coherence-cadence	project-bin/coherence-cadence.sh	After every module's CONFIRM stage — counts proven modules since the last cluster/full coherence pass and exits DUE once the threshold is reached, so the cadence isn't left to memory	mdl,gate,review	5,6	ondemand	verify
build-plan-status	project-bin/build-plan-status.sh	After marking a module done, or any time "how much is built vs proven" is asked — renders progress-report.html from done- prefixes and verify-module.sh/improvement-register.md, kept as two honestly separate views; --json writes architecture/build-plan.json parsed from build-plan.md's Phase headings (a plan with no Phase headings gets no file); --refresh keeps an existing build-plan.json current but never creates one	architect,gate,review	4,5,6	ondemand	build
e2e-evidence-report	skills/e2e-evidence-report.md	Turning an already-rigorous run into a narrated proof a stakeholder can trust without running anything	test,review	6	ondemand	verify
record-demo-video	skills/record-demo-video.md	Recording a narrated screen-capture demo of a running app for a human to watch — opening on the app instead of a blank frame, and keeping captions synced to the pixels	test	6	ondemand	verify
demo-recording-polish	skills/demo-recording-polish.md	A demo film someone will watch looks captured, not produced — 25 fps smear, scroll jumps, no visible pointer, a dense page nobody can read: 2x CDP screencast at 60 fps, drawn cursor and click ripple, eased scroll, and a zoom rendered afterwards from the click log (never a CSS transform in the page)	test	6	ondemand	verify
live-demo-autopilot	skills/live-demo-autopilot.md	Running a customer demo LIVE instead of a video — Playwright drives the real app through scripted scenes with captions and a control panel (pause and take over, redo, skip); off-screen or tile sign-in, session expiry, the 2.5 h trial-licence stop and the 6-session cap	test	6	ondemand	verify
share-demo-package	skills/share-demo-package.md	Sending a demo guide, screenshots or a quickstart doc OUTSIDE the repo — to a customer, prospect or reviewer: relative image paths and "the name shown above" both break the moment the file travels alone, and the usernames a login panel displays are not the ones it accepts	test,review	6,7	ondemand	verify
mpr-corruption-and-sp-load-errors	skills/mpr-corruption-and-sp-load-errors.md	Studio Pro will not load the project, or the .mpr looks gutted — recover before relaunching SP, never git checkout	mdl,gate	-	ondemand	diagnose
lint-gate	project-bin/lint-gate.sh	Running lint as a gate rather than a report — per-rule ratchet against a committed baseline, plus the crash and collapse guards that stop a blind rule passing	mdl,gate	5,6	ondemand	verify
lint-that-actually-runs	skills/lint-that-actually-runs.md	Reading a lint result, or writing/repairing any .star rule — lint's failure mode is a confident clean pass, so 0 findings is a claim needing evidence	gate,review	5,6	ondemand	verify
improvement-register	skills/improvement-register.md	Any review pass that runs more than once — module-review, coherence, monkey, wiring-sweep: findings accumulate across runs, a per-run report cannot show a trend	mdl,gate,test,review	5,6	ondemand	spine
journey-examples	skills/journey-examples.md	Writing an actual .journey.json — the worked field-by-field reference for the contract journey-proof.md argues for	test,review	5,6	ondemand	requirements
wiring-sweep	skills/wiring-sweep.md	Every module before it is called done; buttons, links or actions that do nothing when clicked — does every clickable thing actually do something; run AFTER the happy-path journey is green, never before	mdl,test,review	5,6	ondemand	verify
learned-workflow-patterns	skills/learned-workflow-patterns.md	Writing or debugging a Mendix native Workflow (CREATE WORKFLOW/USER TASK/OUTCOMES) — syntax, the 11 workflow microflow statements, DECISION vs CALL MICROFLOW, and the two corruption classes (binary-version $Type, and create-before-reference)	mdl	5	ondemand	build/workflow
workflow-structure-rules	skills/workflow-structure-rules.md	Designing or reviewing a Workflow's SHAPE before or after the MDL — where a path may end, boundary event vs event sub-process, parallel-split limits, outcome minimums, targeting from the sentence, multi-user decision methods, which edits break running instances; and any CE6689/CE1844/CE1845/MW0012 after a clean mxcli check	architect,mdl,review	3,4,5,6	ondemand	build/workflow
rest-integration-first-time-right	skills/rest-integration-first-time-right.md	Building a REST integration (consumed or published) for the first time on a project — the checks that avoid a rebuild after the first live call	mdl	4,5	ondemand	build/integration
