28,473 skills sorted by stars.
Run repository hygiene sweep.
Use repositories to encapsulate database queries and provide a clean interface for data access Use when designing system...
Comprehensive Prisma repository implementation patterns for NestJS. This skill should be used when implementing reposito...
リポジトリ構造定義書を作成するための詳細ガイドとテンプレート。リポジトリ構造定義時にのみ使用。
PRD・機能設計・アーキテクチャからリポジトリ構造定義書（docs/repository-structure.md）を作成する。 「ディレクトリ構成を決めて」「フォルダ構造を設計」「ファイル配置ルール」「プロジェクト構造」 「どこに何を置く...
Reproduce an EmDash bug that lives below the browser layer -- REST handlers, CLI, MCP, migrations, schema registry, or b...
Use when fixing a reported bug — reproduce it with a failing test before touching the code, then make the minimal fix at...
End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial o...
Use when a named runtime or compiler bug in a local repository needs independent reproduction.
Configures Reqnroll (the canonical .NET BDD framework) - install via `dotnet add package Reqnroll`, author `.feature` fi...
Request a new feature or enhancement for the apexyard FRAMEWORK itself — files a structured issue upstream to me2resh/ap...
Request Body Validator - Auto-activating skill for API Development.Triggers on: request body validator, request body val...
Consult another expert coding agent via codex CLI for extra tricky bugs or complex feature design reviews. Codex investi...
Group recent conversations into overall requests, review each one's progress from memory, link each to the owner goals i...
Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user want...
Plan a refactor as a sequence of tiny, working commits via adversarial interview. Default output is a markdown plan at `...
Request one independent review of a committed plan from a fresh session of the opposite CLI (Claude ↔ Codex), monitor it...
Authored regression cases for request targets and shell redirection.
Use when a change is ready for another reviewer, before merging it or asking for approval.
Use when completing tasks, implementing major features, or before merging. Validates work meets requirements through sys...
Pre-review checklist and validation before code review
當完成任務、實作主要功能或在合併前驗證工作符合需求時使用
Dedicated Form Request validation classes for all controller input. Every endpoint that accepts user input must use a `F...
Copilot agent that assists with requirements analysis, user story creation, specification definition, and acceptance cri...
Interactive PM interview with expertise-adaptive questioning for requirements elicitation
Use when capturing what a feature must do - write testable user-story requirements that state WHAT and WHY, never HOW, w...
Use functional setState updates to prevent stale closures and unnecessary callback recreations. Apply when updating stat...
Sell secondhand like someone who's done it 500 times — honest condition grading, comps-based pricing with a floor and an...
Use when Codex should ask Claude CLI for a rescue-style investigation, second opinion, debugging pass, or explicitly req...
Onboards agents to the RescueKit CLI/SDK with setup, env configuration, safety constraints, and core commands. Use when...
10-team parallel deep analysis with cross-verification for any topic, repository, or technology. Use when user invokes /...
This skill should be used when a task's scope contract is approved and its criteria need grounding before design starts,...
Primary pipeline step after /shape and before /write-a-prd. Use to verify current docs, versions, repo patterns, and key...
ML research frameworks for building and optimizing AI systems with declarative programming.
This skill should be used when the user asks to "research", "fact-check", "check the history", "is this accurate", "rese...
ALWAYS use for ANY request to find academic papers - "find papers on X", "what does the literature say about X", "is the...
Multi-source external research with entity resolution, query planning, parallel fan-out, cross-source clustering, and gr...
Intelligence surge mode — sweep, ingest, synthesize, dispatch. For deep research sessions that must produce ledger-ready...
Use when a decision needs multiple sources gathered and weighed. Answer a single factual lookup directly from an appropr...
Run deep, internet-enabled research on any topic to gather the raw material for content. First step of the content pipel...
Web search and external knowledge lookup. Gathers data on technologies, libraries, best practices, and competitor soluti...
Analyze current trends and challenges in Japanese NLP for a topic. Surveys the existing awesome-japanese-nlp-resources d...
Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and pro...
Researches implementation approaches using browser automation via /chrome, then implements the best solution. Use when b...
Conduct research, synthesize information, and create structured summaries
Use when the user invokes /research-auto or asks to run an autonomous campaign over one active Package toward a measurab...
Use when the user wants to create, refine, merge, archive, or review one standalone Brainstorm before Package conversion...
Use when the user asks for researched, sourced, evidence-backed, or current findings, especially for a recommendation or...