Enforce web project standards for structure, visuals, performance, security, and more

Capability skill — procedure for turning a known-open finding in docs/BUGS.md into a landed fix. No persona. Any agent may invoke this skill; the procedure itself enforces greenfield discipline — falsifying test first, blast-radius walk, minimal correct fix (not quick-hack), reviewer floor, spec updates. Previously architect-only to guard against quick hacks; the safeguards baked into this procedure plus GOVERNANCE §20 reviewer floor plus the skill-creator workflow make the restriction redundant as of round 29.

Guides developers through testing Tauri applications including unit testing with mock runtime, mocking Tauri APIs, WebDriver end-to-end testing with Selenium and WebdriverIO, and CI integration with GitHub Actions.

Diagnose recognition accuracy by aligning expected events (score_structure.json or expectedPerformance fallback) with recognizer output

SPEC document management - lifecycle, versioning, approval workflows, 50+ references, SPEC-first TDD integration

Validate and triage review findings of an implementation plan. Classify each finding using the unified taxonomy (FIX, FIX_UNCLEAR, ASK_USER, REJECT_FALSE_POSITIVE, REJECT_WONT_FIX, REJECT_ALREADY_FIXED). Reads the actual codebase to verify each finding against reality.

Use when the user wants to audit test quality, find flaky test patterns, speed up test execution, or prepare for Swift Testing migration.

>

health

Creates and manages product backlog markdown files with epics, user stories, technical stories, bugs, and spikes. Use when creating backlogs, adding epics/stories/tasks, updating story status, or when user mentions backlog, sprint planning, project management, or task tracking.

UniTask library expert specializing in allocation-free async/await patterns, coroutine migration, and Unity-optimized asynchronous programming. Masters UniTask performance optimizations, cancellation handling, and memory-efficient async operations. Use PROACTIVELY for UniTask implementation, async optimization, or coroutine replacement.

Python best practices for pentest scripts — requests sessions, error handling, output, CLI args

Write high-quality, maintainable tests for Java projects using modern best practices.

Run project tests with the right pytest flags — supports specific files, coverage, and full suite

pr-automation

>

Run a grouped, bisectable Go dependency security sweep on the Fission repo. Use when the user asks to upgrade outdated/vulnerable Go dependencies, run a dep security pass, or process CVE findings from govulncheck. Produces one commit per logical dependency group on a dedicated branch so failures are attributable and revertable.

Review code changes for async-signal-safety violations in KSCrash crash handlers, signal handlers, and monitor code. Verifies suspect system calls by reading the actual implementation in Apple's open-source repos on github.com/apple-oss-distributions rather than guessing. Use when the user asks to review a diff/branch/PR/file for signal safety, or before landing changes that touch signal handlers, Mach exception handlers, or anything reachable from `Sources/KSCrashRecording`, `Sources/KSCrashRecordingCore`, `Sources/KSCrashBootTimeMonitor`, or `Sources/KSCrashDiscSpaceMonitor`.

Guide evaluation of healthcare AI systems with domain-specific safety criteria, clinical accuracy rubrics, and score interpretation. Use when building or reviewing health/medical AI evaluations.

plan-design-review

Fast single-pass FXA-specific commit review covering security, conventions, logic/bugs, tests, and migrations. No subagents — runs directly in the main context.

>

>

Assists with Morphir release management, including pre-release verification, changelog generation, and release coordination. Use when preparing releases, checking release readiness, or managing version bumps.

Create a draft pull request targeting develop. Auto-generates PR body from design files, GitHub issues, and/or commit history. Use when opening a PR.

Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.

Full R017 verification (5+3 rounds) before commit

Turns a fuzzy feature request into spec files a coding agent can implement without guessing. Different from a PRD: the audience is an agent, the currency is technical precision, and each slice is smal

Tạo git commit với message tiếng Việt theo quy tắc trong CLAUDE.md

Commit staged changes using Graphite. Checks if on trunk and creates a new branch if needed. Updates PR title and summary after each commit.

Scaffold, audit, and manage Book_Map projects.

Monitor and report on Ralph Wiggum loop progress. Provides real-time status, iteration summaries, and progress tracking via Archon state. Use to check on running or completed loops, view iteration history, and diagnose issues.

Feature-Spezifikation für RESA erstellen

Generates commit messages and creates commits. Use when writing commit messages, committing changes, or reviewing staged changes.

Pre-publish validation checklist. Use when: preparing to publish to NuGet, validating release readiness, or running the full pre-publish pipeline. Checks version drift, AI docs, build/test/publish, changelog, security versions, and doc-audit freshness.

Live Debugger - inspect runtime argument/variable values in production by placing log probes on methods. Use when asked what values a function receives, what parameters look like at runtime, or to capture live data from running services without redeploying.

Process CEO notes from docs/CEO_NOTES.md into GitHub issues, design decisions, blog topics, and sprint items. Reads raw thoughts and turns them into actionable work.

<!--

Orquestra regras de governanca, DDD, tratamento de erros, seguranca e testes para tarefas com agentes de IA. Use quando a tarefa exigir aplicar padroes obrigatorios antes de analisar, editar ou validar codigo. Nao use para tarefas casuais sem alteracao de codigo nem para substituir skills especificas de linguagem.

Validate UI screens against Lucid Labs design system rules. Use after implementing UI components to verify adherence to brand colors, typography, layout patterns, and service board logic.

Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something

Excel 가져오기 모달의 보일러플레이트를 자동 생성합니다. useExcelImport 훅 기반. 새 가져오기 기능 추가 시 사용.

自动分析 Git 提交历史，生成规范的 PR Changelog。当用户准备提 PR、请求总结代码变更、或是要求“写一下更新日志”时，请务必优先触发本技能。

REST API design patterns for the Verendar project — resource naming, status codes, pagination, filtering, error responses. Includes mandatory Verendar conventions (ApiResponse<T>, PaginationRequest, internal endpoints, soft delete). Use this skill whenever designing or reviewing API endpoints in Verendar. Activate proactively when the user is adding a new endpoint, designing a route group, or asking about API structure.

Use when testing WCAG compliance, screen reader compatibility, keyboard navigation, ARIA attributes, or ensuring application is accessible to users with disabilities - focuses on a11y testing with axe and Playwright

Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.

Work with PrimePath's distributed computation engine across Metal GPU, CPU NEON, and multi-device networking. Use when modifying GPU shaders, load balancing, Conductor/Carriage networking, Nester Carry Chain math, or the three-gear auto-shifting engine.

Coached interview feedback session