AI Skills Hub - Browse 180,000+ Agent Skills

This skill should be used when creating plan files, writing Gherkin requirements, generating tasks with verification commands, or parsing plan file structure. Provides the plan file template and format specifications.

Handoff protocol for Rust multi-agent development system. Use when working as rust-architect, rust-developer, rust-testing-engineer, rust-performance-engineer, rust-security-maintenance, rust-code-reviewer, rust-cicd-devops, or rust-debugger. ALWAYS read on agent startup.

PostgreSQL backup and recovery - pg_dump, pg_basebackup, PITR

Optimize PostgreSQL performance - EXPLAIN ANALYZE, indexing, query tuning

Use when collaborating with other AI assistants (Codex, Gemini, Aider, Cursor, OpenCode), delegating tasks, or requesting code review.

Merge feature branches into main using squash commits with comprehensive commit messages. Use this skill when the user requests to merge, ship, or integrate a feature branch into the main branch. The skill analyzes all commits in the feature branch to understand the full scope of changes, then creates a single squashed commit with a proper conventional commit message that summarizes the entire feature.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Node.js platform functions for the East language. Use when writing East programs that need Console I/O, FileSystem operations, HTTP Fetch requests, Cryptography, Time operations, Path manipulation, Random number generation, or Testing. Triggers for: (1) Writing East programs with @elaraai/east-node-std, (2) Using platform functions like Console.log, FileSystem.readFile, Fetch.get, Crypto.uuid, Time.now, Path.join, Random.normal, (3) Testing East code with describeEast and Assert.

Use when adding shell configuration for a new tool, creating zsh component files, configuring shell completions, using yadm alternates for OS-specific shell config, or troubleshooting modular zsh setup in conf.d structure.

How to create, validate, and manage skills in this skillstash instance

Load when working with KapanRouter instructions, UTXO tracking, flash loan flows, or debugging transaction failures

Create conference talk outlines and iA Presenter markdown slides using the Story Circle narrative framework. Use when structuring a tech talk, creating presentation slides, or organizing talk ideas into a story-driven format.

Expert in Model Context Protocol (MCP) server development. Use when building MCP servers, creating tools for Claude, implementing resources, debugging MCP connections, or integrating databases with Claude Code.

Comprehensive guide to Spring Boot fundamentals - auto-configuration, starters, properties, and profiles

Secure Spring Boot applications - authentication, authorization, OAuth2, JWT, CORS/CSRF protection

Test Spring Boot applications - MockMvc, TestContainers, test slices, integration testing

Frontend development workflow for ScreenGraph using SvelteKit 2, Svelte 5 runes, Skeleton UI v4, and Encore-generated clients. Use when building or updating UI features, routes, or shared components while keeping progressive disclosure intact.

Systematic debugging for Encore.ts backend incidents using diagnostic scripts, database queries, and structured logging. Use when backend tests fail, services crash, or async flows stall.

Master MongoDB schema design and data modeling patterns. Learn embedding vs referencing, relationships, normalization, and schema evolution. Use when designing databases, normalizing data, or optimizing queries.

Master MongoDB replication, replica sets, and sharding for distributed deployments. Learn failover, shard keys, and cluster management. Use when setting up high availability or scaling horizontally.

Master MongoDB indexing and query optimization. Learn index types, explain plans, performance tuning, and query analysis. Use when optimizing slow queries, analyzing performance, or designing indexes.

Master MongoDB aggregation pipeline for complex data transformations. Learn pipeline stages, grouping, filtering, and data transformation. Use when analyzing data, creating reports, or transforming documents.

Analyze PDF documents with table extraction, section identification, and content summarization. Use when reading technical documents, reports, or papers.

Validates KrakenD configurations with specific error fixes, edition compatibility checks, anti-pattern detection, and Flexible Configuration support

Analyze GRPO training runs for learning dynamics and pipeline performance. Use when diagnosing training issues, reviewing Elo progression, checking throughput, or updating experiment results.

