find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-11 00:16
Agents & models
26,090 results
skill-maker
Guide agents through creating skills that follow the agentskills.io specification. This skill should be used when the user asks to "create a skill", "make a…
claude-init
Create, update, or converge repository-level `CLAUDE.md`for Claude Code, keeping only high-signal collaboration constraints, tool pitfalls, approval boundaries, and project-specific rules that cannot be discovered directly from the codebase. Whenever the user mentions initializing Claude Code repository instructions, migrating Cursor or Copilot instructions to a Claude Code version, or converting `AGENTS.md`…
jev-codex-computer-use
In Codex Computer Use, assign direct CUA operations and Jev continuous browser decisions. It applies to tasks that require navigating, expanding, switching, paging, or scrolling based on page state; for already-determined buttons, operate directly, while input and acceptance are handled by Codex. It has a built-in Jev bridge and does not provide Jev control for native desktop applications.
voice-clone-skill
Generate and verify complete-ending local speech with a saved cloned voice, or prepare a reusable Qwen3-TTS voice profile from user-authorized reference audio.…
audio-to-subtitles
Convert audio files to subtitle files using OpenAI Whisper AI transcription. Generates SRT, FCPXML (for Final Cut Pro), and plain text formats. Use when you…
ralph-loop
Keep Codex auto-continuing on the same bounded task until a completion signal appears in the assistant output or a maximum iteration count is reached. Use when…
AgentChat-IndependentTasks
Distribute N independent tasks in parallel to multiple browser AIs, then after collection Claude Code synthesizes authoritative answers and outputs a textbook-style solutions manual PDF. Trigger words: "distribute to multiple AIs", "ask multiple AIs in parallel", "compile into a PDF/solutions manual". Not applicable to tasks requiring collaboration or role division among AIs.
AgentChat-Muse
Muse.ai LLM / agent-worker subagent + OneWeb PROVIDER_CHAIN adapter (key muse). Use for Muse chat, research, and secondary social ops handoff. Draft-only live…
AgentChat-OneWeb
Multi-provider CDP bridge with automatic fallback (Gemini->ChatGPT->Claude->Qwen->Kimi->MiniMax->ChatGLM->Doubao->MiMo->DeepSeek). Use for AI provider…
AgentChat-WebSubAgent
Sequential 6-step AI pipeline — Claude Code plans→Kimi searches→(complex? Gemini reasons)→Claude synthesizes→ChatGPT reviews→Claude fixes. Use for complex…
agentweb-setup
Detect each web-AI provider session on the already-running Chrome (CDP attach only) and ask the user to log in anything that is not ready. Use for…
mcp-server
AgentChat MCP Server — expose 8 AI providers as MCP tools for any MCP-compatible client (Claude Desktop, Cursor, Continue.dev). Configuration/reference skill,…
orca-emulator
iOS Simulator control from inside Orca, with the live device view in Orca's emulator pane. Use when driving a booted Apple Simulator on macOS: taps, gestures,…
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or…
claude-opus-4-6-prompting
Comprehensive prompt engineering reference for Claude Opus 4.6. Use this skill whenever you are writing, reviewing, or optimizing prompts for Claude Opus 4.6…
ulysses-protocol
Thoughtbox-first Ulysses workflow for surprise-gated debugging. Use this when debugging gets uncertain and you need explicit plan, outcome, and reflection…
running-daily-tasks
Unified daily routine: ingests messages into tasks, then guides user through task refinement and dispatch. Works in both Claude Code and Cowork. Triggers on:…
01-env-propagation
Probe env propagation across 3 process tiers (§1.1). Compares which CLAUDE_* env vars are set in plugin-level hook vs skill frontmatter hook vs Bash tool…
alethe-orchestrate
Orchestrate bounded Codex, Claude Code, Agy, Kimi, or custom CLI workers to finish work with the least lead context and provider usage, following strategy…
claude-project-migrate
Migrate Claude Code project data when moving project directories. Automatically encodes paths and copies conversation history, memory, and settings from old to…
felo-superagent
Felo SuperAgent API: AI conversation with real-time SSE streaming and LiveDoc. Use when users want SuperAgent chat, continuous conversation, or LiveDoc-backed…
jsonl-digest
Extract knowledge from new Claude Code JSONL conversation logs and write to auto-memory. Auto mode (default): high-confidence memories written directly,…
obsidian-vault-manager
Obsidian vault operations and personal knowledge management consultant. Flexibly utilizes Obsidian CLI and Claude Code tools, automatically selecting the best tool to complete tasks. Supports vault health checks, note search and queries, tag organization, knowledge extraction and summarization, creating content maps (MOC), restructuring folder structures, batch editing notes, Simplified Chinese to Traditional Chinese conversion (zh-CN →…