Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
resolve-pr-comments
GitHub PRの未解決Review threadsを一括Resolveします。
getty104/claude-code-marketplace 11
-
update-issue
Update an existing GitHub Issue's description based on the issue number and request provided as arguments
getty104/claude-code-marketplace 11
-
fix-review-point
Address unresolved review comments on specified branch
getty104/claude-code-marketplace 11
-
create-task-summary
直近一週間で自身が作成したPRを取得し、やったことのサマリーを作成する。週次報告や作業振り返り時に使用。
getty104/claude-code-marketplace 11
-
triage-prs
Triage open GitHub PRs assigned to the user. Fetch PRs where CI has completed and cc-in-progress label is not present, run create-review-fix-plan for each, then either add cc-fix-onetime label (if fixes are needed) or merge the PR (if it's ready to merge as-is).
getty104/claude-code-marketplace 11
-
read-github-issue
GitHub Issueの内容を取得し、実装プランを作成します。
getty104/claude-code-marketplace 11
-
breakdown-issues
依頼された内容を要件とTODOに分解し、タスクごとにGitHub Issueを作成するスキル。タスクの整理・分解、複数Issueの一括作成、依存関係の明示が必要な場合に使用する。「この機能をIssueに分けて」「タスクを洗い出してIssueにして」「要件を整理してチケット化して」といったリクエストで発動する。
getty104/claude-code-marketplace 11
-
create-issue
Create an implementation plan and a GitHub Issue based on the task description provided as an argument. If an issue number is provided, update the existing issue instead.
getty104/claude-code-marketplace 11
-
exec-issue
Execute tasks based on GitHub Issue content
getty104/claude-code-marketplace 11
-
commit-push
コード変更を適切なgitコミット戦略でgit commitし、pushします。基本的には既存のgitコミットへのsquash戦略を採用し、必要に応じてブランチ全体のgitコミット履歴を再構成します。実装完了時やユーザーがgit commitを依頼した時に使用します。
getty104/claude-code-marketplace 11
-
create-pr
GitHubでPull Request（PR）を作成します。PRのdescriptionには指定されたテンプレートを使用し、必要な情報を記載します。PR作成後、PRのURLを報告します。
getty104/claude-code-marketplace 11
-
check-library
ライブラリの情報を確認するためのスキル。Next.js、shadcn、その他のライブラリについて、適切なMCPサーバーを使用して最新のドキュメントと使用方法を取得します。
getty104/claude-code-marketplace 11
-
create-review-fix-plan
GitHub PRの未解決レビューコメントとCIステータスを確認し、修正プランを作成します。
getty104/claude-code-marketplace 11
-
triage-issues
Triage GitHub issues assigned to the user. Categorize and process issues by adding appropriate labels (cc-create-issue, cc-exec-issue, or cc-update-issue) based on dependency analysis, issue detail status, and whether confirmation items need answers.
getty104/claude-code-marketplace 11
-
codex
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
skills-directory/skill-codex 1,075
-
quality-gates
This skill should be used when the user wants to run code quality checks (linting, formatting, type checking, tests) on the lazyopencode project. Use this skill when asked to "run quality gates", "check the code", "run tests", "lint the code", or verify code quality before committing.
NikiforovAll/LazyOpenCode 3
-
agents-compat-skill
Skill discovered from .agents/ path
NikiforovAll/LazyOpenCode 3
-
project-skill
Project-specific skill
NikiforovAll/LazyOpenCode 3
-
task-tracker
Track and manage development tasks
NikiforovAll/LazyOpenCode 3
-
deploy-helper
Helps with deployment tasks and scripts
NikiforovAll/LazyOpenCode 3
-
my-skill
A skill with nested file structure for testing
NikiforovAll/LazyOpenCode 3
-
ship-cli
Work management system replacing built-in todos with tracked tasks and stacked changes
EduSantosBrito/ship-cli 4
-
ensue-memory
Augmented cognition layer that makes users smarter by connecting conversations to their persistent knowledge tree. Use proactively when topics arise that might have prior knowledge, and when users ask to remember, recall, search, or organize. Triggers on technical discussions, decision-making, project work, "remember this", "recall", "what do I know about", or any knowledge request.
mutable-state-inc/ensue-skill 412
-
claudish-usage
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, Gemini, OpenAI, Ollama, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
MadAppGang/claudish 696