>
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →>
Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.
Tailwind v4 + shadcn/ui
Maintain a development log (DEVLOG.md) at the project root. Use at the START and END of every coding session, after implementing features, fixing bugs, refactoring code, or making any meaningful code changes. Automatically triggered for all development tasks.
Reviews local git changes and generates a pull request summary following the project template. Use when the user asks to automate PR summary, generate PR description, fill PR template, or review local changes for a PR.
Implement new MCP tools in the deno-mcp-template project. Provides the exact file structure, type signatures, registration steps, and patterns for standard tools, sampling tools, form and URL elicitation, resource-backed tools, and notification tools. Use when adding a new tool, creating MCP tools, or asking how tools work in this project.
Johnny Decimal + PARA organization
Create a new Vite plugin in the @taucad/vite package following project conventions and Vite 8 best practices. Use when adding a Vite plugin, creating dev server middleware, implementing build transforms, or extending Vite configuration for the Tau monorepo.
Sync .env from 1Password using env_var_mappings.
>
'Stage files and create a conventional commit with a well-formed message.'
Reproduce and debug Android bugs on an emulator using ADB. Covers emulator setup, test data seeding, UI navigation via uiautomator, log capture, and screenshots. Use when the user asks to reproduce a bug, debug an issue on an emulator, or investigate an Android crash/behavior.
Building Blazor apps. Hosting models, render modes, routing, streaming rendering, prerender.
Personalizes a fork of this Cloudflare multi-worker monorepo—worker names in wrangler, package names, README, and UI—so deploys and docs are not stuck on starter kit defaults. Use when the user created a repo from the template, wants to deploy their own app, or asks to rename workers, rebrand, or remove generic starter kit copy. Skip when developing the upstream starter kit (origin URL contains firtoz/cf-multiworker-starter-kit; canonical https://github.com/firtoz/cf-multiworker-starter-kit) unless the user explicitly asks.
'Use when staging and committing code changes with conventional commit messages'
>-
Elite UX engineer scouting friction points and optimizing user-centered design. User flows, conversion optimization, and design system enforcement.
Create a GitHub Pull Request to merge the current branch into main with a well-structured title and description using GitHub CLI. Use when the user asks to create a PR, open a pull request, submit a merge request, or send changes for review.
Use when building data tables with flowers-nextjs-table. Provides API reference, column definitions, pagination patterns, styling guidance, and troubleshooting for the headless React/Next.js table component.
Import/export validation post-implementation. Checks that all imports resolve to actual exports, catches broken references and circular dependencies.
>-
>-
Preflight check — verifies the user's environment has everything Bodega needs (Node, package manager, Vercel CLI, gh CLI, Next.js if adapting). Reports clearly what's missing and how to fix it. Auto-invoked at the start of setup; can also be run standalone.
Security and compliance for MCPAtlas: threat model, RBAC, audit, supply chain, input validation, plugin sandbox. Use when implementing auth, hardening, or reviewing security-sensitive code.
Create, validate, align and audit stk (salk_toolkit) JSON data meta annotations for survey datasets. Use when working with _meta.json files, infer_meta, read_annotated_data, read_and_process_data, or when the user mentions survey annotations, metafiles, data alignment, or category mapping.
Evidence-first ECC Tools burn and billing audit workflow. Use when investigating runaway PR creation, quota bypass, premium-model leakage, duplicate jobs, or GitHub App cost spikes in the ECC Tools repo.
azure-auth
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
Implements Geoffrey Huntley's Ralph Wiggum autonomous iteration technique for managing LLM context. Use when working on long-running tasks, when context is getting polluted, or when you need autonomous development with deliberate context rotation. Treats LLM context like memory - rotates to fresh context before pollution builds up, with state persisting in files and git.
After coding changes, fully verify and test the remote site (findtorontoevents.ca) using Playwright and HTTP fallback—events load, no JS errors, key features present.
Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript and Python implementations.
Fill changelog entries for the current branch. Use when the user asks to fill changelog, write changelog entries, update changelog, or prepare changelog for a PR.
Run all linting, type checking, tests, Markdown lint, and documentation build for the project. Check for errors and warnings, then fix any problems found. Use when the user asks to run checks, verify the build, run CI locally, or fix lint/type/test errors.
Automates RoEFactura releases by analyzing commits vs main, inferring semver bump, drafting CHANGELOG, then after a single user approval creates r/x.x.x, packs, pushes NuGet, and optionally tags/GitHub release. Use when the user asks to release, publish, bump version, push to NuGet, or cut a new release.
*nd*You** (the lead) do the commits. Do not dispatch sub-agents to commit.
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
Reviews code changes with findings-first output focused on correctness, security, regression risk, and test gaps. Use when reviewing diffs, commits, pull requests, or when the user asks for a code review.
When changing DB schema or permission dimensions, consider predefined roles and bucket_role / role-related code.
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
>-
OpenUI generative UI with Vercel AI SDK. streamText, toUIMessageStreamResponse, and tools support.
>-
DART CI/CD troubleshooting - GitHub Actions, cache debugging, platform-specific failures
Expert guidance for building and editing n8n workflows with Synta MCP tools. Use for creating new workflows, modifying existing workflows, template discovery, node configuration, validation, and connection management in n8n.
Reviews UI foundation, UI generation, and frontend implementation outputs or produced frontend code for consistency, usability, accessibility, responsiveness, correctness, and implementation readiness, then produces a structured QA verdict with required revisions.
Design and resolve RFC documents through evidence-gated multi-round workflow. Use when planning large architectural/program-level changes in docs/rfcs, enforcing goal/scope/direction clarity, explicit first-principles/long-term/original-fit proposal lenses with rationale, draft-to-formal progression, and resolve-time synchronization with task/backlog outcomes before issue closure.
Interact with Cloudflare R2 buckets used by Pagecord. Use when the user wants to list objects, inspect bucket stats, fetch files, or check backup integrity in R2.
Investigate and fix a Sentry issue in this codebase. Use when the user provides a Sentry issue URL or ID and wants diagnosis, a fix, verification, or a PR.
Development workflow guide. Covers build, test, lint, format commands, package structure, Git hooks, TDD methodology, and coding conventions. Use when setting up dev environment, running tests, or following project conventions.
Query the Seq logging server to retrieve and analyze application logs.