web-abin/OpenGeno / skills/geno-init
geno-init
UnverifiedInitialize an OpenGeno feature tree for a project. Asks the user to pick a documentation language (English or Chinese, default English), a drift mode, and a generation mode (stub-only by default, or one-shot full docs that fills every L3 section now). Scans the codebase, proposes a module breakdown, generates the L1 root index, L2 module indexes and L3 feature docs in the chosen language, writes .feat-tree.json, and injects the OpenGeno workflow rules into CLAUDE.md (and AGENTS.md if present). Use when starting OpenGeno on a new project. Run once per project.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.6 KB |
| reference.md | markdown | 10.1 KB |
| scripts/drift-check.shexecutable | script | 2.8 KB |
| scripts/post-edit-warn.shexecutable | script | 1.9 KB |
| scripts/stop-check.shexecutable | script | 2.8 KB |
| templates/claude-md-injection.md | markdown | 3.7 KB |
| templates/claude-md-injection.zh.md | markdown | 3.6 KB |
| templates/feat-tree.json | config | 93 B |
| templates/feature-logic.md | markdown | 1.2 KB |
| templates/feature-logic.zh.md | markdown | 1.1 KB |
| templates/feature-ui.md | markdown | 2.1 KB |
| templates/feature-ui.zh.md | markdown | 2.0 KB |
| templates/module-index.md | markdown | 1.1 KB |
| templates/module-index.zh.md | markdown | 1011 B |
| templates/root-index.md | markdown | 1.4 KB |
| templates/root-index.zh.md | markdown | 1.3 KB |
templates/claude-md-injection.md
View on GitHub<!-- BEGIN OpenGeno -->
## Feature documentation (OpenGeno)
This project uses [OpenGeno](https://github.com/web-abin/OpenGeno) to
maintain a hierarchical living-doc tree under `feat-tree/`. The tree is
the source of truth for user-visible behavior of every feature.
**Doc language: English.** When you create or update any file under
`feat-tree/`, write all prose, headings, comments, and frontmatter values
in English. Do not mix languages within the tree.
### Read before changing
Before changing **user-visible behavior** of an existing feature:
1. Read `feat-tree/index.md` to find the relevant module.
2. Read `feat-tree/<module>/index.md` (L2) to find the specific feature.
3. Read the feature's L3 doc (`feat-tree/<module>/<feature>.md`) before
editing any code.
4. If you can't locate the feature in the tree but you're changing its
behavior, **stop and create the L3 doc first** (see "Add a new
feature" below). Modifying an undocumented feature creates permanent
doc debt.
5. Default cross-link depth is **one hop**. Don't recurse through cross
references unless you have a specific reason.
### Update after changing
In the **same session** that you change feature behavior:
1. Re-read the L3 doc for that feature.
2. Walk it section by section, edit only the sections that diverged.
3. If you added/removed an outgoing cross-feature link, also update the
linked-to doc's "Cross-feature links" section to reflect the new
incoming reference.
4. Set `last_synced_commit:` to current `git rev-parse HEAD`. Set
`last_reviewed:` to today.
5. **Critical:** only bump `last_synced_commit` if you actually re-read
the touched code in this session. Bumping the SHA without verification
destroys the entire system. If unsure, leave it stale and let
`/geno-sync` flag it later.
### What changes trigger a doc update?
| Change | Update doc? |
|--------|-------------|
| Add / remove user-visible behavior | **Required** |
| Change interaction flow, layout, animation | **Required** |
| Change business logic branches | **Required** |
| Add / remove cross-module dependency | **Required (both sides)** |
| Bug fix where new code matches existing doc | No |
| Bug fix that changed behavior (even toward "right") | **Required** |
| Refactor / rename — same behavior | No |
| Performance optimization — same behavior | No |
| i18n / copy / theme tweaks | No |
Rule of thumb: would a user notice? If yes → update.
### Add a new feature
When implementing a brand-new feature:
1. Decide its module (existing or new).
2. Pick the right template from your installed OpenGeno skill:
- UI feature → `templates/feature-ui.md`
- Logic feature → `templates/feature-logic.md`
3. Create `feat-tree/<module>/<feature>.md` from the template, fill in
real content (wireframe, interactions / triggers, logic, state, edge
cases, cross-links). Do NOT leave `TODO` placeholders.
4. Append a row to `feat-tree/<module>/index.md` under "Features".
5. If reachable from existing features, update those features' L3 docs
to add the new outgoing cross-link.
6. Leave `last_synced_commit: ""` empty until the implementation lands —
then update it as part of the normal "update after changing" flow.
### Suspect drift
If you suspect the tree is out of sync with code (after merging a
branch, after a vibe-coding session, after manual edits outside this
workflow), invoke `/geno-sync`.
### What does NOT belong in the tree
The following are infrastructure, not features. They belong in code
comments, ADRs, or this CLAUDE.md — not in `feat-tree/`:
- i18n / translations
- Analytics / telemetry
- Build tooling, CI/CD
- Error reporting (Sentry, etc.)
- Logging
- Pure utility helpers
- Theme primitives (color tokens, typography scales)
<!-- END OpenGeno -->
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |