Use when you need to run Flow type checking, or when seeing Flow type errors in React code.

Use when adding new error messages to React, or seeing "unknown error code" warnings.

Use when you need to run tests for React core. Supports source, www, stable, and experimental channels.

Create and submit a GitHub PR from the current branch

Automated code review for pull requests using multiple specialized agents

Update documentation pages to match source code changes on the current branch

Update a GitHub PR description with a summary of changes

Document a Python module and its classes using Google style

Create changelog files for important commits in a PR

Comprehensive guidelines for Obsidian.md plugin development including all 27 ESLint rules from eslint-plugin-obsidianmd v0.1.9, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, locale file sentence-case enforcement, and submission requirements. Use when working with Obsidian plugins, main.ts files, manifest.json, Plugin class, MarkdownView, TFile, vault operations, or any Obsidian API development.

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

Explains ev-node architecture, components, and internal workings. Use when the user asks how ev-node works, wants to understand the block package, DA layer, sequencing, namespaces, or needs architecture explanations. Covers block production, syncing, DA submission, forced inclusion, single vs based sequencer, and censorship resistance.

小红书全能助手 — 文案生成、封面制作、内容发布与管理。当用户要求写小红书笔记、生成小红书文案/标题/封面、发小红书、搜索小红书、评论点赞收藏等任何小红书相关操作时使用。支持一站式从文案创作到自动发布的完整流程。

The Citadel Lite Security Framework - 100 foundational protocols to harden AI agents.

When writing a git commit message. When task completes and changes need committing. When project uses semantic-release, commitizen, git-cliff. When choosing between feat/fix/chore/docs types. When indicating breaking changes. When generating changelogs from commit history.

Verify claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that MUST use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Triggers on "fact check", "verify claims", "check against primary sources", or when backlog items are marked UNVERIFIED.

Identify required inputs, dependencies, and uncertainty during planning. Use when generating plans or task graphs under incomplete information. Does not block plan generation; instead localizes gaps and creates unblock dependencies.

Add resources to the research directory with comprehensive documentation. Supports single URL, batch processing via --batch, re-research via --rerun, and validation via --validate. Triggers on "add to research", "document this tool", "research this", or URLs to novel agentic development resources.

Global contract for all specialist subagents — enforces role boundaries, scope discipline, and DONE/BLOCKED status signaling. Use when loading any agent that should operate as a bounded specialist following supervisor delegation patterns.