测试设计、漏洞检测、质量保证（1.3万 个）
Recommends against using a random cortisol level to diagnose adrenal insufficiency. Triggers when considering a random cortisol test for AI evaluation (e.g., "random cortisol measurement being considered for AI diagnosis").
中文简介正在准备中。当前显示原文说明。
Execute a swarm plan wave by wave with filesystem isolation via git worktrees. For each wave, main context decides the scenario recipe + implementation contract for every task, then spawns one swarm-worker per task in parallel. Each worker executes its recipe and reports JSON status. Worktree merge-audit verifies write-set discipline before changes land on main. Aborts remaining waves on any audit or task failure.
中文简介正在准备中。当前显示原文说明。
Contract document for the binding test verdict file at .claude/state/last_test_result. Format spec for callers (integrate, simplify, chore, the verify-tick worker) that inline the four mechanical operations. Not Skill-tool-invocable.
中文简介正在准备中。当前显示原文说明。
Workflow track for tasks that need no TDD — documentation edits, governance count bumps, vendored-skill content updates, configuration tweaks, formatting, typo fixes, dependency bumps where no project code changes. Skips `/scenario` and `/implement` (no failing test to drive) and runs the work directly. `archive`, `memory-sync`, `/grant-commit`, and `/commit` remain mandatory. `verify`, `simplify`, `integrate`, and `document` are conditional — required when the diff hits one of the listed triggers, optional otherwise. `verify` is skipped only when the diff is pure-docs/prose AND `project.json → test.kind` is `behavior` (absent/invalid `test.kind` → `structural` → verify runs). Chore is a stripped-down pipeline, not a bypass; never silently skip a conditional phase whose triggers apply.
中文简介正在准备中。当前显示原文说明。
Power batch-sprint helper — hosts the two behaviours that distinguish the `power` workflow track from spec-entry. (1) Per-ticket iteration: security runs once PER TICKET over workflow.json.tickets[] while the mechanical phases run once for the batch. (2) Commit split: at the commit phase, group the batch's working tree into ordered Conventional Commits via commit-split.mjs, closure last. Invoked within a `power`-track workflow; not a standalone feature. Opt-in via velocity.power_mode.enabled; requires git.
中文简介正在准备中。当前显示原文说明。
Draft a Root Cause Analysis for an incident, outage, or repeated test failure. Unlike intake/spec/brd, RCA is not a workflow phase — it's a standalone postmortem artifact that often precedes a bugfix intake. Output lives at `docs/rca/<slug>.md`.
中文简介正在准备中。当前显示原文说明。
Decompose an MVP vision into a sprint manifest — a prioritized feature list where every feature carries explicit done-criteria (a done-record reference, named edge tests, and a wiring test). Produces the sprint manifest that `sprint-oracle` checks for completeness. Use when planning a sprint of parallel work (Slice A of the sprint-mode epic). Not a workflow phase; the manifest it writes is the completeness contract a sprint is held to.
中文简介正在准备中。当前显示原文说明。
The sprint completeness oracle — a mechanical, exit-code-driven check that every feature in a sprint manifest is provably complete across three dimensions (a done-record reference, resolvable edge tests, and a resolvable wiring test). Fails loud with a per-feature gap list naming the missing dimension. Read-only. Use to gate a sprint before it is called done (Slice A of the sprint-mode epic), or any time you want a completeness reading.
中文简介正在准备中。当前显示原文说明。
Draft a Workflow Phase 4 technical spec from an intake (and optionally a BRD + scout + research memo). The spec defines how the system will change: design (C4 + UML + dependency graph in PlantUML), data, APIs, tests, rollout, rollback. Output lives at `docs/specs/<slug>.md`. Never self-approves — approval happens via `/approve-direction`.
中文简介正在准备中。当前显示原文说明。
Dev-only check that a drafted spec for THIS baseline repo won't ship dev-tree references to consumer installs. Catches three failure modes — shipped SKILL.md prose that references paths under `src/`, `tests/`, `scripts/`, `obj/` as runtime invocations (in ```bash fences``` OR `inline backticks`, plus shipped `.mjs`/`.js`/`.sh`/`.py` helper-file imports); new Python helpers added under `.claude/skills/<slug>/` (shipped helpers must be `.sh` or `.mjs`/`.js` going forward); and imports of modules that aren't in `obj/template/.claude/manifest.json` (consumer won't have the file). The aggregate scanner (`scan-shipped-skills.mjs`) walks only baseline-owned skill dirs (via `owner: baseline` frontmatter) at top level — `references/` and other subdirs are documentation, not runtime. BLOCKER findings hard-block implementation entry; ADVISORY surfaces but doesn't block. Read-only — surfaces a punch list; maintainer edits the spec and re-runs until CLEAN.
