consult-guidelines
Review relevant guidelines before starting a task
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Review relevant guidelines before starting a task
Use it when the user asks to "ask gemini", "ask codex", or "ask in browser"
Phase 0.1 — Automatic codebase scan before PRD generation. Extracts key terms from the user prompt, searches the codebase for related files, identifies existing patterns, and generates context.md in the state directory.
Query past decisions, bets, learnings, and documents by topic
Always use Context7 MCP to fetch up-to-date library/API documentation before generating code that depends on external libraries or config. Use when the user asks for setup steps, configuration, or code involving third-party libraries. Prefer Context7 docs over memory. Include citations to the retrieved docs when possible.
Advise on course difficulty and prerequisites. Use when a customer is unsure about the level or required knowledge.
Applies rigorous critical analysis to evaluate claims, arguments, and research. Use when evaluating evidence quality, peer reviewing content, assessing argument validity, or identifying weaknesses in reasoning. Triggers on phrases like "critically analyze", "evaluate this", "review this paper", "check the logic", "assess the evidence", "find flaws", "peer review".
Fact-checking and source verification workflow for research documents. Launches parallel fact-checkers, aggregates findings, applies corrections systematically.
Web search via the DDGS metasearch library. Use for searching for unknown documentation, facts, or any web content. Lightweight, no browser required.
DEPRECATED: This skill has been replaced by memory/check_seen and memory/mark_seen tools. Use fetch-rss-feeds or other collection skills which handle deduplication automatically through the Memory MCP server.