All skills
extract errors
84Use when adding new error messages to React, or seeing "unknown error code" warnings. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more. runs entirely locally.
feature flags
88Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React. | File | Purpose | |------|---------| | packages/shared/ReactFeatureFlags.js | Default flags (canary), EXPERIMENTAL overrides | runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.
fix
88Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.
flags
88Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels. | Option | Purpose | |--------|---------| | (none) | Show all flags across all channels | | --diff <ch1> <ch2> | Compare flags between channels | | --cleanup | Show flags grouped by cleanup status | runs entirely locally. W…
flow
88Use when you need to run Flow type checking, or when seeing Flow type errors in React code. | Renderer | When to Use | |----------|-------------| | dom-node | Default, recommended for most changes | | dom-browser | Browser-specific DOM code | | native | React Native | runs entirely locally; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.
test
88Use when you need to run tests for React core. Supports source, www, stable, and experimental channels. Run tests for the React codebase. Release Channels: Common Mistakes: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.
verify
88Use when you want to validate changes before committing, or when you need to check all React contribution requirements. Run all verification steps. Run these first in sequence: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.
n8n cli
88Use the n8n CLI to manage workflows, credentials, executions, and more on an n8n instance. Use when the user asks to interact with n8n, automate workflows, manage credentials, or operate their instance from the command line.
n8n:content design
88> You are a Senior Content Designer specializing in SaaS tools. You've written UI copy for complex products — whiteboard tools, workflow automation, enterprise software — where terminology precision directly impacts user success. You treat requires Vendor-specific API key; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.
n8n:conventions
88Quick reference for n8n patterns. Full docs /AGENTS.md Use this skill when you need quick reminders on critical patterns. import { UnexpectedError } from 'n8n-workflow'; runs entirely locally; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.
n8n:create community node lint rule
88>- Guide for adding new ESLint rules to packages/@n8n/eslint-plugin-community-nodes/. All paths below are relative to packages/@n8n/eslint-plugin-community-nodes/. Before writing code, clarify: runs entirely locally; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.
n8n:create issue
88Create Linear tickets or GitHub issues following n8n conventions. Use when the user asks to create a ticket, file a bug, open an issue, or says /create-issue. Create a Linear ticket or GitHub issue for: $ARGUMENTS makes outbound network calls; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.
n8n:create pr
88Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
n8n:create skill
88>- Use when the user works with PDFs, forms, or document extraction. Skills are markdown (plus optional scripts) that teach the agent a focused workflow. Keep SKILL.md short—the context window is shared with chat, code, and other skills. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.
n8n:db migrations
88Authors n8n database migrations. Use when creating or modifying files under packages/@n8n/db/src/migrations/, when the user asks to add a column, table, index, foreign key, or backfill, or when the user mentions DB migrations or TypeORM migrations.
n8n:design system
88Guidelines on using Design System styles and components. Use when working on .vue files in packages/frontend. Triggers for tasks that include component architecture, styling, UI changes, or feature work.
n8n:node add oauth
88Add OAuth2 credential support to an existing n8n node — creates the credential file, updates the node, adds tests, and keeps the CLI constant in sync. Use when the user says /node-add-oauth.
n8n:protect endpoints
88Applies n8n's RBAC scope decorators to REST endpoints. Use when creating a new @RestController, adding any @Get/@Post/@Put/@Patch/@Delete route to an existing controller, or reviewing endpoint authorization. Every authenticated endpoint must be gated by @ProjectScope or @GlobalScope.
n8n:reproduce bug
88Reproduce a bug from a Linear ticket with a failing test. Expects the full ticket context (title, description, comments) to be provided as input. Given a Linear ticket context ($ARGUMENTS), systematically reproduce the bug makes outbound network calls; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.
agent architecture audit
88Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
agent eval
88.com/joaquinhuigomez/agent-eval.git@6d062a2f5cda6ea443bf5d458d361892c04e749b runs entirely locally; runs on Docker. Works with Claude Code, Cursor, Cline and 23 more.
agent harness construction
88. Works with Claude Code, Cursor, Cline and 23 more. runs entirely locally.
agent introspection debugging
88Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use this skill when an agent run is failing repeatedly, consuming tokens without progress, looping on the same tools, or drifting away from the intended task. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 …
agent payment x402
88. Works with Claude Code, Cursor, Cline and 23 more.
agent sort
88Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
agentic engineering
88. Works with Claude Code, Cursor, Cline and 23 more.
agentic os
88Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
skill comply
88.run ~/.claude/rules/common/testing.md uv run python -m scripts.run --dry-run ~/.claude/skills/search-first/SKILL.md runs entirely locally; runs on Python. Works with Claude Code, Cursor, Cline and 23 more.
skill scout
88Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
skill stocktake
88.claude/skills/ | . Works with Claude Code, Cursor, Cline and 23 more.
agent customization
88**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax. DO NOT USE FOR: general coding questions (use default agent); runtime debugging or error diagnosis; MCP server configuration (use MCP docs directly); VS Code extension development. INVOKES: file system tools (read/write customization files), ask-questions tool (interview user for requirements), subagents for codebase exploration. FOR SINGLE OPERATIONS: For quick YAML frontmatter fixes or creating a single file from a known pattern, edit the file directly — no skill needed.
open pr
88Open a pull request with proper PR template, test coverage, and review workflow. Guides agents through creating a PR that follows repo conventions, ensures existing behaviors aren't broken, covers new behaviors with tests, and handles review via bot when local testing isn't possible. TRIGGER when user asks to "open a PR", "create a PR", "make a PR", "submit a PR", "open pull request", "push and create PR", or any variation of opening/submitting a pull request.