Loading...
Loading...
Found 30 Skills
Agent Context Isolation
Execute proactive auto-loading: automatically detects and loads agents.md files. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
Build AI agents with structured access to Sanity content via Context MCP. Covers Studio setup, agent implementation, and advanced patterns like client-side tools and custom rendering.
Interactive session to craft a system prompt for an AI agent powered by Sanity Agent Context MCP.
Pattern for progressively refining context retrieval to solve the subagent context problem
End-of-session documentation workflow that updates README, CHANGELOG, agent context files, and creates session logs. Use when wrapping up a working session, when asked to document session progress, when preparing handoff documentation, or when the user says "wrap up", "end session", "document progress", or "save session".
Generate CLAUDE.md and AGENTS.md by exploring the codebase
Enables autonomous context management for codebases through claude.md files. Use when creating, maintaining, or synchronizing AI agent context. Provides tools and workflows for monitoring context health, detecting staleness, and updating intelligently. Helps Claude work proactively as a context manager.
Append project fragment knowledge that is "too short to warrant a separate file but needs to be known by AI every time" to fixed sections of AGENTS.md / CLAUDE.md — such as special compilation flags, services that must be started before running, path pitfalls, command aliases, and environment variable conventions. Triggers: When the user says "make a note", "add to AGENTS", "save to CLAUDE.md", "the project requires X to compile", "must do Y every time from now on", or just encountered a project-specific setting that can be explained in one sentence.
Creates or audits a CLAUDE.md file — the ambient project-context document Claude Code loads at session start. Use when user says 'create a CLAUDE.md', 'audit our CLAUDE.md', 'is our CLAUDE.md any good', 'our CLAUDE.md is out of date', 'make CLAUDE.md load-bearing', or 'write scope-level CLAUDE.md'. Do NOT use for skills (use create-or-audit-skill), agents (use create-or-audit-agent), or user-facing documentation (use write-doc).
让 agent zoom out，并给出更广的 context 或更高层 perspective。Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
Scaffolds per-project agent context — creates a tailored AGENTS.md, a CLAUDE.md symlink, and an agent_docs/ directory so AI agents can work effectively in the repository.