Use when a user wants you to discover and optionally install new agent skills for a task, and you must get explicit consent before any global install into Codex.

Server-specific best practices for FastAPI, Celery, and Pydantic. Extends python-skills with framework-specific patterns.

Use when user asks to create, write, edit, or test a skill. Also use when documenting reusable techniques, patterns, or workflows for future Claude

<one-line description of what this Skill does and what it outputs>. Default output to docs/onboarding/, override via OUTPUT_DIR.

Create new Claude Code skills with proper structure, YAML frontmatter, and best practices. Use when creating reusable knowledge modules, adding specialized guidance, or building domain-specific expertise.

Validates that a skill or MCP implementation matches its manifest by running Codex-powered semantic comparisons across descriptions, preconditions, effects, and API surface.

Agent Skill: Generate and maintain AGENTS.md files following the public agents.md convention. Use when creating AI agent documentation, onboarding guides, or standardizing agent patterns. By Netresearch.

Clear description of what this skill does and when Claude should use it. Be specific about triggers - include the functionality AND when to activate. Example: "Extract text from PDFs and fill...

Security audit skill for detecting dangerous APIs, footgun patterns, and vulnerability variants. Use when reviewing code for security issues or doing variant analysis.

Interactive game to learn Claude Agent Skills (SKILL.md) - explore, learn, and quiz yourself!

Agent Skill: CLI tool management. Use when commands fail with 'command not found', installing tools, or checking project environments. By Netresearch.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent...

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge,...

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions...

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise...

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture,...

Brief description of what this skill does. Use when [trigger condition 1], [trigger condition 2], or [trigger condition 3].

This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural...

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context...

This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context...