菜单
Rule enforcing canonical ID generation for all entity identifiers (FEAT, UC, SC, FR, NFR, US, ADR). All IDs must be generated via the shared script — never compute base-62 manually.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | id-generation |
| description | Rule enforcing canonical ID generation for all entity identifiers (FEAT, UC, SC, FR, NFR, US, ADR). All IDs must be generated via the shared script — never compute base-62 manually. |
All entity IDs in the PRD spec use a 4-character timestamp encoded in base-62 with a type prefix.
NEVER use sequential numeric IDs. IDs like FR-0001, UC-0002, NFR-0003 are wrong. Correct IDs look like FR-0Fy0, UC-0KTg, NFR-0L2x. Always run the script below to generate codes.
| Prefix | Entity |
|---|---|
FEAT- | Feature |
UC- | Use Case |
SC- | Scenario |
FR- | Functional Requirement |
NFR- | Non-Functional Requirement |
US- | User Story |
ADR- | Architecture Decision Record |
Always generate IDs by running the shared script. Never compute base-62 inline or manually.
node ${CLAUDE_PLUGIN_ROOT}/shared/skills/id-generation/scripts/generate-id.js [count]
The script outputs raw 4-character timestamps encoded in base-62 (e.g., 0Fy0, 0KTg, 0L2x). The caller prepends the appropriate prefix (FEAT-, UC-, SC-, FR-, NFR-, US-, or ADR-).
Do not invent IDs. Every ID must come from the script. Sequential numbers (0001, 0002) are never valid.
Before using a generated ID, check existing IDs in the relevant file for the prefix:
| Prefix | Where to check |
|---|---|
FEAT- | FEATURES.md |
UC- | USE-CASES.md |
SC- | Scenario headings in the parent UC file |
FR- / NFR- / US- | The feature's REQUIREMENTS.md |
ADR- | The feature's ARCHITECTURE.md |
If a collision is detected, re-run the script — the timestamp will have advanced, producing a new code.
Decompose a use case into ordered, independently-executable slices. Owns the slice file format — one Markdown file per slice, holding the contract surface and the test plan as language-tagged snippets and nested bullets. Referenced by /m:plan (default and cover modes) to emit the per-slice files the build consumes.
Engineering principles that bind any code Molcajete plans, builds, or reviews — integration tests as the trust contract, hexagonal default, dependency injection, 80% coverage floor, universal software craft (small functions, clear boundaries, no god files, refactor to reuse), technology-agnostic. Loaded by /m:plan and /m:build. Mirrored to the host project at `.claude/rules/principles.md` by /m:setup.
Technology-agnostic rules for the test-first build loop. Implementer and Validator role contracts, outer-edge mocking, reading specs/TECH-STACK.md, Runner Inference, coverage gate scoped to touched files, reactive refactor.
Rules and templates for the /m:setup command. One-shot foundation setup from a single project description plus codebase detection. Generates PROJECT.md, TECH-STACK.md, ACTORS.md, GLOSSARY.md, MODULES.md, DOMAINS.md, FEATURES.md, and .molcajete/settings.json.
Conventions for generating README.md files as LLM-optimized navigation documents. Covers YAML frontmatter, file tables, subdirectory tables, Mermaid diagrams, and stack-specific variants (backend, frontend, config). Used by /m:doc and the documentation task in build plans.
Status as first-class state on slices, use cases, and features. Defines the three-value enum (pending | dirty | implemented), per-level semantics, the bottom-up roll-up rule, and which command writes which level's status. Status lives on the artifact's frontmatter and is the source of truth — the CHANGELOG is for context and markers, not state.