Loading...
Loading...
Found 3,190 Skills
Turn any workflow into a properly structured Claude Code skill — YAML frontmatter, phase-based instructions, real code blocks, and a verify checklist. Use when the user wants to package a repeated workflow, create a new skill, turn a process into a slash command, or publish to the skills directory. Triggers on requests like "make a skill", "create a skill", "turn this into a skill", "new skill for...", "package this as a skill", "build a skill", "I want to publish a skill", "help me write a skill", or any request to create a reusable Claude Code skill.
Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously — modify, verify, keep/discard, repeat. Supports optional loop count via Claude Code's /loop command.
AI-assisted Ansible authoring toolkit for Claude Code. Scaffolds, reviews, and updates playbooks, roles, collections, and ansible.cfg files following production best practices. Sub-commands: new-playbook, review-playbook, update-playbook, new-role, review-role, update-role, new-collection, review-collection, update-collection, new-conf, review-conf, update-conf. Requires bash_tool. Runs discovery (CLAUDE.md to ansible.cfg to README to filesystem) at the start of every command.
Provides autonomous project pattern learning by analyzing the codebase to discover development conventions, architectural patterns, and coding standards, then generates project rule files in .claude/rules/. Use when user asks to "learn from project", "extract project rules", "analyze codebase conventions", "discover project patterns", or wants to auto-generate Claude Code rules for the current project.
Interactive TUI dashboard for visualizing Claude Code token usage, costs, and task breakdowns by project, model, and activity type.
Expert skill for using wanman, the open-source local agent matrix runtime that coordinates multiple Claude Code or Codex agents on your machine.
This skill should be used when searching Claude Code session transcripts with semantic understanding. Triggers on queries like "find sessions about X", "when did I work on Y", "search previous conversations". Supports natural language queries with synonym matching.
Run an autonomous /loop iteration -- check progress, work on next task, schedule next wake
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "multi-agent", "agent swarm", "coordinator agent", "worker agent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", "agents that communicate", "parallel agents", or needs guidance on agent structure, system prompts, triggering conditions, subagent orchestration, or multi-agent swarm development for Claude Code.
Move a project folder AND migrate all its Claude Code state in one shot — session store, prompt-up-arrow history, running-session records. Use whenever the user wants to rename/move a project directory and keep `claude --resume` working. Handles sub-directory sessions automatically. 移动/重命名项目目录并迁移所有 CC 历史（session + prompt 历史 + 运行记录）。
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".
Enable Claude Code instances to discover and message each other across different terminal sessions and projects