rest-between-mendix-apps	skills/rest-between-mendix-apps.md	App-to-app REST or microservices: two or more Mendix apps you build that read each other over REST — before the contract, before the first consumer, and before calling an API tested: pull vs push, key+version rule, auth in the operation microflow (BUG-152), honest last-success/stale/"as of", one owner per fact, and the six-rung cross-app test ladder with its per-change/slice/release cadence	architect,mdl,test,review	3,4,5,6	ondemand	build/integration
multi-app-system	skills/multi-app-system.md	A SYSTEM of two or more Mendix apps — a second app joins, a decision (IdP, SSO, contract, shared module, persona list) binds more than one app, or several agent sessions build apps of one system: the system register (apps + owners, contracts + status, shared assets, mirrored cross-app decisions), one writer per .mpr, handoffs, SSO and service accounts across apps	lead,architect	-	ondemand	architecture
multi-app-release	skills/multi-app-release.md	Releasing or deploying a change that CROSSES apps — a published contract going to v2 (which order publisher and consumers deploy in), a shared module (MPK) update, or seed data used by more than one app: before the first app is changed and before the release order is written; version + content hash per app, expand/switch/contract order from contract links, Catalog one-definition-per-version, run-once data migrations, pre-release checklist	lead,architect,mdl,review	-	ondemand	build/integration
contract-check	bin/contract-check.sh	Changing anything a published contract exposes — an entity, attribute, microflow or service behind a published OData, REST or business event service — in an app that another app consumes: before exec and before merge, run bin/contract-check.sh check (and --impact <app>:<Module.Element>) over the system registry; mxcli impact/refs do not see OData exposure	architect,mdl,review	3,5,6	ondemand	build/integration
mendix-epics-api	skills/mendix-epics-api.md	Working with the Mendix Epics board programmatically — creating/reading stories and epics, updating workflow state, or integrating BRDs with the portal	ba,architect	P,0	ondemand	reference
bug-submission-checklist	skills/bug-submission-checklist.md	Preparing an mxcli/Studio Pro bug for submission — scope pinning, read-back-vs-write-path verification, gate-sensitivity negative controls, severity scoping, before it's called filable	mdl,gate,review	5,6	ondemand	diagnose
upstream-feedback	skills/upstream-feedback.md	About to open an issue, PR or discussion against mxcli or the toolkit — before drafting, choosing which repo and vehicle it belongs to	all	-	ondemand	diagnose
empty-widget-triage	skills/empty-widget-triage.md	A page/grid/list/combobox renders or shows empty ('0 to 0 of 0', blank cells, zero rows, zero options) during UI review or an e2e run — before assuming a single cause (seed, access rule, datasource, binding)	mdl,test,review	5,6	ondemand	diagnose
doctor-triage	skills/doctor-triage.md	doctor.sh reports FAIL or WARN, or someone asks whether a red setup line blocks them — check what is actually on the machine before naming a fix; a wrong-arch binary, a missing one and a broken self-check all read the same	all	-	ondemand	diagnose
sandbox-ab-tool-defect-probe	skills/sandbox-ab-tool-defect-probe.md	Suspecting an mxcli/mxbuild tool defect and deciding whether to swap a binary — proving it's version-specific without risking the real model	mdl,gate	-	ondemand	diagnose
restart-sp-reopen-and-hang-detection	skills/restart-sp-reopen-and-hang-detection.md	Restarting Studio Pro on macOS — the reopen bug, the port bug, and detecting a real hang vs a slow load	mdl,gate	-	ondemand	diagnose
learned-sidebar-collapse-icons	skills/learned-sidebar-collapse-icons.md	Building or auditing a collapsible sidebar nav — Atlas Core's collapsed state needs icons assigned per menu item or it silently clips label text	mdl	5	ondemand	build/pages
learned-popup-navigation	skills/learned-popup-navigation.md	Writing a popup page's microflow with a retry/validation-failure branch that re-shows the same popup — missing close page stacks duplicate dialogs	mdl	5	ondemand	build/mdl
learned-datagrid-customcontent-binding	skills/learned-datagrid-customcontent-binding.md	Writing MDL for a datagrid column with ShowContentAs customContent that needs to display a bound value	mdl	5	ondemand	build/mdl
learned-popup-feedback-pattern	skills/learned-popup-feedback-pattern.md	Writing ANY microflow behind a button that commits, completes a workflow task, or triggers a backend flow — popup or full page: it owes the user a message, a close, and a control that stops offering the action once done	mdl	5	ondemand	build/mdl
