agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-12 00:15
Agents & models
26,179 results
tmux
Read and drive other tmux panes when Claude runs inside tmux. Use whenever the user points at something running in another pane/split/window — their dev…
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn…
dial
Query the DIAL AI model catalog, inspect a specific model's details/capabilities, or check rate-limit usage via the local `dial` CLI shipped with the pi-dial…
patent-writer-agent
Based on the technical disclosure document and DOCX/PDF/Markdown technical materials, generate a complete draft of a Chinese patent application, including the abstract, claims, description, drawing descriptions, and specific embodiments.
writing-fragments
A mining session that digs fragments out of the user — heterogeneous small pieces of writing (claims, anecdotes, sharp sentences, half-formed ideas) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing. (Grilling session that…
skill-fit
Skill fit: a read-only audit that matches a project against the skill catalog. Profiles the project (language/framework, git, tests, CI, product stage, current…
pump-ai-agents
AI agent integration layer for the Pump SDK — agent instruction files, .well-known discovery, LLM context documents, 15+ skill files, MCP server prompts, and…
ui-skills
Opinionated constraints for building better interfaces with agents.
elon-algorithm
Aggressively simplify any artifact — code, a prompt, a skill, a doc, or prose — by running Elon's algorithm (question every requirement → delete → simplify) on…
claude-code
Use when you need to run Claude Code from another agent (Codex or any shell-capable agent): hand it a task headlessly with `claude -p`, pick the model, effort…
collaborate-with-claude-5
Use when you work with an Anthropic Claude 5 model (Opus 5.5, Sonnet 5.5, Fable 5.1, Haiku 5.5) as a worker or reviewer: choosing the member, deciding what to…
collaborate-with-gpt-6
Use when you work with an OpenAI GPT-6 model (GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna) as a worker or reviewer: understanding its decision habits, choosing the…
retro
Run a sprint retrospective. Evolve the organization through KPT organization → improvement actions → automatic feedback to CLAUDE.md/rules/agents
autorag-query
Query AutoRAG-Research pipeline results using natural language. Converts questions to SQL, executes safely (SELECT-only), returns formatted results.…
create-generation-plugin
Guide developers through creating a custom generation pipeline plugin for AutoRAG-Research. Walks through scaffolding, implementing BaseGenerationPipeline…
create-retrieval-plugin
Guide developers through creating a custom retrieval pipeline plugin for AutoRAG-Research. Walks through scaffolding, implementing BaseRetrievalPipeline…
roblox-pathfinding-and-npcs
Complete coverage of Roblox pathfinding and NPC AI. Covers PathfindingService, agent parameters (radius, height, jump, climb), waypoint actions, blocked-path…
roblox-physics-and-constraints
Complete coverage of Roblox rigid-body physics for building vehicles, mechanisms, doors, platforms, and dynamic objects. Covers assemblies, root parts,…
roblox-studio-mcp-server
How to set up, connect, and effectively use the official Roblox Studio MCP (Model Context Protocol) server so an AI agent can read and write scripts, explore…
build-my-skill
Turn an existing professional process or a desired work outcome into an installable AI skill through focused, profession-specific conversation. Clarify…
agentskills-io
Create, validate, and publish Agent Skills following the official open standard from agentskills.io. Use when (1) creating new skills for AI agents, (2)…
rewardkit
Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or…
ci-fails-buildkite
Fetch and diagnose vLLM Buildkite CI failure logs. Use when investigating failing CI jobs on a PR or build, when the user pastes a buildkite.com URL, or asks…