ci-loop
Babysit CI after a push: a monitor→classify→remediate state machine that watches a run to completion, mechanically fixes trivial/build breakage, reproduces test failures locally to tell a flake from a real bug, reruns suspected flakes within a budget, hands reproduced failures to a fixer that commits a fixup and pushes, and loops until CI is green or it can justify a bail back to the user. Prefers a deterministic dynamic workflow when available; falls back to in-instance Task dispatch. Use when the user types /ci-loop or asks to watch/babysit/auto-fix CI for a pushed branch or PR until it's green.
codify
Turns an observed agent misbehavior, or a correction the user just gave, into a durable fix: a hook that makes the behavior impossible, a CLAUDE.md rule, a change to the skill that was running, or a new reusable skill. Picks the narrowest home that removes the failure mode, checks for an existing rule to tighten before adding one, and keeps CLAUDE.md from bloating. Invoked via /codify when an agent goes off the rails on something the user does not want repeated.
decision-records
Where a decision goes and how it is written down so the next reader finds it: architecture decision records (ADRs, amended by addendum and never by silent edit), protocol-change proposals for frozen interfaces, design notes with a status lifecycle, adversarial review waves with a triage roll-up, and corrections filed on the issue rather than only in a commit. Use when a decision was just made and needs a home, when an existing ruling needs revisiting, when a review wave is being filed, or with `init` to scaffold the whole decision layout in a repo that has none. Pairs with `handoff` (the next.md rewrite) and `doc-graph` (per-package docs).
doc-graph
Set up and maintain a per-package documentation graph in any repo: one CLAUDE.md per package (Purpose, Key Types, Relationships, Traffic, Invariants, Deep Docs) with a byte-identical AGENTS.md mirror, a no-toolchain gate script that checks coverage, mirror equality, git-time staleness and file:line citation drift in docs/, and a repo-customized doc-gardening skill that regenerates stale docs from source. Use `init` in a repo that has none of this (it detects the language and layout, asks what the repo's traffic vocabulary is, installs scripts/doc_check.sh, a make target, a CI job, and .claude/skills/doc-gardening/), or `check` and `garden` in a repo that already has it. Pairs with `decision-records` and `handoff`.
doc-gardening
>
explainer-video
>
go-debug
Interactively debug Go programs in a single context using Delve (dlv) driven through tmux. Use when a bug requires runtime inspection — stepping through code, examining variables, walking goroutines, attaching to a live process, or debugging a hanging integration test — rather than just reading the source. Triggers include "step through this", "set a breakpoint", "attach to the running server", "why is this goroutine stuck", "debug this failing test".
handoff
Rewrite the repo's session handoff document (docs/next.md) at the end of a body of work: re-baseline every claim against the tree and CI rather than carrying it forward, name where the previous edition was wrong, record the rulings nobody should re-litigate and the gaps deliberately left open, and order what to do next with exit criteria. Also `init` to create the handoff and a starter docs/execution.md (how waves are planned, sub-agents briefed, and gates verified) in a repo that has neither. Use when finishing a milestone, a wave, or a PR series; when a fresh session cannot tell where the tree is; or when next.md and the code disagree. Pairs with `decision-records`.
hunk
Line-level git staging and non-interactive rebase for agents that know exactly which lines they changed. Use when you need atomic commits carved out of a larger diff, or when you need to squash/drop/reorder/reword commits without interactive prompts.
incremental-commit
Create incremental, atomic commits that tell a story with detailed commit messages. Use when the user asks to commit changes, split a diff into logical commits, or wants a clean commit history instead of one large commit. Triggers include "commit this", "make atomic commits", "break this into commits", "/incremental-commit".
litbucket
Publish, search, and inspect internal Litbucket static artifacts. Use when asked to publish a site, dashboard, notebook, report, or other static bundle to an internal address, to find one that already exists, or to share a generated artifact with the team. Triggers include "publish this to litbucket", "put this on lightning.wiki", "find the <name> dashboard", "give me a link to this report".
lnget
Use lnget to fetch resources from L402-protected URLs that require Lightning payments. Covers basic fetching, payment limits (max cost, max routing fee), token cache management, and Lightning backend status. Use when an HTTP request returns 402 Payment Required and a Lightning micropayment is needed, or when downloading files behind a Lightning paywall.