corpus-extraction-integrity	skills/corpus-extraction-integrity.md	Extracting structured requirements from a large delivered document corpus into per-scope knowledge-base files	ba	P,0,1	ondemand	requirements
anonymize-client-app-for-demo	skills/anonymize-client-app-for-demo.md	Turning a client-derived Mendix app into a clean, shareable demo with zero client fingerprint — branding, data, custom widgets	mdl,review	6	ondemand	build
field-run	skills/field-run.md	Driving the whole toolkit pipeline on a real source to find what the written skills don't say — the toolkit is the subject, not the app it builds	all	-	ondemand	diagnose
learned-mdl-cannot-express	skills/learned-mdl-cannot-express.md	Before a wireframe or a design commits to a WIDGET, when a requirement shows a widget to one role and not another, and when a page script hits a parse error that looks like a syntax mistake: the short list of things MDL cannot write at all, and the four-minute probe that answers it at Stage 3 instead of at build time	architect,mdl	3,5	ondemand	design
learned-css-that-never-applied	skills/learned-css-that-never-applied.md	A CSS/SCSS or style change that appears to have done nothing (a colour or class that won't show), a focus ring or outline that paints on every page landing or load, or an app still grey after a design port every instrument called green — the three ways a correct rule paints nothing (matches nothing / matches chrome / loses the cascade), the two reads that tell them apart, and the class that arrived in the stylesheet and is bound to no widget	mdl?,review,gate	5,6	baseline	design
learned-detection-gaps	skills/learned-detection-gaps.md	Before trusting a green check/exec/DESCRIBE result as proof, or when a runtime symptom appears over a fully green model — the register of constructs that pass early rungs and fail later ones	mdl?,gate,review	5,6	baseline	diagnose
learned-dg2-patterns	skills/learned-dg2-patterns.md	Building or altering any data grid — native DATAGRID vs pluggable DG2 decision rule, the ALTER PAGE INSERT corruption, sort-by and filter-binding traps	mdl	5	ondemand	build/pages
learned-file-upload-widget	skills/learned-file-upload-widget.md	Putting any file upload / attachment / document field on a page, an uploader page failing mx check with CE0463, or an uploader DESCRIBE that will not re-execute — the File Uploader MDL shape proven end to end on v0.23 and v0.24, the widgets mxcli cannot author, and the upload instrument	mdl,test	5	ondemand	build/pages
security-is-not-a-later-script	skills/security-is-not-a-later-script.md	Creating any entity, or calling a module security-ready — entity and grants land in one script, and ready means SHOW SECURITY MATRIX proves it	mdl?,gate,review	5	baseline	build/security
scriptable-sp-verification	skills/scriptable-sp-verification.md	Needing Studio Pro load evidence without a human at the GUI — direct-binary launch and log capture; a capture technique, NOT a validated pass/fail oracle	mdl,gate	-	ondemand	diagnose
learned-local-db-confusion	skills/learned-local-db-confusion.md	A runtime test or seed reads/writes data that then is not there (the test wrote a row, the DB query shows nothing), or vice versa — three local Postgres instances can answer on this box; resolve the real port from the project's own compose file first	mdl,test,gate	5,6	ondemand	diagnose
gate-check-file-locations	skills/gate-check-file-locations.md	gate-check.sh reports a Stage 0 file not found that plainly exists — ANALYSIS_BASE falls back to project root until Stage 1; move the file, do not debug the script	ba,gate	0	ondemand	diagnose
full-harness-audit	skills/full-harness-audit.md	The user asks for a full end-to-end test, a click-through proof, or does-everything-actually-work — or you are unsure which harness skill applies; this one routes you	test,review	5,6	ondemand	verify
test-result-audit	skills/test-result-audit.md	End of any build+test cycle that wrote docs/report.json — did the testing itself hold up, not just get filed; one level up from finding-disposition	test,review	5,6	ondemand	verify
finding-disposition	skills/finding-disposition.md	Any report from a test/review run is about to be published — no report ends without a disposition for every finding	test,review,gate	5,6	ondemand	verify
wizard-walkthrough	skills/wizard-walkthrough.md	Handing the human a batch of steps only they can perform (Stage 7 cutover, browser-only GitHub settings) — generate a paced confirm-and-verify walkthrough script instead of a prose checklist; hypothesis under trial, no field run yet	gate,review	P,7	experimental	verify
