claude-hooks
This skill should be used when creating hooks, automating workflows, or when "PreToolUse", "PostToolUse", "hooks.json", "event handler", or "create hook" are…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Agents & models
25,595 results
multi-agent-vcs
This skill should be used when dispatching subagents for parallel development, coordinating multi-branch implementations, or when "parallel agents",…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
agent-style
Literature-backed English technical-prose writing rules (agent-style, 21 rules). Its lane is FORMAL technical prose (papers, design docs, proposals, READMEs,…
peon-ping-remix
Internal — invoked headlessly by the peon eval server; humans should run `peon eval <pack>` instead. Execute one PeonPing reroll job — invoked headlessly by…
write-goal
Compile a plain-language task into a concise, auditable Codex or Claude Code `/goal`, or explain why a normal prompt fits better. Use when the user asks to…
qa-engineer-agent
QA Engineer Agent — Test Strategy, Test Case Design, Automated Testing, Performance Testing, Security Testing
tech-leader-agent
Technical Lead Agent — Technical architecture decisions, code review, team technical management, technical planning and roadmap
asi-integrated
Unified ASI skill combining ACSets, Gay-MCP colors, bisimulation games, world-hopping, glass-bead synthesis, and triad interleaving for autonomous skill…
plugin-validator
Validate Claude Code plugin structure, manifests, frontmatter, and dependencies. Use when user mentions "validate plugin", "check plugin health", "plugin…
refine-agent-workflow
Recommend focused improvements to agent instructions and workflows.
glorp
Guide for downstream coding agents driving Glorp — especially Glorp Garage (the remote multi-session control plane) and its sandboxes (Garage-provisioned…
creating-kiro-agents
Use when building custom Kiro AI agents or when user asks for agent configurations - provides JSON structure, tool configuration, prompt patterns, and security…
codex-in-app-browser
Drive the Codex in-app browser (open, navigate, click, type, screenshot, read page state) through the app's own node_repl runtime. Use when the session uses a…
hf-mcp
Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio…
huggingface-best
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by…
huggingface-llm-trainer
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO,…
mongodb-mcp-setup
Guide users through configuring key MongoDB MCP server options. Use this skill when a user has the MongoDB MCP server installed but hasn't configured the…
netlify-mcp-servers
Build, deploy, and secure Model Context Protocol (MCP) servers on Netlify. Use whenever the task involves creating an MCP server, exposing an app or API to AI…
grounded-rag-ingestion
Chunk a document into provenance-carrying JSONL ready for embedding via the Nutrient Data Extraction API (`/extraction/parse`, spatial output). Every chunk…
teamlead-coordination
ALWAYS LOAD THIS SKILL WHEN ACTING AS A TEAMLEAD AGENT SESSION. Do not run a Teamlead-led multi-epic session directly — use this skill first. Backlog-driven…
abai-autoplus-chatgpt-registration
Multi-threaded automated ChatGPT free account registration and management web panel with OAuth bypass using Codex
hsf
Write specifications using Hybrid Specification Format (HSF v6), a prose-based format optimized for LLM consumption. Uses natural-language instructions within…
evolve
Harness evolution skill. Collects and generalizes feedback on the execution results of the harness in use, reflects it in the agent/skill/orchestrator, and captures the delta compared to the initial configuration to update the change history. 'Harness retrospective', 'harness evolution', 'harness feedback reflection', 'harness improvement', 'the results were disappointing, harness…