orchestrate
Expensive planner (Opus 4.8 / Fable 5) decomposes a task into independent work items, a fleet of cheap Sonnet 5 (or Haiku 4.5) workers executes them in parallel via a Workflow, and the planner synthesizes the results. Emulates the native orchestrator pattern in Claude Code: keep the expensive model scarce (one planning pass, one synthesis pass) and the cheap model abundant (N parallel workers). Prefers a deterministic dynamic workflow when available; falls back to in-instance Task dispatch. Use when the user types /orchestrate or asks to decompose, fan out, or parallelize a task across independent workers.
review-loop
Adversarial review→triage→fix loop until a cold verifier signs off. Fans out lens-specific reviewer subagents, verifies every finding against the code (killing false positives), auto-applies confirmed fixes as fixup commits, and repeats until a fresh verifier approves. Prefers a deterministic dynamic workflow when available; falls back to in-instance Task dispatch. Use when the user types /review-loop or asks to adversarially review-and-fix a change set, branch, or commit range until clean.
technical-writing
Clear-writing guide distilled from Steven Pinker's \"The Sense of Style,\" with mechanical checks from Google's developer documentation style guide. Use when writing or revising prose that must be clear to a reader — documentation, design docs, specs, explanations, essays, emails, reports, RFCs, release notes — or when asked to make writing clearer, tighter, less academic, or less jargon-laden. Activate for \"make this clearer\", \"tighten this\", \"why is this hard to read\", \"edit this for clarity\", or any prose-quality pass. Also activate when prose is dense, overwritten, or hard to parse on the first read: sentences packing three ideas, invented metaphors and analogies the reader must decode, anthropomorphized systems, or phrasing that shows off instead of informing.
test-refine
Refines an existing Go test suite — removes trivial/duplicate tests, strengthens weak assertions, reshapes tests around invariants, and closes branch-coverage gaps. Uses code-guided coverage and (when available) gremlins mutation-testing survivor data rather than relying on line coverage alone. Use when test quality is uneven, after a test-generation pass, before opening a PR, or as a quality gate on critical paths (consensus, channel state, payment flows). Triggers: "refine these tests", "tests are bloated", "tighten assertions", "remove trivial tests", "audit test quality", "/test-refine".
meme-scout
Comprehensive tool for scouting trending meme coins on DEX platforms like DexScreener. Use for discovering trending tokens, analyzing price movements, volume data, and risk assessments. Supports multiple timeframes (5m, 1h, 6h, 24h) and includes risk checking capabilities for specific tokens.
token-minter
Generate, build, and deploy custom ERC20 tokens on EVM networks. Use when users want to create and deploy their own ERC20 tokens with custom parameters like name, symbol, decimals, and initial supply. Supports deployment to various networks including Sepolia testnet and requires Foundry (forge/cast) for blockchain interactions.
trading-strategist
Provides trading strategies for cryptocurrencies based on Binance market data, calculated technical analysis indicators, and aggregated market sentiment from crypto RSS news feeds. Use when users ask for trading advice, strategy recommendations, or analysis combining price data, TA, and sentiment for crypto assets like ETH, BTC, or altcoins.
yield-opportunities
Comprehensive tool for finding and analyzing DeFi yield opportunities across protocols, chains, and asset types. Use when users want to earn yield on crypto assets (staking, lending, liquidity farming, aggregators). Supports exhaustive parallel research using librarian agents, direct web searches, and GitHub repository analysis.
evm-swiss-knife
Interact with EVM-compatible blockchains using Foundry's cast tool for querying balances, calling contracts, sending transactions, and blockchain exploration. Use when needing to interact with Ethereum Virtual Machine networks via command-line, including reading contract state, sending funds, executing contract functions, or inspecting blockchain data.
market-sentiment
Aggregate news from popular cryptocurrency RSS feeds, analyze sentiment of articles, and calculate an overall market sentiment score with detailed explanation. Use when assessing crypto market sentiment for trading decisions, research, or monitoring trends from RSS sources.
seo-audit
Audit websites for SEO, technical, content, security, JS rendering, and AI readiness using SEOmator CLI. Returns LLM-optimized reports with health scores across 373 rules and 20 categories, and can diff two audits to show what a deploy changed. Use when analyzing websites, debugging SEO issues, checking site health, or comparing a site before and after a change.