Synchronizes Cursor Rules (.mdc files in .cursor/rules/) to CLAUDE.md by generating a Rules section with context-efficient descriptions and usage instructions. Use when setting up Cursor Rules for the first time, after adding or modifying rules, or when the Rules section in CLAUDE.md is missing or outdated.

Detects Python project configuration and provides commands for testing, building, coverage, and containerization.

This Claude Skill can be used to build, test, and automate iOS apps. 13 production-ready scripts including ultra token-efficient xcode build automation, log monitoring, intelligent simulator selection, and accessibility-driven UI simulator navigation.

Auto-tune channel parameters to find optimal offset, squelch, and AGC settings for best audio quality. Use when setting up new channels, improving weak signals, or finding the sweet spot for demodulation settings.

Analyze and optimize AGC (Automatic Gain Control) parameters for WaveCap-SDR channels. Use when audio is too quiet, too loud, has pumping artifacts, or when tuning AGC attack/release/target settings for FM/AM/SSB modes.

Adjust SDR radio settings (frequency, gain, squelch, bandwidth, filters, AGC) in WaveCap-SDR. Use when changing tuning parameters, optimizing reception, or configuring channels.

Validate WebSocket and HTTP stream health for WaveCap-SDR channels. Use when debugging streaming issues, measuring latency or throughput, detecting packet loss, or verifying audio/spectrum delivery.

Control WaveCap-SDR server via MCP tools. Use when the user wants to tune frequencies, start/stop captures, manage channels, or control P25 trunking systems.

Probe and test SDR hardware capabilities (RTL-SDR, SDRplay, HackRF, etc.). Use when verifying device detection, discovering supported sample rates and gains, testing antenna ports, or troubleshooting SDR hardware issues.

Fix stuck SDRplay API service that causes device enumeration to hang. Use when SoapySDRUtil --find hangs, SDRplay device times out, or the SDRplay RSP is unresponsive.

Autonomous issue management - fetches open GitHub issues, analyzes priorities, detects dependencies, spawns parallel subagents, and verifies results. Triggers: /run-issues, autonomous issues, batch issues, parallel issue processing.

箇条書きコンテンツを技術記事に仕上げる際に使用する。自然な文体とスタイルで執筆するためのガイドライン。

An agent that codes tasks in BDD-style. Automatically does not commit.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion by presenting structured options

This skill should be used when the user asks about Jira work items, sprints, boards, or projects. Activates when detecting: ticket IDs (PROJ-123), questions about "current sprint", "my tickets", "Jira issues", board information, project status, or any Jira-related queries. Provides read-only access to Jira Cloud via Atlassian CLI.

Automatically find relevant context from knowledge graph and code relationships while coding. Detects when context would be helpful (new files, unfamiliar code, architectural decisions) and surfaces related entities, prior decisions, and code dependencies.

Dependency management specialist. Use when updating dependencies, scanning for vulnerabilities, analyzing dependency trees, or ensuring license compliance. Handles npm, pip, maven, and other package managers.

Deploys public-facing apps that handle their own authentication (like Jellyfin, game servers) without Authelia forward auth

Long-term memory system for Claude Code using HelixDB graph-vector database. Store and retrieve facts, preferences, context, and relationships across sessions using semantic search, reasoning chains, and time-window filtering.

Convert Figma designs to pixel-perfect React components with Tailwind CSS.

git commit, push, PR作成を一括実行。新機能実装完了後やレビュー対応完了後に使用。メインエージェントのコンテキスト節約のため、定型的なPR作成フローをこのSkillに委譲する。

This skill should be used when the user needs to review and respond to GitHub Pull Request comments. It automatically fetches review comments (both inline code comments and PR-level comments) from GitHub Codex, Claude Code, or human reviewers, organizes them by priority, and lets the user select which items to address using AskUserQuestion. After the user selects items, the main agent automatically implements the fixes.

