Test design, vulnerability assessment, and quality assurance (13.9K skills)
Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts. Use when user asks 'where are we in development', 'what stage are we in', 'full project audit'.
The English summary is being prepared. Showing the original description.
Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.
The English summary is being prepared. Showing the original description.
Brownfield onboarding — audits existing project artifacts for template format compliance (not just existence), classifies gaps by impact, and produces a numbered migration plan. Run this when joining an in-progress project or upgrading from an older template version. Distinct from /project-stage-detect (which checks what exists) — this checks whether what exists will actually work with the template's skills.
The English summary is being prepared. Showing the original description.
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.
The English summary is being prepared. Showing the original description.
Map test coverage to GDD critical paths, identify fixed bugs without regression tests, flag coverage drift from new features, and maintain tests/regression-suite.md. Run after implementing a bug fix or before a release gate.
The English summary is being prepared. Showing the original description.
Prepare a day-one patch for a game launch. Scopes, prioritises, implements, and QA-gates a focused patch addressing known issues discovered after gold master but before or immediately after public launch. Treats the patch as a mini-sprint with its own QA gate and rollback plan.
The English summary is being prepared. Showing the original description.
Audit GDD-specified content counts against implemented content. Identifies what's planned vs built.
The English summary is being prepared. Showing the original description.
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
The English summary is being prepared. Showing the original description.
Run an automated smoke test using the godot-mcp server. Launches the project, captures debug output, and checks for errors or crashes.
The English summary is being prepared. Showing the original description.
Auto-apply security basics and block deploys that would leak secrets. Never ask the user about security choices — just do it, and run a real secret scan before going live.
The English summary is being prepared. Showing the original description.
Class-based reactive state management for React (Expressive MVC). Use when writing or refactoring React state - converting useState/useEffect/useMemo hooks, fixing prop drilling, choosing state ownership (Model vs Component, has-pool domain rows, region controls), dependency snapshots, presence boundaries with get(true), providing context, async suspense, router - and when auditing a codebase for fit.
The English summary is being prepared. Showing the original description.
封面与标题 A/B：为带货短视频生成多套封面（自动挑选清晰帧或用干净素材图 + 不同标题与版式）和多组标题/文案，导出 3:4 / 9:16 封面文件和对比图，并给出 A/B 测试方法与记录表。Use when the user wants a video cover, 封面, 首图, thumbnail, 标题, 文案, title variants, A/B test covers for 抖音 / 视频号 / 小红书 / TikTok, or wants to improve click-through rate.
The English summary is being prepared. Showing the original description.
Turn the generated release notes into the ones a release publishes. Generates the entries with script/release-notes, then merges entries that describe one change, drops work that never shipped and internal changes, rewrites entries into one consistent voice, and writes the Highlights and Upgrading sections, with an audit that accounts for every generated entry. Use before tagging a release, or when asked to draft, clean up or review release notes.
The English summary is being prepared. Showing the original description.
Check project progress, show context, and route to next action (execute or plan). Use --forensic to append a 6-check integrity audit after the standard report.
The English summary is being prepared. Showing the original description.
Retroactively audit and fill Nyquist validation gaps for a completed phase
The English summary is being prepared. Showing the original description.
Create phases to close all gaps identified by milestone audit
The English summary is being prepared. Showing the original description.
Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan
The English summary is being prepared. Showing the original description.
Cross-phase audit of all outstanding UAT and verification items
The English summary is being prepared. Showing the original description.
Generate tests for a completed phase based on UAT criteria and implementation
The English summary is being prepared. Showing the original description.
Audit milestone completion against original intent before archiving
The English summary is being prepared. Showing the original description.
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
The English summary is being prepared. Showing the original description.
Full repository maintenance pipeline that orchestrates all project agents in sequence - code review, accessibility, bundle size, security, API stability, test coverage, ecosystem, and release preparation. Acts as a quality gate before publishing or merging major changes. Use when: maintenance, health check, pre-release audit, quality gate, full pipeline, repo health, pre-merge check, release readiness, audit all.
The English summary is being prepared. Showing the original description.
Cut a new timepicker-ui release. Use when the user wants to bump the version, prepare a release, write/update the changelog, or sync version + changelog across README, CHANGELOG.md and the docs-app (changelog/what's-new/version strings). Drives the build-release subagent in an audit → approve → apply flow, then runs a sanity build. Does NOT git-commit/tag or npm-publish — proposes those for the user to run.
The English summary is being prepared. Showing the original description.
Audit and improve the accessibility of the timepicker-ui LIBRARY (app/src) - ARIA, keyboard operability, focus trap/management, screen-reader announcements, labels - against WCAG 2.2 AA and the WAI-ARIA Authoring Practices. Use when the user wants an a11y audit/fix of the picker itself (clock, wheel, plugins, modal, inputs). Drives the accessibility subagent in an audit → approve → apply flow. Does NOT cover docs-app (use /docs-a11y for that).
The English summary is being prepared. Showing the original description.