chore(release): merge dev into main — all audit fixes complete

Author: Adityaraj0421

.github/ISSUE_TEMPLATE/bug_report.md

@@ -6,7 +6,7 @@ labels: bug
 
 ## Environment
 
-- Weave version: [e.g. 0.1.0]
+- Weave version: [e.g. 1.0.0]
 - Python version: [e.g. 3.11.4]
 - OS: [e.g. macOS 14, Ubuntu 22.04]
 - Platform adapter in use: [e.g. claude_code, cursor, codex, windsurf]

README.md

@@ -21,10 +21,18 @@ Weave ingests skills from AI coding tools (Claude Code, Cursor, Codex, Windsurf)
 
 ![Weave demo](https://raw.githubusercontent.com/Adityaraj0421/weave-compose/main/demo.gif)
 
-<!-- demo.gif is generated by running: brew install vhs && vhs demo.tape -->
-<!-- Record and commit demo.gif to the repo root to activate this image. -->
+<details>
+<summary>Record your own terminal demo</summary>
 
-> Record your own: `brew install vhs && vhs demo.tape`
+Install [VHS](https://github.com/charmbracelet/vhs) and run:
+
+```bash
+brew install vhs
+vhs demo.tape
+```
+
+The `demo.tape` script in the repo root records all five CLI commands and saves `demo.gif`.
+</details>
 
 ---
 
@@ -102,13 +110,42 @@ weave query "build a feature" --top 2
 
 ---
 
+## FAQ
+
+**Does Weave call any AI API or send data to the cloud?**
+No. Weave never calls any AI API. All embeddings run locally via `sentence-transformers`. No telemetry, no network calls after the model is cached.
+
+**Where is my session stored?**
+In `.weave_session.json` in your current working directory. It is created by `weave load` and read by `weave query`, `weave list`, and `weave status`. It is never committed — it is in `.gitignore` by default.
+
+**Does it work offline?**
+Yes, after the first run. The embedding model (`all-MiniLM-L6-v2`, ~80 MB) is downloaded from HuggingFace on first use and cached at `~/.cache/huggingface/`. All subsequent runs are fully offline.
+
+**Can I use Weave with Gemini CLI?**
+A Gemini CLI adapter is not yet included — the entry in `weave/core/adapters/` is a stub. It is the top community contribution priority. See [docs/adapters.md](docs/adapters.md) to write one.
+
+**How do I add support for a custom platform?**
+Subclass `BaseAdapter` in `weave/core/adapters/`, implement `load(path)` and `detect(path)`, then register it in `weave/core/detector.py`. The full guide is in [docs/adapters.md](docs/adapters.md).
+
+---
+
+## Learn More
+
+- [Full changelog](CHANGELOG.md) — every release, what changed and why
+- [GitHub Releases](https://github.com/Adityaraj0421/weave-compose/releases) — tagged release notes
+- [Known limitations](docs/limitations.md) — documented gaps before you file an issue
+- [Project roadmap](docs/roadmap.md) — what shipped and what's coming next
+
+---
+
 ## Contributing
 
 Contributions are welcome at every layer — new platform adapters, composition strategies, CLI improvements, and documentation.
 
 - **Contributor guide:** [docs/contributing.md](docs/contributing.md)
 - **Writing a new adapter:** [docs/adapters.md](docs/adapters.md)
 - **Architecture overview:** [docs/architecture.md](docs/architecture.md)
+- **Inter-skill protocol spec:** [docs/protocol.md](docs/protocol.md)
 
 All code must pass `pytest`, `ruff check .`, and `mypy --strict .` before merging.
 
@@ -117,3 +154,7 @@ All code must pass `pytest`, `ruff check .`, and `mypy --strict .` before mergin
 ## License
 
 MIT — see [LICENSE](LICENSE).
+
+---
+
+See [CHANGELOG.md](CHANGELOG.md) for the full release history.

docs/architecture.md

@@ -84,7 +84,7 @@ The `Skill` dataclass in `weave/core/schema.py` is the lingua franca of the enti
 
 ### Output Interfaces
 
-The CLI (`weave/cli/main.py`, built with `typer`) is the primary interface in v0.1. It exposes `weave load`, `weave query`, `weave list`, `weave status`, `weave clear`, `weave detect`, and `weave run`. A local FastAPI server (`weave/server/`) and React UI (`ui/`) are added in Phase 4, but they consume the same selector + composer pipeline — the core is interface-agnostic.
+The CLI (`weave/cli/main.py`, built with `typer`) is the primary interface. It exposes `weave load`, `weave query`, `weave list`, `weave status`, `weave clear`, `weave detect`, `weave run`, and `weave serve`. A local FastAPI server (`weave/server/`) and React UI (`ui/`) are also available — all three consume the same selector + composer pipeline, making the core fully interface-agnostic.
 
 ---
 
@@ -115,3 +115,11 @@ Tracing a single `weave query "design a button component"` call:
 ```
 
 **Key performance property:** embedding runs once at `weave load` time. `weave query` only embeds the short query string — not the skills. This makes repeated queries fast even with large skill registries.
+
+---
+
+## Inter-Skill Protocol
+
+Phase 5 introduces an inter-skill protocol that allows skills to discover and call each other without human involvement. Skills advertise capabilities via a `weave.skill.json` sidecar manifest and can declare dependencies on other skills. The Weave runtime resolves dependencies at load time and injects dependency contexts at a lower weight alongside the primary skill.
+
+See [docs/protocol.md](protocol.md) for the full protocol specification, JSON schema, and request/response format.