メニュー
このリポジトリの skills
SkillsMP は tools-only/X-Skills から 2,943 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
tools-only/X-Skills収集済み skill 2,943 件中 40 件を表示しています。
Structural analysis agent for schema comparison, pattern detection, cross-file relationship analysis, and migration planning across JSON, YAML, TOML, XML, CSV — handles schema drift detection, multi-file diffing, and batch analysis; includes enterprise XML…
原文の言語: 英語
Fast read-only exploration agent for querying structured data files using dasel v3 — discovers structure, lists keys, samples arrays, extracts values across JSON, YAML, TOML, XML, CSV, HCL, INI; includes enterprise XML domain patterns for InstallAnywhere…
原文の言語: 英語
Cross-reference research files with existing skills, agents, hooks, and plugins to discover integration opportunities. Reads research file, searches repo, validates claims against primary sources, and appends structured Integration Opportunities section.
原文の言語: 英語
Architectural review after linting-root-cause-resolver completes. Verifies resolution quality, examines artifacts in .claude/reports/, checks fixes align with codebase patterns and design principles, validates type safety improvements, code organization, and…
原文の言語: 英語
Resolve linting/type errors by investigating root causes, not silencing symptoms. Use when ruff, mypy, pyright, or basedpyright report issues. Researches rules, reads code context, loads python3-development skill, and elegantly rewrites code to fix underlying…
原文の言語: 英語
Teaches dasel v3 selector syntax, functions, and query patterns — answers how-do-I questions about dasel, helps construct selectors, explains v3 syntax differences from v2; includes enterprise XML domain patterns for InstallAnywhere .iap_xml, Spring bean XML,…
原文の言語: 英語
Warden skill: evaluates first-pass findings and proposes deterministic lint rules that could permanently catch the same patterns. Requires Warden's multi-pass pipeline (phase 2).
原文の言語: 英語
Make map animations with Mapbox
原文の言語: 英語
Sequencing patterns for Remotion - delay, trim, limit duration of items
原文の言語: 英語
Content quality reviewer. Evaluates E-E-A-T signals, readability, content depth, AI citation readiness, and thin content detection.
原文の言語: 英語
Sitemap architect. Validates XML sitemaps, generates new ones with industry templates, and enforces quality gates for location pages.
原文の言語: 英語
Comprehensive DAG failure diagnosis and root cause analysis. Use for complex debugging requests requiring deep investigation like "diagnose and fix the pipeline", "full root cause analysis", "why is this failing and how to prevent it". For simple debugging…
原文の言語: 英語
Manages Apache Airflow operations including listing, testing, running, and debugging DAGs, viewing task logs, checking connections and variables, and monitoring system health. Use when working with Airflow DAGs, pipelines, workflows, or tasks, or when the…
原文の言語: 英語
Performance analyzer. Measures and evaluates Core Web Vitals and page load performance.
原文の言語: 英語
577+ pattern prompt injection defense. Now with typo-tolerant bypass detection. TieredPatternLoader fully operational. Drop-in defense for any LLM application.
原文の言語: 英語
Review plan.md OR a single phase file against templates AND codebase compliance. Use after creating planning documents or when asked to 'review the plan', 'check the phase', 'verify template compliance'. Each invocation reviews ONE file only. Do NOT use for…
原文の言語: 英語
Write, review, or debug end-to-end tests using Playwright. Use when asked to 'write e2e tests', 'add Playwright tests', 'test this user flow', 'fix flaky tests', 'create a test suite', or 'debug this e2e failure'. Invoke with /playwright-e2e or when user…
原文の言語: 英語
Software architecture specialist for Next.js/Supabase SaaS systems. Use PROACTIVELY when planning new features, designing database schemas, evaluating multi-tenant patterns, or making architectural decisions. Key capabilities: trade-off analysis,…
原文の言語: 英語
Improve a rough or thin prompt into a detailed, actionable one using project context. Use when the user types '/improve-prompt <rough idea>' or '/?? <rough idea>'. Takes a vague request and returns a well-structured prompt with specific file paths, project…
原文の言語: 英語
General-purpose development workflow for ad-hoc tasks outside of plans. Routes to the right domain skills (postgres-expert, server-action-builder, react-form-builder, service-builder, playwright-e2e), enforces task tracking, and follows a reference-grounded…
原文の言語: 英語
Review code for quality, security, and project pattern compliance, then auto-fix Critical/High issues. Use after implementing a phase, completing a feature, or modifying existing code ('review this code', 'check my implementation', 'audit this PR', 'review…
原文の言語: 英語
Creates Claude Code agent files from requirements — handles discovery, template selection, frontmatter generation, scope determination (project/user/plugin), and plugin.json updates. Use when the user asks to create an agent, generate an agent, add an agent…
