Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement…
EnglishEnterprise-grade browser automation using WebDriver protocol. Use when the user needs to automate web browsers, perform web scraping, test web applications, fill forms, take screenshots, monitor performance, or execute multi-step browser workflows. Supports Chrome, Firefox, and Edge with connection pooling and health management.
EnglishGenerate a complete book cover set (ebook, print, audiobook, social) with a rich visual…
EnglishStructured decision-making framework — weigh options, evaluate trade-offs, deliver clear…
EnglishStrategies for handling subagent failures with retry logic and escalation patterns.
EnglishManage user scripts and automated processes — start, stop, restart, monitor, view…
EnglishGraduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.
EnglishDeep research before planning. Launches parallel agents to search docs, web, and codebase, then synthesizes findings into actionable context.
EnglishIntelligent task decomposition and planning engine. Use when task complexity > 5, involves multiple steps, or requires coordination across multiple skills.
EnglishUse when receiving structured JSON data from tool results (API responses, database queries, email lists, calendar events) or when presenting structured data to the user. Triggers on any tool output containing arrays of objects or tabular data.
EnglishManage your author website — auto-publish books on completion, draft blog posts from your projects, render and deploy with one…
EnglishUse when the user says "write me a...", "draft a...", "create a...", "I need a...", "compose a...", "write an email", "draft a blog post", "create a report", "write a LinkedIn post", "draft a presentation", "write web copy", "compose a memo", or wants any non-code text written from scratch. Handles 9 writing domains: email, blog, web copy, business report, research/academic, presentation, prose/essay, technical docs, and social media. Gathers context before writing, avoids AI writing patterns, and optionally writes in the user's voice profile.
EnglishAnalyse et améliore un prompt existant pour obtenir de meilleurs résultats avec un LLM.
French
AGENT SKILLS ATLASIncludes After Action Review, Browser Automation, Cover Designer, 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
After Action Review
Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop
Browser Automation
Enterprise-grade browser automation using WebDriver protocol. Use when the user needs to automate web browsers, perform web scraping, test web applications, fill forms, take screenshots, monitor performance, or execute multi-step browser workflows. Supports Chrome, Firefox, and Edge with connection pooling and health management.
Cover Designer
Generate a complete book cover set (ebook, print, audiobook, social) with a rich visual brief
Decision Maker
Structured decision-making framework — weigh options, evaluate trade-offs, deliver clear recommendations
Error Recovery
Strategies for handling subagent failures with retry logic and escalation patterns.
Market Research
Research market size, trends, and dynamics for pitches or strategy
Orchestrator Mgmt
Manage user scripts and automated processes — start, stop, restart, monitor, view logs
Promote
Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.
Research
Deep research before planning. Launches parallel agents to search docs, web, and codebase, then synthesizes findings into actionable context.
Task Planner
Intelligent task decomposition and planning engine. Use when task complexity > 5, involves multiple steps, or requires coordination across multiple skills. Keywords: implement, develop, build, create, 实现, 开发, 构建, 设计
Toon Formatting
Use when receiving structured JSON data from tool results (API responses, database queries, email lists, calendar events) or when presenting structured data to the user. Triggers on any tool output containing arrays of objects or tabular data.
Website Publisher
Manage your author website — auto-publish books on completion, draft blog posts from your projects, render and deploy with one command
Write
Use when the user says "write me a...", "draft a...", "create a...", "I need a...", "compose a...", "write an email", "draft a blog post", "create a report", "write a LinkedIn post", "draft a presentation", "write web copy", "compose a memo", or wants any non-code text written from scratch. Handles 9 writing domains: email, blog, web copy, business report, research/academic, presentation, prose/essay, technical docs, and social media. Gathers context before writing, avoids AI writing patterns, and optionally writes in the user's voice profile.
Full Pipeline
연예인 화장품 숏폼 콘텐츠 전체 파이프라인. 연예인명만 입력하면 리서치부터 포스팅 최적화까지 모든 단계를 자동으로 실행합니다. (팀 에이전트 기반)
Prompt Optimizer
Analyse et améliore un prompt existant pour obtenir de meilleurs résultats avec un LLM. À utiliser quand l'utilisateur a un prompt qui ne donne pas les résultats voulus o
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 After Action Review 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.
- Reported license for the skills shown: MIT. The author’s terms apply.