# THE skill-routing table — the single source of truth for every routing surface.
#
# Routing a skill used to take six coordinated edits (README's two tables, the runbook row,
# init-project.sh's CLAUDE.local.md heredoc, gate-check.sh's stage map, the agent templates)
# plus a seventh copy inside every project's CLAUDE.local.md that no script could update.
# Measured on 2026-08-18, before this file existed: 17 of 43 skills were routed by NOTHING a
# project agent reads; facts-lock.sh reached 1 of 6 wired projects; agent-roles.md and
# source-triage.md reached 1 each. Every skill added since had silently become the eighteenth.
#
# Edit THIS file, then run:  bin/render-routing.sh
# CI / gate:                 bin/render-routing.sh --check   (exit 2 == a surface has drifted)
#
# Format: TAB-separated, seven columns. Blank lines and #-comments ignored.
#   1 name    stable id (basename without .md/.sh)
#   2 path    repo-relative path of the thing to load
#   3 when    one line: "always relevant for ..." — the trigger, not a description
#   4 agents  comma list of lead|ba|architect|mdl|gate|test|review, or "all" ("all" includes lead).
#             lead = the main session: it dispatches helpers, runs gates, asks the user. It has
#             no agents/*.md stub, so a lead-only row renders into no stub on purpose. Helpers
#             never read a row that does not name them — the project baseline view carries a
#             Role(s) column for exactly that (added 2026-10-05: before it, the view filtered by
#             stage only, so a Stage 5 page helper was pointed at the lead's, the tester's and
#             the reviewer's rows too — process/context-cost-research-2026-09-30.md §1).
#   5 stages  comma list of P,0,1,2,3,4,5,6,7 (conversion-runbook stages), or "-" for none
#   6 tier    baseline     (always-on: goes into every project's CLAUDE.local.md)
#             ondemand     (situational: load when the task calls for it)
#             experimental (under trial: routed and discoverable, but _routing_stage_arm skips
#                          it on purpose, so a skill nobody has proven yet can never be the
#                          reason a gate fails)
#   7 group   which question the skill answers, NOT what kind of thing it is. One of:
#               spine         what am I doing, who decides, how do I ask
#               source        reading a legacy system (migration entry mode only)
#               requirements  what must be built
#               architecture  how it is shaped
#               design        how it looks, before any MDL
#               build         authoring the model — the loop itself
#               build/mdl     the MDL language and tool reference
#               build/pages   page-building patterns
#               build/agents  Mendix AI agents — the agent document, tools, KBs, chat UI
#               build/workflow / build/integration / build/security   (declared, still empty)
#               verify        does it work
#               diagnose      something is broken and it may be the tooling
#               reference     lookup tables, not method
#             The set is CLOSED — routing_validate_groups() rejects anything else, because a
#             typo would otherwise render as a real fourteenth group nobody notices.
#
#             Added 2026-08-20. Several build/* groups started empty on purpose: a flat list of
#             62 skills hid the fact that this toolkit said nothing at all about workflows,
#             REST, agents, grids or build-time security. The empty group is the finding — and
#             it works: build/workflow, build/integration and build/agents were each filled by
#             a skill written because the empty heading made the hole visible.
#
#             Groups order the RENDERED tables (ROUTING.md, README's situational table). The
#             baseline views are NOT grouped by this column — sub-headings would imply a
#             selectivity the group column does not carry for baseline rows. They ARE sliced by
#             column 5 (stages): the rendered baseline table carries a Stage(s) column, and a
#             session reads a row only when its stage cell says "every stage" (column 5 was "-")
#             or names the stage the project's register says it is in. That slicing comes from
#             the stages column already on every row, so adding it did not require touching a
#             single baseline row — only the renderer.
#
# TSV rather than a markdown ROUTING.md because a renderer has to parse this in bash 3.2 on
# macOS, and several "when" strings contain the "|" that a markdown table uses as its column
# separator. ROUTING.md at the repo root is the human-readable view — rendered FROM here, so
# it can never disagree with what the scripts install. Kept in bin/lib/ next to
# install-manifest.sh (the same one-manifest-N-readers precedent) and deliberately NOT in
# skills/, which gate-check.sh treats as PROTOCOL_PATHS: a data file there would trip a
# protocol-staleness ack on every routing edit.
#
handoff-to-studio-pro	skills/handoff-to-studio-pro.md	Handing a headless-built model to a person — opening it in Studio Pro, a free sandbox, or a colleague's machine: the model travels, the demo data and runtime config (keys, an agent's bound model) do not, and each needs its own re-establish step	test,review	6,7	ondemand	build