Guide experienced developers through RED phase of TDD cycle - writing failing tests and verifying expected failures

Guide experienced developers through GREEN phase of TDD cycle - writing minimal implementation to pass failing tests

SDD仕様書（overview.md, specification.md, technical-details.md, phase計画書）の構造・フォーマットガイド。以下の状況で使用する: (1) 仕様書を作成・編集する時、テンプレートを参照したい時 (2) 「**不明**」マーク、複数案提示、調査項目状態の書き方を確認する時 (3) specs/{taskname}/ のファイル構成を理解したい時 (4) Phase計画書（tasks/phase{N}-*.md）のフォーマットを確認する時 各ファイルのテンプレートはassets/templates/に配置。

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Provides intelligent header detection and semantic column mapping for robust data import.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Data Provider architecture rules for Crispy CRM. Use when creating data handlers, adding new resources, modifying unifiedDataProvider, implementing CRUD operations, or working with React Admin handlers and Supabase queries. Enforces Strangler Fig migration pattern, View/Table duality, validation boundaries, and service layer encapsulation.

Evidence-based completion claims - BLOCKS claiming tests pass, builds succeed, features work, or tasks are done without running verification commands first. Enforces TDD for implementation tasks. Triggers on done, complete, fixed, passes, works, ready, finished, verified, all good, ship it, commit, PR, push, merge, implement, create feature, build.

錯誤處理與 Result Pattern 技能，協助開發者實作統一的錯誤處理機制，包含 Result Pattern 應用、Failure 物件建立與分層錯誤處理策略。

Handler 業務邏輯層實作技能，協助開發者實作符合專案規範的 Handler，包含業務邏輯處理、流程協調、Result Pattern 錯誤處理與跨 Repository 操作。

Create detailed implementation plans with diagrams and dependency graphs. Use when planning features, refactoring, or multi-step development work before writing code.

GraphQL schema design including types, fields, pagination, nullability, naming conventions, and descriptions. Use when designing or modifying GraphQL schemas.

Next.js App Router Server Components, Client Components, layouts, data fetching, and Server Actions. Use when working with Next.js app directory, component boundaries, or data fetching patterns.

Upgrade Go to the latest version via Homebrew and update all go.mod files in the examples directory. Use when the user mentions upgrading Go, updating Go version, or wants to use the latest Go.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when working with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Provides expert-level assistance with dbt Semantic Layer, MetricFlow, semantic models, metrics, dimensions, entities, measures, and BI tool integrations. Use this skill when building semantic models, creating metrics (simple, ratio, cumulative, derived, conversion), debugging validation errors, or integrating with BI tools. Extracted from official dbt documentation and optimized for data practitioners.

Provider-agnostic wait-for-change skill that uses the Dumbwaiter MCP server to wait on PR events (GitHub first) via wait.start/status/cancel/await, with progress notifications and durable state.

Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

Builds and manages iOS/macOS apps using xcodebuild and xcrun simctl CLI tools. Use when working with Xcode projects, running apps in simulators, managing simulator instances, taking screenshots, capturing logs, running tests, or automating builds.

Generate markdown presentations compatible with IA Presenter. Use when the user requests to create an IA Presenter presentation, generate an IA Presenter document, or convert content into an IA Presenter markdown file. Also use when the user asks to create a presentation in markdown format without specifying a tool.

Use for autonomous WORKER mode execution - selects highest priority FAILING item with ralph_loop.enabled=true, reads PRD context, implements with iteration tracking, records attempts, commits on success or reverts on failure. ONE item per invocation with intelligent exit detection.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Domain expert for Splatoon 3 competitive gear abilities and weapon meta. Use when: (1) Labeling or classifying gear build features from SAE analysis, (2) Understanding why specific ability combinations appear in builds, (3) Identifying weapon archetypes and their associated ability patterns, (4) Semantic analysis of gear/ability relationships, (5) Interpreting competitive meta patterns in build data, (6) Any task requiring deep knowledge of Splatoon 3 ability synergies, anti-synergies, breakpoints, or playstyle associations.

