Spawn, list, inspect, and stop sub-agents through the wrapper. Sub-agent config travels as a JSON-serialized string. Flat parameter surface.
EnglishUse claude CLI for interactive AI sessions, scripting with print mode, MCP server management, and plugin configuration. Master session management, tool control, and automation workflows.
EnglishHub for the claude-cli-wrapper MCP server — execute, session, context, review, agent, and config tools. Routes to spoke skills.
EnglishCreate executable prompts for Claude Code. Use when user asks to create a prompt, generate a prompt for a task, or write a prompt for another agent.
EnglishExecute PLAN.md files using intelligent strategies based on checkpoint types. Use when user says 'execute', 'run plan', 'build it', or wants to progress from PLAN to SUMMARY.
EnglishExecute prompts from .principled/prompts/ via delegated sub-tasks. Use when user asks to run, execute, or launch prompts.
EnglishReview all git changes — triage each as ship, gitignore, or discard, then commit, push, and sync all worktrees.
EnglishManage the full project lifecycle: PLAN (create executable roadmaps) and EXECUTE (run plans with intelligent orchestration).
EnglishManage CLAUDE.md and rules — extract learnings, add rules, restructure, and review. Use when updating project conventions.
EnglishSolve complex problems by generating multiple solutions and picking the best one. Use when user says 'pick the best approach', 'compare options', or 'deep dive into a solution'.
EnglishAnalyze session transcripts to extract data, diagnose anti-patterns, and generate GitHub issues from findings.
EnglishTask lifecycle state machine — states, transitions, and task tree model. Use when you need to understand task states, dispatch subtasks, or review completions. Do NOT use for domain-specific procedures — this only covers the universal state machine.
EnglishPlan test strategies and execute test-driven development cycles, including coverage addition and test repair.
EnglishCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
English
AGENT SKILLS ATLASIncludes Agent Mgmt, Claude CLI, Claude CLI Wrapper, 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
Agent Mgmt
Spawn, list, inspect, and stop sub-agents through the wrapper. Sub-agent config travels as a JSON-serialized string. Flat parameter surface.
Claude CLI
Use claude CLI for interactive AI sessions, scripting with print mode, MCP server management, and plugin configuration. Master session management, tool control, and automation workflows.
Claude CLI Wrapper
Hub for the claude-cli-wrapper MCP server — execute, session, context, review, agent, and config tools. Routes to spoke skills.
Create Prompts
Create executable prompts for Claude Code. Use when user asks to create a prompt, generate a prompt for a task, or write a prompt for another agent.
Execute Plans
Execute PLAN.md files using intelligent strategies based on checkpoint types. Use when user says 'execute', 'run plan', 'build it', or wants to progress from PLAN to SUMMARY.
Execute Prompts
Execute prompts from .principled/prompts/ via delegated sub-tasks. Use when user asks to run, execute, or launch prompts.
Git Review
Review all git changes — triage each as ship, gitignore, or discard, then commit, push, and sync all worktrees.
Plan Lifecycle
Manage the full project lifecycle: PLAN (create executable roadmaps) and EXECUTE (run plans with intelligent orchestration).
Rules Orchestration
Manage CLAUDE.md and rules — extract learnings, add rules, restructure, and review. Use when updating project conventions.
Sadd
Solve complex problems by generating multiple solutions and picking the best one. Use when user says 'pick the best approach', 'compare options', or 'deep dive into a solution'.
Session Analytics
Analyze session transcripts to extract data, diagnose anti-patterns, and generate GitHub issues from findings.
Task Lifecycle
Task lifecycle state machine — states, transitions, and task tree model. Use when you need to understand task states, dispatch subtasks, or review completions. Do NOT use for domain-specific procedures — this only covers the universal state machine.
Test Orchestration
Plan test strategies and execute test-driven development cycles, including coverage addition and test repair.
Write a Skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
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 Agent Mgmt 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.