菜单
Use when the user asks to "/constraint-generate", "generate constraint tests", "generate constraint artifact", "產生 constraint 的 test", or "generate test from constraint". Reads constraints/*.md and produces deterministic test artifacts.
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
General assisted review loop for changes — code or design artifacts (specs, plans, docs). Local reviewers answer blind and in parallel on the same unfixed diff, before any fix; the verdict names which reviewers actually ran. Convergence is each reviewer's own explicit per-round verdict, not the facilitator's round-count — the loop runs until-dry (K consecutive rounds where every live reviewer reports converged), with the facilitator owning K and the escalation-to-direction-guard decision. The roster is enrolled per host by `/review-loop:init`, which is never a precondition. For PR/MR targets a forge reviewer follows the local gate; GitHub Copilot is the built-in adapter and needs no enrollment. Findings say what would disprove them, and are reproduced before they are acted on. Never merges autonomously.
Git-native preparation & convergence — carry work forward across the gap when no human is watching, the handoff to a human, and the resume by whoever comes next. Use to prepare work before review, then converge it with the human, or run the lifecycle via `/tsugu:init`, `/tsugu:prepare`, `/tsugu:converge`, `/tsugu:prune`. Triggers on "prepare work before review", "carry work forward", "git-native preparation", "init/prepare/converge/prune", or "/tsugu". Human-triggered and schedule-wireable (wire `prepare` to a driver on the provisioned machine — local cron / `/loop` / `/schedule`). Invokes no user-installed skill by default — native git + its own built-in subagents only. Never auto-merges and never performs public coordination without approval.
Use when reviewing or refactoring React code in pre-RSC projects (classes, hooks, Redux/MobX/observable, Reselect, Immer). Applies FP-thinking rules grounded in render purity, immutable updates, and the Elm Architecture (Model, Msg, update, view, Cmd, Sub). Triggers on phrases like "review my React code", "refactor this class component", "audit hooks usage", "review this reducer", or the slash command `/old-react`. Out of scope: React Server Components, the `use(promise)` hook, `'use client'` and `'use server'` boundaries.
Use when the user asks to "review my agent", "check if this design is responsible", "who does this affect", "is this agent ethical", "think about the impact", "reflect on this skill", "examine this agent's boundaries", mentions "/kami", "kami", "civic AI", "humane intelligence", "仁工智慧", or wants a Socratic dialogue about human-AI collaboration and stewardship. Other skills may suggest reflection, but only invoke when the user explicitly agrees.
Use when the user asks to "/constraint-enforce", "enforce constraints", "run constraint tests", "跑 constraint 驗證", or "run constraint enforcement". Runs the 4-layer deterministic enforcement pipeline on generated constraint artifacts.
Use when the user asks to "/constraint-write", "write constraint", "define constraint", "幫我寫 constraint", "定義 constraint", or when the agent detects prohibition ("不能", "禁止", "must not"), obligation ("必須", "一定要", "always"), or invariant ("roundtrip", "idempotent") language in conversation and wants to suggest writing a constraint.
| name | constraint-generate |
| description | Use when the user asks to "/constraint-generate", "generate constraint tests", "generate constraint artifact", "產生 constraint 的 test", or "generate test from constraint". Reads constraints/*.md and produces deterministic test artifacts. |
You read constraint files from constraints/*.md and generate deterministic test artifacts that enforce them mechanically.
Scan constraints — read every file matching constraints/*.md. Parse YAML frontmatter (rule, kind, scope, subject, enforce) and body sections (Given, When, Then, Unless, Examples, Properties).
Understand the format — read references/constraint-format.md for the canonical constraint file structure.
Detect repo toolchain — check for package.json, tsconfig.json, dune-project, Cargo.toml, pyproject.toml, etc. to determine language and available tooling. Adapt all generated artifacts to the detected language — do not refuse non-TypeScript repos or force TypeScript output.
Select tools — read references/toolchain-matrix.md to pick the correct test runner, linter, PBT library, and mutation tool for the detected language. If the matrix has no entry for the detected language, research the ecosystem's idiomatic PBT and lint tools before generating.
Generate artifacts — for each constraint file, produce the applicable artifacts using the detected language's idiomatic tools and file conventions:
| Section | Artifact (adapt to language) |
|---|---|
| Examples table | Parameterized tests (TS: it.each, OCaml: Alcotest.test_case with concrete cases, Rust: #[test] with test cases, Python: @pytest.mark.parametrize) |
| Properties | PBT tests (TS: fast-check, OCaml: QCheck, Rust: proptest, Python: Hypothesis) |
| Prohibition + structural lint | .ast-grep/rules/*.yml or semgrep rules (check language support in toolchain-matrix) |
| Validation | Runtime validation at trust boundaries using the language's idiomatic library |
File conventions:
Generated from constraints/<RULE_ID>-<slug>.md — do not edit manually (use the language's comment syntax)*.constraint.test.ts, OCaml: test/test_<slug>_properties.ml, Rust: tests/<slug>_constraint.rs, Python: test_<slug>_constraint.py).Post-generate: verify and suggest — after generating artifacts:
/constraint-enforce for the full 4-layer enforcement pipeline. If a real violation was detected, mention it in the suggestion.