Reference skill for Splatoon ability families, AP rungs, token constraints, and domain rules for mechinterp experiments

Work with personal notes archive stored in date-based directory structure with Markdown files. Navigate notes by date, ID, or slug. Search content and tags.

Ace-Tool 与 Serena MCP 协作流程。触发场景：(1) 需要理解代码库结构 (2) 语义代码搜索 (3) 符号级代码定位 (4) 代码导航和分析。提供两阶段协作：Ace-Tool 语义搜索→Serena 精确定位，强调只读安全与工具互补。

Process scanned homework PDFs by extracting student names via vision, matching to roster, creating individual PDFs per student, and updating completion spreadsheets. Triggers: "process homework PDF", "organize by student", "create student files from scan", "update homework checklist", "who submitted", "sort assignments", "grade papers", "split PDF by student", "track completion", "missing assignments". Handles: batched scanned worksheets, handwritten name recognition, fuzzy roster matching, session resume for large batches (99-image limit), teacher grading automation.

Audit frontend codebases for security vulnerabilities and bad practices. Use when performing security reviews, auditing code for XSS/CSRF/DOM vulnerabilities, checking Content Security Policy configurations, validating input handling, reviewing file upload security, or examining Node.js/NPM dependencies. Target frameworks include web platform (vanilla HTML/CSS/JS), React, Astro, Twig templates, Node.js, and Bun. Based on OWASP security guidelines.

작업 시작 (Supabase DB 기반). Use when (1) "랜드 #123 작업 진행", (2) "#45 시작하자", (3) "이슈 작업 시작해줘". 이슈 상태 변경 + 브랜치 생성 + Draft PR.

Supabase CLI를 활용한 데이터베이스 타입 생성 및 동기화. PROACTIVELY use when (1) DB 스키마 변경 후 타입 업데이트, (2) Repository 구현 전 타입 확인, (3) 새 테이블/컬럼 추가 시, (4) 타입 불일치 오류 발생 시. Cloud 환경 전용 - On-Premise는 수동 타입 정의 필요.

프로덕션 배포 게이트 확인. Use when: (1) 프로덕션 배포 가능 여부 확인, (2) 미완료 테스트 이슈 체크, (3) 배포 준비 상태 리포트.

Interactive project creation from cm-template. Use when (1) user requests new service creation, (2) creating new cm-* project, (3) need guided wizard for project configuration, (4) generating ready-to-copy project in implement-dist/.

워크플로우 진행 상황 조회. Use when (1) 현재 워크플로우 진행도 확인, (2) 워크플로우 히스토리 조회, (3) 진행 중인 워크플로우 목록.

SEMO 패키지 피드백 수집 및 이슈 생성 (Supabase DB 기반). Use when (1) /SEMO:feedback 명령어 호출, (2) 사용자가 SEMO 동작 오류 지적, (3) 개선 제안 요청.

Create Epic issue in docs repository. Use when (1) ideate 스킬에서 자동 호출, (2) epic-master needs to create new Epic, (3) 요구사항 → Epic 변환.

아이디어 탐색부터 Epic 생성까지 원스톱 워크플로우. Use when (1) 러프한 아이디어가 있을 때, (2) 새 기능/프로젝트 구상 시, (3) "뭔가 만들고 싶어", (4) 가설 수립 및 검증 필요 시.

개발 환경 및 인증 상태 자동 검증. Use when (1) 온보딩 시 환경 확인, (2) 도구/인증 상태 체크, (3) `/SEMO:health-check` 명령, (4) orchestrator 업무 시작 시 자동 실행.

