Draw reliable, well-aligned text/ASCII architecture diagrams with nested boxes, arrows, and connectors.
Terraform module design patterns, resource composition conventions, and project structure standards. Use when designing module structure, choosing resource composition patterns,…
테스트/검증이 필요할 때 사용한다. 'qa', '검증해', '테스트 돌려', 'test-fix', '심층 검증', '철저히 테스트', '보안까지 확인', '전방위 검증' 같은 요청에 반드시 사용. 기본값은 3-CLI 합의 딥 QA (기능+보안+UX). 빠른 테스트-수정 루프는 --quick.
Thoughtbox-first Theseus workflow for behavior-preserving refactors. Use this when structure changes but behavior must stay fixed and scope drift needs hard boundaries.
Deep analysis with extended thinking. Use when facing complex architectural decisions, ambiguous trade-offs, multi-system debugging, or any problem where the answer is not obvious…
Install Tilt and scaffold or audit Tiltfile + tilt/ configurations with ecosystem-aware templates. Auto-detects Java/Gradle (Spring Boot), Next.js, Python/uv, and external…
Migrate a project to a newer version of the tldraw SDK. Use when upgrading tldraw packages, fixing TypeScript errors after a tldraw upgrade, or when the user mentions tldraw…
Design the target AWS architecture — ECS Fargate / EKS / Serverless choice, VPC topology with public-private-isolated subnets, managed database selection (RDS/Aurora/DynamoDB),…
Cloudflare Named Tunnel one-click setup: install cloudflared, login, configure tunnel with custom domain, auto-detect project port, push DNS route, write to global tunnel…
Analyze Claude Code tool call patterns — success rates, duration, error frequency, and tool usage rankings from Supabase otel_events.
The correctness lens for a frontend build, organized around one question that decides whether your test suite is a safety net or a straitjacket: does this test go red when…
ockemon-pso TUI 컴포넌트/훅/패널 테스트 작성 및 실행. ink-testing-library + vitest로 테스트를 작성하고, 실패 시 진단-수정 사이클을 반복. "tui test", "TUI 테스트", "tui coverage", "test feed-panel", "test use-menu" 등으로…
ockemon-pso TUI 시각 테스트 — 렌더링 스냅샷, 인터랙션 플로우, 프레임 비교. ink-testing-library로 컴포넌트를 렌더링하고 lastFrame() 출력을 스냅샷으로 캡처. 키 입력 시뮬레이션 → 프레임 전환 검증 → 레이아웃/색상/경계 확인.
Use when: designing, reviewing, refactoring, or test-planning type-safe architecture, compiler-enforced contracts, validation-as-types, explicit interfaces, generic misuse,…
Advanced TypeScript type system patterns for production codebases. [What: branded types for nominal typing, discriminated unions, template literal types, conditional types, the…
Create, update, review, or refactor VS Code Copilot skills, hooks, and MCP configs. Use when the user wants to build or maintain reusable skills, lifecycle hooks, MCP…
Minimal / clean / Linear / Notion / Vercel / whitespace-heavy UIs. Locked knobs: CRAFT=8, MOTION=3, DENSITY=2. Monochrome + one accent, Inter/Geist, hairline borders over shadows.
Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships — from LongLeo287/SEOSONA-OS
Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships — from majiayu000/claude-skill-registry
Senior {{engine_name}}/{{engine_code_language}} developer assistant for the current {{engine_name}} project.
Iterative test-coverage improvement loop — dispatches `/optimus:unit-test` (unit-test phase) and `/optimus:refactor` with testability focus (refactor phase) into fresh subagent…
Start Unity C# development workflow with architecture, implementation, review, and testing phases
Fast-forward the coding-agent-skills clone these skills were deployed from to origin/main, then redeploy every skill: at the latest release on origin/main by default, or at main…
Generate a PR description from the current branch's changes against a GitHub PR, using the gh CLI. Use when writing, drafting, or updating pull request descriptions, PR summaries,…
Track Claude Code token usage, sessions, tool calls, lines of code, commits, and PRs per user and team. Supabase OTel queries for usage dashboards.
