You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 32125e3
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: .claude/skills/continue/SKILL.md
+21-19Lines changed: 21 additions & 19 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
---
2
2
name: continue
3
-
description: Resume fully autonomous work on the `main` branch and drive the per-task TDD loop. Trigger when the user says 続けて, "resume", "pick up where we left off", "/continue", "次", "go", or starts a fresh session expecting prior context. `/continue` may also be re-invoked automatically (cron / wake hook); treat every invocation as the same go signal. The full step-by-step loop spec (Step 0 → 7) lives in CLAUDE.md § Autonomous Workflow + § The only stop (single condition: user explicit stop) and is loaded into every turn's system prompt; this skill is the invocation trigger and carries the resume procedure, the Phase-boundary review chain, the subagent delegation cheatsheet, and the model-selection guidance.
3
+
description: Resume fully autonomous work on the `staging` branch and drive the per-task TDD loop. Trigger when the user says 続けて, "resume", "pick up where we left off", "/continue", "次", "go", or starts a fresh session expecting prior context. `/continue` may also be re-invoked automatically (cron / wake hook); treat every invocation as the same go signal. The full step-by-step loop spec (Step 0 → 7) lives in CLAUDE.md § Autonomous Workflow + § The only stop (single condition: user explicit stop) and is loaded into every turn's system prompt; this skill is the invocation trigger and carries the resume procedure, the Phase-boundary review chain, the subagent delegation cheatsheet, and the model-selection guidance.
4
4
---
5
5
6
6
# continue
@@ -27,14 +27,17 @@ spec is not duplicated here — CLAUDE.md is the single source.
27
27
28
28
## Resume procedure (on every session pickup)
29
29
30
-
1. Read `.dev/handover.md` (SessionStart hook already prints it;
31
-
re-read). Pay attention to any "Guardrail refresh" section —
32
-
it points at recent principle.md / CLAUDE.md spirit edits the
33
-
loop must honour.
34
-
2. Read `CLAUDE.md` § Project spirit (top section, governs all
35
-
other rules) and `.dev/principle.md` (Bad Smell catalogue +
36
-
Structural imagination phase). These two are the meta layer
37
-
the per-task loop is checked against.
30
+
1. Run `project workflow catchup`. It drains the axioms and the
31
+
live kanban cards. There is no handover file: `.dev/handover.md`
32
+
was retired on 2026-09-11 (memory `20260910235746-74389f7f`), so
33
+
any older text that points at it, or at its "First task on
34
+
resume", is stale.
35
+
2. Read `CLAUDE.md` § Project spirit (governs all other rules) and
36
+
the smell sensors it indexes in hive memory (the `bad-smell`
37
+
tag, the premises `20260911004145-29ffd52a`, structural
38
+
imagination `20260911004146-720ff81e`). `.dev/principle.md` no
39
+
longer exists. These are the meta layer the per-task loop is
0 commit comments