ar9av
4bf87a8d19
Two strands of work. Session brain — a topic graph over raw agent session history, so you can find the session where something happened instead of remembering its UUID. Reads every Claude transcript plus the pruned sessions that survive only as prompts in history.jsonl, clusters them with local TF-IDF and community detection (no embeddings, no API calls, no new dependencies), and writes a sidecar at ~/.claude/session-brain/ — the vault is never touched. Ships five modules, the sessions-* CLI commands, an interactive graph.html, and the /session-brain and /wiki-sessions skills. This is retrieval, deliberately distinct from wiki-history-ingest, which distils sessions into permanent vault pages. Docs — README.md was 598 lines and put trust-check flags and a 17-row agent matrix in front of anyone evaluating the project. Cut it to a 129- line landing page (problem statement, 60-second install, four blocks of runnable commands, graph screenshot, why-not-a-notes-folder) and move the reference material into docs/: installation, agents, skills, cli, configuration, architecture, session-brain, contributing. README_TW.md mirrors the new structure; docs/ stays English-only for now. The restructure also closed real drift: - Ten skills existed but appeared in no reference — session-brain, session-search, wiki-dedup, wiki-digest, wiki-import, wiki-context-pack, wiki-stage-commit, wiki-switch, vault-skill-factory, and obsidian-layout-adjustment. - SETUP.md listed 12 of 39 skills and still claimed "no scripts, no dependencies" despite the pip package. It is now a signpost into docs/. - Eight config variables were undocumented anywhere, including WIKI_STAGED_WRITES, which wiki-setup prompts for and three skills read. Added to .env.example and docs/configuration.md. - sessions-name and a number of CLI flags were missing from the docs. Two details worth noting. README links are absolute GitHub URLs because pyproject sets readme = "README.md" as the PyPI long_description, and PyPI resolves relative hrefs against pypi.org rather than the repo — docs/ links would have 404'd on the package page. And three doc-drift guards asserted their facts against README.md; since those facts moved rather than disappeared, the assertions were repointed at the page that now owns each one instead of padding content back into the README. Also gitignore /vault/ (a local knowledge vault, not a fixture) and the packed browser extension. Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2.4 KiB
Contributing
This is early. The skills work, but there's room to make the brain smarter: better cross-referencing, sharper deduplication, bigger vaults, new ingest sources. If you've been chewing on this problem or have a workflow that could be a skill, PRs are welcome.
Adding a new skill
- Create a folder in
.skills/your-skill-name/ - Add a
SKILL.mdwith YAML frontmatter (name,description) and markdown instructions - Run
bash setup.shto symlink it into every agent directory - Test by saying something to your agent that matches the description
The description is load-bearing — it's the only thing an agent sees when deciding whether your skill is relevant. Write it as a list of the phrases a user would actually say, and state what the skill is not for when it's easily confused with a neighbour.
See .skills/skill-creator/SKILL.md for the full guide, or just ask your agent to run /skill-creator.
When you add a skill, also add it to the skills reference and the routing table in AGENTS.md.
Keeping both READMEs in sync
README.md (English) and README_TW.md (Traditional Chinese) are one documentation surface. Keep headings, examples, links, and user-facing behavior structurally and semantically aligned.
Syncing is advisory, not a merge gate — the readme-translation-drift CI job only reports when the translation falls behind. To catch up:
python tools/check_readme_sync.py
It lists the commits that changed README.md without a later README_TW.md update, plus the pending English diff. Translate and backfill those into README_TW.md. Reviewers assess translation quality.
The docs/ pages are English-only for now.
Repo conventions
.skills/is the source of truth. Everything else —.claude/skills/,~/.codex/skills/, and so on — is symlinks created by setup. Never edit a symlinked copy.CLAUDE.md,GEMINI.md, and.hermes.mdare symlinks toAGENTS.md. EditAGENTS.md.- New config variables belong in three places:
.env.example,docs/configuration.md, and the skill that reads them. - New CLI subcommands belong in
docs/cli.md.
Tests
pytest
Tests live in tests/. Skill behavior that can be asserted deterministically (config resolution, manifest handling, graph math, session indexing) has coverage there; the LLM-driven parts don't.