SEMO 도움말 및 Semicolon 팀 컨텍스트 응답 (공통 Skill). Use when (1) /SEMO:help 커맨드, (2) "도움말", "SEMO란", "어떻게 해" 키워드, (3) SEMO 사용법 질문.

회의록에 안건 추가. 자연어로 요청하여 GitHub Discussion 회의록에 안건을 추가합니다. Use when (1) "회의록에 안건 추가해줘", (2) "이번 주 회의에서 논의할 내용 추가", (3) "회의 안건으로 OOO 넣어줘", (4) 회의 안건 등록 요청.

정기 회의록 GitHub Discussion에 자동 생성. Use when (1) "정기 회의록 생성해줘", (2) /create-meeting-minutes 커맨드, (3) "이번 주 회의록 만들어줘", (4) 이터레이션 기반 회의록 생성 요청.

SEMO 패키지 버전 체크 및 업데이트 알림. Use when: (1) 새 세션 시작 시 자동 체크, (2) 수동 버전 확인 요청, (3) SEMO 업데이트 실행.

전체 SEMO 패키지 통합 품질 감사. Use when (1) 전체 패키지 품질 점검, (2) Agent/Skill/Command 표준 준수 검토, (3) 비효율적 구조 탐지, (4) 정기 감사 수행.

Use when creating new skills or editing existing skills - applies prompt engineering principles to write clear, goal-focused process documentation that trusts LLM intelligence

Implement features from task specifications using Test-Driven Development (TDD) with bmad-commands for file operations and testing. This skill should be used when implementing new functionality from approved task specs.

Atomic command primitives for BMAD operations. Provides type-safe, testable wrappers around file operations and test execution with structured JSON I/O and built-in telemetry. This skill should be used when BMAD workflows need deterministic, reliable primitive operations with observability.

Rustでのエラー設計を、境界ごとに thiserror / anyhow を使い分けて実装する。ドメイン/ライブラリは型付きエラー(thiserror)、アプリ境界のみ anyow。context付与、unwrap禁止、HTTP/CLI変換の指針を含む。

sdd-initで作成したSpecドラフトを入力として、TDDを回せるだけのテスト観点（ハッピー/代表的失敗/境界/不変条件/非機能）をSpecに網羅する。ここではテスト実装・プロダクション実装は行わない。スコープ変更・要件追加もしない（必要なら未決事項として質問を起票し、合意が取れるまでTDDへ進ませない）。出力は「Specの更新（テスト戦略・テストケース一覧・カバレッジチェック）」「ブロッカー/未決事項」「tdd-redに渡す“次に書くべきテスト1つ”候補」に限定する。

sdd-slice-wishで決めた「推奨スライス」を入力として、仕様書 docs/specs/YYYYMMDD-{name}.md のドラフトを作成する。ここでは実装もテスト実装も行わない。テストケースの網羅（境界・異常・不変条件の列挙）は sdd-test-cases の責務。

Use when needing to retrieve information from past sessions, conversations, or stored knowledge. Triggers on questions that could benefit from historical context including user preferences, past discussions, workflows, coding patterns, or any query where previous session information would be helpful. Activates broadly for retrieval queries.

Guide for creating multi-phase skills with orchestrated sequential execution. Use when user wants to create a skill that runs multiple steps in sequence (like gap-finder), needs a start-* orchestrator pattern, or asks about multi-step/multi-phase skill architecture.

Load when executing spec/design/plan/implement commands for a specific feature. Provides templates, agent dispatch patterns, and workflow orchestration for per-feature work.

Use when user explicitly requests to coordinate with other Claude Code agents, join an agent chat, or communicate across multiple repositories/projects

Parse and analyze personal financial transaction CSV exports to calculate account totals and generate detailed breakdowns. Use when the user asks to analyze transaction data, generate financial summaries, calculate account balances, or review spending from CSV exports. Supports account grouping (Galicia, Mercado Pago, Quiena, LLC/Relay, HSBC, Crypto), automatic internal transfer detection, and detailed transaction listings.