原文の言語: 英語
Focused engineering agent that executes ONE task at a time. Use when implementation work needs to be done — writing code, creating files, modifying existing code, running commands. Key capabilities: skill-aware (dynamically loads postgres-expert,…
原文の言語: 英語
Independent review agent that performs comprehensive code review and validation after a builder completes work. Invokes `/code-review` for reference-grounded analysis, auto-fixes Critical/High issues, runs verification (typecheck + tests), and reports…
原文の言語: 英語
Implement phases from a plan. Acts as thin dispatcher: spawns builder agents per phase, validators to verify, handles PASS/FAIL routing. Builders are ephemeral — each phase gets a fresh builder with clean context. Use when ready to implement ('implement the…
原文の言語: 英語
Create, edit, and export draw.io diagrams via the draw.io MCP server with real-time browser preview. Use when asked to 'create a diagram', 'draw a flowchart', 'make an architecture diagram', 'visualise this system', or 'update the diagram'. Do NOT use the…
原文の言語: 英語
Create client-side forms with react-hook-form, shadcn/ui form components, and server action integration for Next.js/Supabase applications. Use when building forms with validation, error handling, and loading states ('create a form', 'build the settings form',…
原文の言語: 英語
Create, review, optimize, or test PostgreSQL and Supabase database code including schemas, migrations, functions, triggers, RLS policies, and PgTAP tests. Use when asked to 'create a migration', 'write RLS policies', 'design the schema', 'add a table',…
原文の言語: 英語
Create Next.js Server Actions with Zod validation, authentication, and service layer integration for Next.js/Supabase applications. Use when implementing mutations, form submissions, or API operations that need authentication and validation ('create a server…
原文の言語: 英語
Perform a high-level flow audit of an implementation plan, analyzing phase-to-phase dependencies, data flow consistency, ordering logic, stale artifacts, and risk assessment. Use when asked to 'audit the plan', 'check plan flow', 'review plan dependencies',…
原文の言語: 英語
Phase-level implementation workflow for builder agents. Handles reading phase files, finding references, invoking domain skills, implementing all steps, and running verification (tests + typecheck). Preloaded into builder agents via skills: field — not…
原文の言語: 英語
Code quality and Next.js/TypeScript pattern compliance reviewer. Use PROACTIVELY after writing or modifying TypeScript/React/Next.js code. Key capabilities: TypeScript strictness (no any), Server Action validation, RLS validation, import ordering, server-only…
原文の言語: 英語
Documentation and codemap specialist for Next.js/Supabase projects. Use PROACTIVELY after feature implementations to update CLAUDE.md, architecture maps, and guides. Analyzes project structure and generates accurate docs. Trigger phrases: 'update the docs',…
原文の言語: 英語
Research and document a single tool, library, or resource into a structured research entry. Gathers information from primary sources using MCP tools and gh CLI. Creates comprehensive markdown entries following the standard template. Works standalone or…
原文の言語: 英語
Creates Claude Code hook scripts for plugins — generates Node.js .cjs files, wires hooks.json, selects correct event and scope. Use when creating hooks, wiring PostToolUse or PreToolUse logic, enforcing validation on tool calls, or building SessionStart…
原文の言語: 英語
Onboarding wizard that customizes this Claude Code setup for your specific project. Collects project details through a structured intake questionnaire, then fills all CUSTOMIZE markers across CLAUDE.md and rule files automatically. Use when first adopting…
原文の言語: 英語
Build pure, interface-agnostic services with injected dependencies for Next.js/Supabase applications. Use when creating business logic, CRUD services, or data access layers ('create a service', 'build the project service', 'add a delete method', 'write the…
原文の言語: 英語
Create complete implementation plans with phases for new features or projects. Use when starting a new feature, planning a refactor, or designing a system ('create a plan', 'plan this feature', 'design the phases for...', 'plan the implementation'). Do NOT…
原文の言語: 英語
Test-Driven Development specialist enforcing write-tests-first methodology. Uses Vitest with happy-dom. Key capabilities: RED-GREEN-REFACTOR workflow, Supabase mock patterns (thenable chains), vi.hoisted() for pre-module mocks, component testing with…
原文の言語: 英語
Structured multi-step reasoning via the Sequential Thinking MCP server. Use when asked to 'debug this complex bug', 'help me decide between X and Y', 'analyze this tricky problem', 'think through this step by step', 'what's causing this intermittent failure',…
原文の言語: 英語