implement-fanout
Implement several INDEPENDENT tickets in parallel — each in its own git worktree via a subagent — then collect their draft PRs. Use when 2+ ready tickets have…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,657 results
install-skill
Install a Claude Code skill from a GitHub URL. When you enter the URL of a skill folder in a GitHub repository, it automatically downloads all files of that skill and installs them into .claude/skills/.
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…
chezmoi-management
mizchi's personal chezmoi dotfiles operation notes. Covers source location, directory naming conventions, daily diff/apply flow, skill addition procedure, the boundary between APM and chezmoi, pre-commit (prek + secretlint), and troubleshooting. ~/.claude/,…
skills-audit
Audit locally installed agent skills for security/policy issues using the SkillLens CLI (`skilllens scan`, `skilllens config`). Use when asked to scan a skills…
humanize-korean
This is a Korean-language specialized skill that precisely removes the "AI feel" from Korean text written by AI (ChatGPT, Claude, Gemini, etc.) and polishes it so it reads like human-written writing. Translationese (through ~/~ in terms of/double passive), excessive English quotations, mechanical parallelism (first, second, third), AI-specific idioms (in conclusion/it suggests...
moai-platform-supabase
Supabase specialist covering PostgreSQL 16, pgvector, RLS, real-time subscriptions, and Edge Functions. Use when building full-stack apps with Supabase backend.
t2i-prompt-dialect
Rewrite an asset brief into the exact prompt dialect of the target image model (OpenAI gpt-image-1, Google Imagen/Gemini, SDXL, Flux.1/Flux.2, Midjourney,…
verification-agent
Verify claims, quotations, citations and references against live primary sources, and produce a reproducible audit record instead of an assertion. Use when…
skills_sync-cli
Provides usage instructions and best practices for the skills_sync CLI tool. Use this to understand how to manage, sync, and configure AI agent skills based on…
skills_sync-optimizer
Optimizes the user's skills.yaml configuration, offering tailored skill suggestions and organizing redundant or out-of-stack skills.
contrastive-refinement
Use when a skill or harness edit needs evidence before it lands — probe candidates on the same task, compose from contrasts, keep lessons with evidence.
grill
Use when a plan is fuzzy and needs hardening before a spec — decision-tree grilling in frontier rounds, every open decision put as a numbered question with a…
skill-lifecycle
Advanced skill management system, supporting full lifecycle management of skills, documentation standard formulation, skill integration and splitting, and workflow orchestration; provides simple/complex skill documentation writing standards to ensure documentation quality and maintainability
kelly-agent-builder
Busabase-backed App-in-Skill low-code agent configuration and governance console for a platform team. Use when the user invokes $kelly-agent-builder or…
kelly-agent-eval
Review board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored…
kelly-agent-observability
Busabase App-in-Skill dashboard visualizing a generated MOCK fleet of LLM agents running behind a shared AI gateway for a generic organization. Use when the…
im-down
Use when you are ending a Claude Code work session and the next session must resume from a verified packet instead of from conversational memory.
im-up
Use when a fresh Claude Code session must resume from an im-down packet and verify repository state before any work begins.
tk-domain-modeling
[auto] Refine the domain language, verify conceptual boundaries, and record only terms or significant decisions that will be maintained for a long time.
eval-iterate
Iterates on a failing AI/LLM eval (an L2 suite, a golden-set / judge eval, or any eval gating a PR) until it is green AND confirmed, not just luckily passing…
chatkit
Build AI chat applications with OpenAI ChatKit SDK. Use when creating chat UIs, multi-session systems, integrating AI agents (OpenAI, Gemini, Claude, Ollama),…
computer-use-fast
Do GUI tasks on a Mac in as few agent turns as possible. Try a shell command first, then run the whole click/type/read sequence in ONE terminal call with…
prompting-gpt
Create, revise, or review prompts and agent instructions using the user-specified model or otherwise the detected runtime model to select a matching reference,…