skill-creator
Create new OpenCode skills with valid SKILL.md frontmatter.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Agents & models
25,390 results
ruby-on-rails
Comprehensive Ruby on Rails 8.1 best-practices skill covering MVC, Active Record, routing, views, background jobs, storage, security, testing, performance,…
ua-parser
Build, review, debug, migrate, or plan User-Agent detection with UAParser.js v2 (ua-parser-js OSS AGPL and @ua-parser-js/pro-personal, pro-business,…
models-config
Model configuration editor for ~/.pi/agent/models.json - Manage model configuration with Bun scripts
public-repo-explorer
Instructs the agent on how to efficiently browse public GitHub repositories using a local shallow clone. You MUST use this skill whenever the user asks you to…
skill-creator
Guide for creating effective skills. Use when creating a new skill or updating an existing skill that extends agent capabilities with specialized knowledge,…
seedance-examples-ko
This skill should be used when the user asks for Korean Seedance 2.0 examples, Korean prompt patterns, example rewrites, or safe versions of working Korean…
seedance-vocab-ko
This skill should be used when the user asks for Korean Seedance 2.0 prompt wording, Korean cinematic vocabulary, or translation of camera, lighting, action,…
endor-agent-kit-setup
Use when setting up Endor Labs Agent Kit for Cursor, checking readiness, verifying Endor auth, choosing namespaces, or diagnosing missing endorctl, gh, Endor…
agent-browser
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
jujutsu
This document instructs Claude Code to use `jj` (Jujutsu) instead of `git` for version control operations. jj is a Git-compatible VCS that provides a simpler…
mcpa-certification
The MCPA (Model Context Protocol Associate) AI-native mentor and onboarding flow in the Chinese edition of AI Engineering from Scratch. Used by learners preparing for MCPA, continuing the certification path, interactively studying the next lesson, running and validating hands-on labs, taking diagnostics or full mock exams, and shoring up weak areas. Works with Claude…
supabase-auth-memory
Standardize authentication and persistent memory storage using Supabase PostgreSQL. Use when building SaaS apps that need user auth, cross-device sync, and…
async
Launch and coordinate Codex subagents as deferred tasks. Use when the user wants to start bounded subagent work now, keep the main thread moving without…
product-manager
Transforma a Claude en un Product Manager de clase mundial. Usar cuando necesites diseñar lógica de negocio, definir flujos de usuario, analizar competidores,…
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows. Use when piping output between agents/tools as streaming JSON or…
claude-md
Author, audit, and maintain CLAUDE.md memory files the way Anthropic recommends — under 200 lines, only-always-true facts, situational knowledge moved to…
claude-sdk
Build autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production best practices for Anthropic models
agent development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…
optimize-agentic-workflow
Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.
pr-finisher
Prepare an open pull request for merge from a GitHub Copilot cloud agent. Drives Reviews, local validation, and Mergeable to a ready state. Does not merge, and…
flow-next-export-context
Export RepoPrompt context for external LLM review (ChatGPT, Claude web, etc.). Use when you want to review code or plans with an external model. Triggers on…
hamelnb
Work against a live local Jupyter notebook kernel. Use this when an agent needs a Jupyter-like in-memory REPL, wants to inspect or edit a notebook while…
humanizer
This skill should be used when the user wants to humanise text, remove AI slop, make writing sound less like ChatGPT, or rewrite content to sound more natural…