菜单
Detect architecture-level technical debt: coupling, cycles, boundary violations, layer leaks. Outputs findings conforming to the debt-finding schema.
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
Conventional Commits 1.0 enforcer. Two complementary modes: (1) AUTO-SUGGEST — when you say "commit", "commit my changes", "commit this", or invoke `/commit`, the skill inspects `git diff --staged`, proposes 1–3 conventional commit messages (type + optional scope + subject), and asks which one to use. You never have to remember the format. (2) VALIDATOR — every `git commit` passes through a PreToolUse hook that validates the first line of the message against the Conventional Commits regex. Non-conformant commits trigger a confirm prompt — they cannot slip through silently. Types allowed: feat, fix, refactor, perf, docs, test, chore, build, ci, style, revert. Optional scope in parentheses (lowercase kebab-case, ≤ 20 chars). Optional `!` and `BREAKING CHANGE:` footer. Use when: "commit", "commit my changes", "make a commit", "commit this", "validate commit", "/commit". Proactively invoke whenever the user says "commit" or runs `git commit` through the agent, and after a logical unit
Check for and apply AI-Native Dev Stack updates, non-destructively. Detects whether the stack repo is behind upstream, shows what changed, and fast-forwards the shared clone — without ever touching your personalized configs (CLAUDE.md, Mavis agent.md, config.sh). Use when: "upgrade the stack", "update ai-native-dev-stack", "is the stack up to date?", "get the latest rules/method". Proactively suggest at the start of a session if an update is available.
CRUD operations on the Debt Registry. Manages the active list of accepted debts, decisions, and resolution status. Persists to the KG (Layer 0).
Generate preventive rules (linters, tests, CI checks) from detected findings. Stops the same pattern from re-appearing after a fix.
Scan a codebase to detect technical debt (code, security, dependencies, tests, architecture). Orchestrate deterministic tools + LLM. Produce a `.debt-scan.json` file conforming to the schema.
Challenge every finding and plan before validation. Reduce hallucinations, force proofs, verify completeness.
| name | debt-architecture |
| description | Detect architecture-level technical debt: coupling, cycles, boundary violations, layer leaks. Outputs findings conforming to the debt-finding schema. |
Same as debt-scan — use LANG_MAP from tools/scan_code.py to identify primary language.
For each language, run the appropriate architecture scanner:
| Language | Tool | Detects |
|---|---|---|
| Python | pydeps (or custom AST walker) | Circular imports, fan-out, fan-in |
| Rust | cargo geiger + custom cycle detector | Circular crate deps, unsafe FFI |
| TypeScript/JS | dependency-cruiser (already used) | Layer violations, circular imports, reach |
| Java | jdeps + maven-dependency-plugin | Cycle detection, layer violations |
| Go | go list -f '{{.ImportPath}}' + custom cycle detector | Circular package deps |
If a tool is not available, fall back to the custom AST walker (see tools/scan_architecture.py).
Architecture findings are typed differently from code findings:
architecture, subcategory: circular_dependency)architecture, subcategory: high_coupling)architecture, subcategory: boundary_violation)architecture, subcategory: layer_leak)architecture, subcategory: god_module)Same as debt-scan — invoke skills/critic/SKILL.md on the complete list.
Each finding creates a Debt node in the KG with an affects edge to the affected Component nodes (per ADR-0023).
New architecture findings are added to the registry with:
.debt-architecture.json : findings + critic report (V1 format)report-architecture.md : human-readable summarytools/scan_architecture.py : orchestrates the scanners + custom AST walkerkg_store.py (Layer 0) : persistenceskills/critic/SKILL.md : mandatory critic.debt-architecture.json file is also written for V1 consumers