中文简介正在准备中。当前显示原文说明。
Write executable failing tests from a recipe handed to you by the main context. Used by `/tdd` Step 2 and ad-hoc when a phase needs tests-first to drive implementation. Decisions about which scenarios to cover, which categories matter, and which fixtures to use are made by the caller — this skill executes that recipe with code-structure discipline.
中文简介正在准备中。当前显示原文说明。
Write the production code that makes a pre-decided set of failing tests pass, within an explicit write_set, following an explicit behavior contract. Used by `/tdd` Step 3 and by `/swarm-dispatch` workers. The caller has already decided architecture, naming, file layout, and abstraction boundaries — this skill executes that recipe with code-structure discipline and a 5-iteration RALPH loop. No scope expansion, no design decisions, no test edits.
中文简介正在准备中。当前显示原文说明。
Drift check between the baseline implementation on disk and the claims in `docs/init/seed.md` + cross-references in CLAUDE.md, README.md, and the rendered docs site. Verifies hook/agent/skill/command names + counts, settings.json wiring, project.json key presence, .mcp.json servers, vendored license files, and helper script presence. Exit 0 PASS / 1 FAIL — suitable for CI. Read-only; safe to invoke any time.
中文简介正在准备中。当前显示原文说明。
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
中文简介正在准备中。当前显示原文说明。
Split a dirty working tree into single-concern Conventional Commits. The deterministic inventory.mjs helper groups dirty paths by concern (docs, source + paired test, config, governance); main context refines the grouping and presents a commit plan. Read-only until the user approves the plan — it never stages, never commits, never touches consent paths. Disjoint from the commit skill (Phase 11 executor): the planner proposes a split; the executor lands one consented commit. Use when a working tree has accumulated heterogeneous changes that should not land as one commit.
中文简介正在准备中。当前显示原文说明。
Workflow Phase 8 (optional) — OWASP-aligned security review of pending code changes. Produces a prioritized findings report (Critical/High/Medium/Low) mapped to OWASP Top 10 and CWE IDs. Output at `docs/security/<slug>-<date>.md`. Read-only.
中文简介正在准备中。当前显示原文说明。
Phase 10.5 — move the slug's workflow artifacts (intake, scout, research, spec, approvals, swarm state, security reports, rendered diagrams) to docs/archive/<YYYY-MM-DD>/<slug>/. Runs before /commit so the committed tree is clean of work-in-flight files. workflow.json stays live and gets archived as the first step of /commit.
中文简介正在准备中。当前显示原文说明。
Workflow Phase 9 — Integration and Verification. Runs the full test suite, stamps the binding verdict at .claude/state/last_test_result, optionally runs a cross-engine smoke check, and writes harness_state so the harness auto-continues or yields. No subagent delegation.
中文简介正在准备中。当前显示原文说明。
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
中文简介正在准备中。当前显示原文说明。
웹 테스트, 폼 입력, 스크린샷, 데이터 추출 등 브라우저 자동화. .claude/skills/playwright-cli 기준
中文简介正在准备中。当前显示原文说明。
A guided agent security review of amux, its CI/CD, and repo.
中文简介正在准备中。当前显示原文说明。
Review application and infrastructure changes for exploitable security risks by tracing assets, trust boundaries, attacker-controlled input, authorization, sensitive data, and dangerous sinks. Use for security reviews, threat-focused PR reviews, authentication or authorization changes, input handling, secrets, dependencies, and infrastructure permissions; do not use to exploit live systems or modify code unless separately requested.
中文简介正在准备中。当前显示原文说明。
Design, implement, and evaluate risk-based software tests across unit, integration, contract, end-to-end, and regression layers. Use when adding tests, reproducing bugs, improving coverage, diagnosing flaky tests, or defining a test strategy; do not use to change production behavior unless the user also requests implementation.
中文简介正在准备中。当前显示原文说明。
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
中文简介正在准备中。当前显示原文说明。