ตั้งค่าและใช้งาน ast-grep สำหรับ code search, lint และ refactoring ด้วย AST-based patterns — dispatcher เข้า workflows/{scan,rewrite,transform,migration}
1Password のマスタートークンを使って Cloudflare のデプロイ用 API トークン (Workers Scripts + D1) を発行し、GitHub Actions の secrets に登録する。「デプロイ用のトークンを発行して」「Cloudflare のトークンを作って設定して」「CLOUDFLARE_API_TOKEN…
Universal document consistency auditor. Runs deterministic drift checks across docs, code, tests, and CI, resolves conflicts through a per-fact-class authority registry…
Write or revise a vault markdown note with clear structure, concise summary, key points, and explicit follow-up actions.
AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing…
Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, JavaScript…
Generate comprehensive edge cases and test scenarios by decomposing features across 12 dimensions. Use before implementation or testing to catch issues early.
Use when you need publish-grade SVG or PNG technical diagrams for architecture, flow, sequence, UML, state, or comparison visuals, with preview used afterward for review rather…
Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures,…
Generate a test plan for specific code based on VCP testing standards. Produces unit tests, integration tests, edge cases, and mock guidance.
Audit a data pipeline for Veracity and Value. Dispatches data-scientist, compliance-auditor, and data-engineer agents with project context injected at dispatch time.
Cut Vercel build times for Next.js App Router projects — measure per-phase from the build log, then attack page count, duplicated type checks, and dead Turbopack-era config.
Generate optimized Vercel Edge Functions with geolocation, authentication, and data transformation — from tools-only/X-Skills
테스트 시드 인프라의 3자 SSOT 정합성을 검증합니다 — seed-data 파일 ↔ seed-test-new.ts 의 truncate/insert wiring ↔ verification.ts 의 count check 가 한 세트로 움직여야 함. 새 seed 파일 추가 후, verification.ts 편집 후 사용.
Render version hierarchies as text trees for debugging, inspection, or reporting.
This skill should be used when the user provides screenshots, videos, screen recordings, or mentions visual bugs, UI glitches, layout shifts, animation issues, or visual…
Renders planned changes as ASCII visualizations with risk heat maps, execution order diagrams, dependency graphs, impact metrics, and before/after architecture comparisons.
Use this skill whenever the user needs to perform VMware compliance auditing, baseline checking, or drift detection on vSphere/ESXi/NSX environments.
Use this skill whenever the user needs the GPU / AI-infrastructure layer of VMware Private AI Foundation with NVIDIA (PAIF-N) on vSphere 9.x / VCF 9.1: inventory GPU hosts and…
Use this skill whenever the user needs to manage VMware storage — datastores, iSCSI targets, and vSAN clusters.
Use this skill whenever the user needs to manage vSphere Kubernetes Service (VKS) — Supervisor clusters, vSphere Namespaces, and TKC cluster lifecycle.
Creates a concise engineering implementation plan saved to specs/, then generates one information-rich, thematically-consistent diagram image per section (hero + per-H2) to aid…
Watch a video (URL, local path, or SMB/UNC share) fully locally. Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, ALWAYS transcribes with faster-whisper locally and…
Static-analysis review pass over HTML/CSS/JSX/Astro source for 2026 web design anti-patterns and must-do violations.
The state-architecture lens for a frontend build — the heart of the system. Use after keel's skeleton works, when designing or auditing state, or when "it's out of sync" bugs keep…
Systematic debugging loop — reproduce, analyze root cause, fix, then challenge with a fresh verification pass to distinguish fundamental fixes from workarounds.
Build WinDAGs — the orchestration platform where AI agents accumulate genuine expertise through DAGs of skillful agents.
Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.
Add or repair an editable shared Python-package dependency across consuming projects, including clone-local configuration and verification.
Break a work-items.md file (produced by /plan-work-items) into independently-grabbable GitHub issues, one per slice, in each slice's target repo.
Structured adversarial debate between AI councillors using Agent Teams to evaluate ideas, plans, or decisions.
End-to-end live production — OBS as the mixer with obs-websocket control, MIDI/OSC cue triggers, DMX lighting sync, PTZ camera moves, system audio routing, NDI/SDI I/O, and…
Assess legacy workloads before modernization — application dependency graph, database schema, traffic patterns, RTO/RPO, compliance constraints (ISMS-P/PCI-DSS), technical debt…
Convert a WordPress website to a static site and deploy to Cloudflare Pages. Mirrors the rendered HTML via SSH, extracts only referenced assets (shrinks 1.5GB+ to ~25MB), fixes…
Writes and evaluates persuasive copy — headlines, hooks, CTAs, taglines, and landing-page sections — with per-line V/F/U rubric scoring, annotations, and ranked alternatives.