Evaluates ambient context artifacts (CLAUDE.md, memory, local skills, settings hooks) for compatibility with swarm governance. Returns a classified report so users can address interference before launching a team.
EnglishCreate structured, reproducible bug reports for software defects. Load when asked to file a bug, report an issue, write a defect report, or document unexpected behavior. Generates complete bug reports with steps to reproduce, expected vs actual behavior, severity classification, environment details, and evidence. Also provides templates for Jira, GitHub Issues, and Linear. Trigger phrases: "report this bug", "file a bug", "write a bug report", "this is broken", "defect report", "issue template", "bug template", "document this issue", "create a ticket".
EnglishDetects semantic code quality issues (logic, architecture, UX) that static hooks cannot catch. Provides 10 rules across 4 categories: API patterns, HTML/accessibility, architecture, and logic. Auto-triggered in Forge Dev Check 3.7Q and referenced during code review.
EnglishProfessional-grade brand voice analysis, SEO optimization, and platform-specific content frameworks.
EnglishFigma file URL을 입력받아 디자인 토큰·메타·스크린샷을 Figma MCP로 fetch하고 CLAUDE-DESIGN-PROMPTS.md + ANALYSIS-REPORT.md를 갱신하여 claude.ai/design 결과물 정합도를 향상시킨다. 트리거 — 사용자가 Figma URL과 함께 "디자인 토큰 추출", "claude.ai/design 정합도 fix", "Figma 동기화", "디자인 시스템 갱신"을 요청하거나 /figma-design-sync 슬래시 명령으로 호출할 때. Figma MCP rate limit 도달 시 Codex/Gemini Vision PNG 재분석으로 자동 폴백. 입력은 Figma URL + 대상 doc 경로 + 옵션 brand 정정 룰. 산출물은 CLAUDE-DESIGN-PROMPTS.md 토큰 갱신 + figma-export/ANALYSIS-REPORT.md 실측·diff + figma-export/variables.json 원본 + 변경 보고서. evalcases on.
EnglishGenerate and run load tests with k6, Locust, or Artillery. Auto-detects API framework, creates realistic user behavior flows (browsing, authenticated CRUD, search-heavy), runs ramp-up, sustained, spike, and stress test profiles with defined latency and error-rate thresholds, then produces a bottleneck analysis with optimization recommendations. Use when you need to benchmark API performance, find breaking points under traffic, test auto-scaling, validate SLAs, or identify slow endpoints before production deploy.
EnglishRun a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go wrong.
EnglishEssential tools and frameworks for modern product management, from discovery to delivery.
EnglishAI 하네스 엔지니어링 감사. Check Chain, OWASP Agentic Top 10, 가드레일 패턴, Hook 커버리지를 기준으로 측정·제어 역량을 평가한다.
KoreanPlanner-Generator-Evaluator 하네스. Evaluator만 subagent로 격리해 독립 검수한다. spec 없이 개발할 때 사용한다. 버그 수정은 /forge-fix.
KoreanGodBlade 게임 에셋 5 카테고리 워크플로우 오케스트레이터. /game-asset-pipeline 또는 배치 생성. AIGenerated/{Characters,Monsters,UI,Backgrounds,Effects}/ 경로 자동 라우팅. image-orchestrate 스킬 래핑. Use for: (1) GodBlade 게임 에셋 배치 생성, (2) 카테고리별 에셋 생성·관리, (3) 생성된 에셋 목록 조회. SKIP: 단일 이미지 생성(/image-orchestrate), 비-GodBlade 게임 에셋.
KoreanHWP 파일을 PDF로 변환하여 이미지/도형/표 포함 100% 읽기 가능하게 만드는 스킬. HWP 파일 분석, 한글 문서 변환, 정부과제 서류 읽기 시 자동 트리거.
KoreanQA 하네스 부트스트랩 스킬 (AD-92 Phase 0 + P0-FIX). /qa 실행 전 자동 호출되어 서버 생명주기 관리, qa-config.json 생성, DB seed 격리, API 전수 발견, scenarios.md 게이트를 준비한다. 트리거: /qa 실행 시 Phase 0 자동 진입, 또는 QA 환경 세팅, 서버 기동 후 테스트, scenarios.md 생성 요청 시.
KoreanАнализирует скриншоты мобильного приложения на L10N дефекты (переводы, CLDR форматы, RTL). Используй для проверки локализации UI, когда нужно найти ошибки в переводах, форматах дат/валют или проблемы RTL-верстки. Не используй для функционального тестирования UI или анализа кода.
Russian
AGENT SKILLS ATLASIncludes Audit Context, Bug Report, Code Quality Rules, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Audit Context
Evaluates ambient context artifacts (CLAUDE.md, memory, local skills, settings hooks) for compatibility with swarm governance. Returns a classified report so users can address interference before launching a team.
