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 →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.
Implement delivery and logistics systems including food delivery, package delivery, driver management, and real-time tracking. Use when building delivery apps, courier services, food delivery platforms, or last-mile logistics applications. Triggers on requests for delivery tracking, driver dispatch, food ordering, courier management, or fleet operations.
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.
Desenvolve aplicações Vue 3 seguindo arquitetura Feature-Sliced Design (FSD), implementando lazy loading, code splitting, e padrões de performance. Use quando desenvolvendo features, componentes, ou trabalhando com Vue 3 neste projeto.
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.
Design product behavior and user experience with a product designer mindset. Use when shaping features, reviewing UX, improving flows, evaluating usability, clarifying copy, or making user-facing trade-off decisions.
Rosetta ad-hoc adaptive meta-workflow that constructs, tracks, reviews, and executes a tailored execution plan per user request. Use when no other specific workflow matches the request.
Run the validation pipeline and produce a short markdown report.
Run Frontend/UI QA: Storybook coverage and visual checks, responsive behaviour, component consistency. Use when the user runs a full QA, /qa-frontend, or asks for frontend-only QA. Output structured findings in the QA report format.
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
Autonomous PR creation from a worktree branch.
Re-ask the voice and beneficiary questions and update .bodega.md. Useful when the user's preference changes or the store is being handed off to someone new.
Internationalization (i18n) and Localization (L10n) best practices.
Regenerate the entire design system from a new brand color while preserving the project type. Updates .forge.json and shows what changed.
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.
Generate responsive breakpoint tokens: sm through 2xl.
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.
Rebuild the semantic token mapping from your palette. Maps surface, text, border, accent, and feedback tokens to specific palette shades based on project type.
Guidance for `effect/Filter` focused on APIs like Fail, make, and Filter. Load after `effect-skill-router` when this module is the primary owner.
Equip an agent with the capability to **reduce a problem to foundational truths** and recombine them into novel solutions.
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.
Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI. Generates creative, polished code that avoids generic AI aesthetics.
Guidance for `effect/Console` focused on APIs like dir, log, and info. Load after `effect-skill-router` when this module is the primary owner.
Guidance for `effect/Boolean` focused on APIs like isBoolean, or, and and. Load after `effect-skill-router` when this module is the primary owner.
Comprehensive guide for Manim Community - Python framework for creating mathematical animations and educational videos with programmatic control
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.
Safe HTML templating patterns for Cloudflare Worker using Hono. Use when injecting dynamic content into HTML responses, generating meta tags, or rendering server-side HTML with user data.
When changing DB schema or permission dimensions, consider predefined roles and bucket_role / role-related code.
Explain how a file, folder, or feature works
Create or update product briefs through guided or autonomous discovery. Use when the user requests to create or update a Product Brief.
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.
Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images.
- **Step 1** of the integrated pipeline: **1) agi-schedule-shift** → 2) agi-schedule-daily-update → 3) agi-schedule-pipeline-check → 4) weather-go-nogo.
Add or insert a new numbered pipeline step in the p2cs_project, following the standardized Step/DataFile/explore notebook patterns and safely renumbering subsequent steps (code, data, figures, tests, config, dependencies, and imports) when inserting in the middle of the pipeline. Use when creating a new step_* directory, inserting a step between existing ones, or updating step numbers across the project.
Создать пустой внешний отчёт 1С (scaffold XML-исходников)
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.
- Purpose: check proofs against expectations