Loading...
Loading...
Found 1,990 Skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch for Claude Code or Cursor, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Use when creating or configuring Claude Code agents and their frontmatter.
Socratic book-learning tutor for any book or course. Teaches chapter-by-chapter using guided questioning, ~200-word explanations, and comprehension checks. Tracks progress and writes durable concept notes to a vault. Reads book config from project CLAUDE.md. Use when the user says "chapter N", "let's study", "teach me X", or when a project CLAUDE.md declares a learning context.
Expert skill for using wanman, the open-source local agent matrix runtime that coordinates multiple Claude Code or Codex agents on your machine.
Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.
Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.
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 Use when user says 'create a CLAUDE.md', 'audit our CLAUDE.md', 'is our CLAUDE.md any good', 'our CLAUDE.md is out of date', 'make CLAUDE.md load-bearing', or 'write scope-level CLAUDE.md'.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).
Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state probing, native code-surface registration, capability checks, and a verdict block. Re-runnable, idempotent. Use when: "sync gbrain", "refresh gbrain", "re-index this repo", "gbrain search isn't finding things". (gstack)
Use when the user wants to bootstrap a target codebase for AI-driven development with Claude Code. Generates a concise CLAUDE.md grounded in the actual stack (build tools, test runner, code style), creates a docs/ folder skeleton (designs/, prd/, plans/), and seeds conventions (conventional commits, plan-checkbox format, where designs and PRDs live). Triggers on "init Claude in this repo", "set up CLAUDE.md", "bootstrap docs folder", "prepare this project for Claude Code", "scaffold AI dev workflow", "/init this project".
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
Use OpenAI Codex from inside Claude Code for code reviews, adversarial reviews, and delegating tasks to Codex as a subagent.