Bug Report
Create structured, reproducible bug reports for software defects. Load when asked to file a bug, report an issue, write a defect report, or document unexpected behavior. Generates complete bug reports with steps to reproduce, expected vs actual behavior, severity classification, environment details, and evidence. Also provides templates for Jira, GitHub Issues, and Linear. Trigger phrases: "report this bug", "file a bug", "write a bug report", "this is broken", "defect report", "issue template", "bug template", "document this issue", "create a ticket".
Code Quality Rules
Detects semantic code quality issues (logic, architecture, UX) that static hooks cannot catch. Provides 10 rules across 4 categories: API patterns, HTML/accessibility, architecture, and logic. Auto-triggered in Forge Dev Check 3.7Q and referenced during code review.
Content Creator
Professional-grade brand voice analysis, SEO optimization, and platform-specific content frameworks.
Design Handoff
Generate developer handoff specs from a design. Use when a design is ready for engineering and needs a spec sheet covering layout, design tokens, component props, interac
Figma Design Sync
Figma file URL을 입력받아 디자인 토큰·메타·스크린샷을 Figma MCP로 fetch하고 CLAUDE-DESIGN-PROMPTS.md + ANALYSIS-REPORT.md를 갱신하여 claude.ai/design 결과물 정합도를 향상시킨다. 트리거 — 사용자가 Figma URL과 함께 "디자인 토큰 추출", "claude.ai/design 정합도 fix", "Figma 동기화", "디자인 시스템 갱신"을 요청하거나 /figma-design-sync 슬래시 명령으로 호출할 때. Figma MCP rate limit 도달 시 Codex/Gemini Vision PNG 재분석으로 자동 폴백. 입력은 Figma URL + 대상 doc 경로 + 옵션 brand 정정 룰. 산출물은 CLAUDE-DESIGN-PROMPTS.md 토큰 갱신 + figma-export/ANALYSIS-REPORT.md 실측·diff + figma-export/variables.json 원본 + 변경 보고서. evalcases on.
Load Test
Generate and run load tests with k6, Locust, or Artillery. Auto-detects API framework, creates realistic user behavior flows (browsing, authenticated CRUD, search-heavy), runs ramp-up, sustained, spike, and stress test profiles with defined latency and error-rate thresholds, then produces a bottleneck analysis with optimization recommendations. Use when you need to benchmark API performance, find breaking points under traffic, test auto-scaling, validate SLAs, or identify slow endpoints before production deploy.
Pre Mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go wrong.
Product Manager Toolkit
Essential tools and frameworks for modern product management, from discovery to delivery.
Audit Harness
AI 하네스 엔지니어링 감사. Check Chain, OWASP Agentic Top 10, 가드레일 패턴, Hook 커버리지를 기준으로 측정·제어 역량을 평가한다.
Forge Pge
Planner-Generator-Evaluator 하네스. Evaluator만 subagent로 격리해 독립 검수한다. spec 없이 개발할 때 사용한다. 버그 수정은 /forge-fix.
Game Asset Pipeline
GodBlade 게임 에셋 5 카테고리 워크플로우 오케스트레이터. /game-asset-pipeline 또는 배치 생성. AIGenerated/{Characters,Monsters,UI,Backgrounds,Effects}/ 경로 자동 라우팅. image-orchestrate 스킬 래핑. Use for: (1) GodBlade 게임 에셋 배치 생성, (2) 카테고리별 에셋 생성·관리, (3) 생성된 에셋 목록 조회. SKIP: 단일 이미지 생성(/image-orchestrate), 비-GodBlade 게임 에셋.
Hwp2pdf
HWP 파일을 PDF로 변환하여 이미지/도형/표 포함 100% 읽기 가능하게 만드는 스킬. HWP 파일 분석, 한글 문서 변환, 정부과제 서류 읽기 시 자동 트리거.
QA Setup
QA 하네스 부트스트랩 스킬 (AD-92 Phase 0 + P0-FIX). /qa 실행 전 자동 호출되어 서버 생명주기 관리, qa-config.json 생성, DB seed 격리, API 전수 발견, scenarios.md 게이트를 준비한다. 트리거: /qa 실행 시 Phase 0 자동 진입, 또는 QA 환경 세팅, 서버 기동 후 테스트, scenarios.md 생성 요청 시.
Screenshot Analyze
Анализирует скриншоты мобильного приложения на L10N дефекты (переводы, CLDR форматы, RTL). Используй для проверки локализации UI, когда нужно найти ошибки в переводах, форматах дат/валют или проблемы RTL-верстки. Не используй для функционального тестирования UI или анализа кода.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Audit Context skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.