ts-sync	project-bin/ts-sync.sh	Sharing the project with a colleague on Mendix Team Server while the build loop stays on GitHub — content-transplant snapshots between the two clones (status/push/pull); SUPERSEDED by platform-link.md §3 (adopt without rewriting history, field-proven) — only if that path fails; UNPROVEN against a real Team Server	mdl,gate	6,7	experimental	build
preview-over-hub-tunnel	skills/preview-over-hub-tunnel.md	Exposing a container-run app at a public URL (mxcli run --hub) — demo/stakeholder preview: the db-name default trap, the runtime REST client ignoring JVM proxy settings (GenAI 403 "Host not in allowlist" that is really a proxy bypass), and stale-app detection	test,review	5,6	ondemand	verify
run-hub	bin/run-hub.sh	Starting a hub-tunnelled preview with the flags outbound calls actually need — wraps mxcli run --hub with db-name and the runtime proxy settings from preview-over-hub-tunnel.md	test	5,6	ondemand	verify
walking-skeleton	skills/walking-skeleton.md	Stage 5 start, before the first module of any entry mode — one entity, flow, page, nav, demo user, journey and screenshot proven in the running app, so build/run/look/test are known to work before a module depends on them	mdl,gate,test	5	ondemand	build
bug-lookup	bin/bug-lookup.sh	A CE error (mx check or mxbuild: CE0066, CE0117…), a cited BUG-n, or behavior that looks like a known mxcli quirk rather than a modeling mistake — `bin/bug-lookup.sh CE0117` / `BUG-102` / "keyword" / the whole pasted error message (ranked top 3) prints the matching ledger entries, so the session reads one entry, not the whole ledger	mdl,gate	5,6	baseline	diagnose
file-bugs	bin/file-bugs.sh	You hit, or worked around, a bug in mxcli or the toolkit, or log a FINDINGS.md entry about either — `bin/file-bugs.sh` (the `--add` line is in learned-detection-gaps.md) keeps docs/bugs.jsonl, redacts, shows duplicates, files with `--auto` when PROJECT.md says `Bug filing: auto`, else only a human files (`!`, `--file PBUG-NN`, y/N, denied to agents), or prints new-issue links (`--links`, `--json`)	mdl,gate	5,6	baseline	diagnose
status	bin/status.sh	The first command of every session, and any time someone asks "where are we" or "what next" — one screen: stage, done/overdue, the ONE next action, from the instruments, never from memory	all	P,0,1,2,3,4,5,6,7	baseline	spine
platform-link	skills/platform-link.md	At project birth (before the first build script) and any time a model needs a platform home: creating the Team Server app, adopting an existing GitHub-born model into it without rewriting history, or deploying; also when the Platform SDK returns 403, git rejects the PAT, a deploy cannot be triggered from a PAT, or the app turns out to be a Free App	all	P,5,6,7	ondemand	build
teamserver-alignment	skills/teamserver-alignment.md	Any session that will push a model to Mendix Team Server, and BEFORE telling the user a Team Server push is blocked — which remote is authoritative, settle-then-push order, and the four checks that have to fail first	mdl?,gate,review?	5,6,7	baseline	build
retesting-learned-rules	skills/retesting-learned-rules.md	Before obeying any learned-* STOP or workaround that costs a detour — probe the binary you actually have, then stamp the verdict back into the rule	all,mdl?	-	baseline	spine
deploy-to-sandbox	skills/deploy-to-sandbox.md	Promoting an app to a deployed sandbox or cloud node, or before a customer tests a deployment — "it works locally" is not evidence about a deployment; also when a test suite fails only against the remote URL	all	7	ondemand	build
learned-constants-and-secrets	skills/learned-constants-and-secrets.md	Adding a constant, installing a marketplace module, deploying to a new environment, or needing a Mendix PAT — where an encryption key, API credential, endpoint or access token gets its value, why a free node has only one channel, and why a token missing from the files you grepped is not missing	mdl,architect,gate	4,5,6	ondemand	build/integration
constants-audit	project-bin/constants-audit.sh	Before any first deploy to a new environment, and after installing or updating any marketplace module — which constants would be blank where nobody can set them, and which now carry a secret in the model. Never prints a value	mdl,gate,architect	5,6	ondemand	verify
speed-setup	skills/speed-setup.md	The user says the toolkit, an exec or the gate is slow, or asks to update the toolkit, run doctor and check whether it can be faster on their machine (werk de toolkit bij, draai doctor, controleer of het sneller kan)	lead	-	ondemand	diagnose