Ant Design 规范助手
智能化的 Ant Design 开发助手，提供代码生成、规范检查、最佳实践指导、Figma 设计稿转代码等功能
rp-why
Load when reflecting on AI collaboration quality or tracking growth over time. Analyzes session history to surface how deeply you think with AI tools and whether your orchestration sophistication matches your cognitive depth. Provides actionable nudges to push toward more strategic work.
testing-strategy
Guidelines for writing effective tests in this project
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
code-review
Comprehensive code review checklist for pull requests
goose-blog-post
Write and publish blog posts for the block/goose open source project
api-setup
Set up API integration with configuration and helper scripts
beads
Use beads (bd) for persistent task tracking in coding projects. A git-backed issue tracker designed for AI agents with dependency graphs, hierarchical tasks, and multi-agent coordination.
voop
Upload files to the web instantly and get a public URL. Use when the user asks to share a file online, publish a file to the web, get a public link for a file, upload HTML/images/PDFs to share, or needs a quick way to make any local file publicly accessible. Trigger phrases include "upload this", "share this file", "publish to web", "get a public URL", "make this accessible online".
ag-skill-creator
Creates and evaluates Agent Skills following the official specification. Use when the user wants to create a new skill, scaffold a skill directory, evaluate or validate an existing skill, or needs guidance on skill structure and format.
cc-skill-creator
Creates and evaluates Agent Skills following the official specification. Use when the user wants to create a new skill, scaffold a skill directory, evaluate or validate an existing skill, or needs guidance on skill structure and format.
cp-skill-creator
Creates and evaluates Agent Skills following the official specification. Use when the user wants to create a new skill, scaffold a skill directory, evaluate or validate an existing skill, or needs guidance on skill structure and format.
macos-disk-cleanup
Safely analyze and clean a nearly full macOS disk, with special handling for Git Worktrees, Codex/Claude worktrees, Conductor workspaces, build artifacts, package caches, Xcode/CoreSimulator data, Android AVDs, installers, temporary directories, active processes, and root-owned residues. Use when the user says the Mac disk is full, asks for a deep disk-space analysis, wants cleanup candidates graded by safety, approves P0/high-confidence cleanup, or suspects many project Worktrees are consuming space.
pr-review-loop
Submit or monitor a GitHub pull request with a short polling loop that waits for automated review, fixes actionable feedback, pushes updates, and stops only when the PR has no unresolved review feedback and is merge-ready. Use when the user asks to create a PR and keep checking AI or GitHub code review suggestions every few minutes.
ship
Commit, push, and create a PR in one step. Use when the user says 'ship', 'ship it', '/ship', '提交PR', '发PR', or wants to commit + push + create a pull request in a single action.
video-downloader
Download videos using yt-dlp. Use when user asks to download video, download audio, download subtitles, or provides a video URL from YouTube, Bilibili, Twitter, etc.
daily-news
Generate daily design inspiration & novel things report. Use when user asks for 'design news', 'design daily', 'design inspiration', '设计日报', '设计灵感', 'デザインニュース', 'what's new in design', 'novel products', '新奇事物'. Aggregates from Dribbble, Awwwards, Product Hunt, Behance, design influencers on Twitter, and more.
env-sync
Sync .env files from git root repository to worktrees. Use when asked to sync env, copy env, environment file, or when working in a git worktree that is missing a .env file. Automatically detects missing .env in worktrees.
code-standards
Setup universal code quality standards in your project. Use when the user wants to generate coding standards files (CLAUDE.md, AGENTS.md, GEMINI.md, etc.) or mentions 'code standards', 'code review setup', or similar intent in any language.
homeassistant-config
Create and manage Home Assistant YAML configuration files including automations, scripts, templates, blueprints, Lovelace dashboards, and file organization. Use when working with Home Assistant configuration files (.yaml, .yml) or discussing HA automations, scripts, sensors, or dashboards.
ableton-lom
Ableton Live Object Model (LOM) API reference for Python Remote Scripts and control surface development.
grabbit
Control the Grabbit CLI to record browser interactions (HAR) and generate API workflows. Use this skill when the user wants to: (1) Automate browser actions, (2) Capture web traffic for API analysis, (3) Create deterministic workflows from browsing sessions, or (4) Learn how to use the Grabbit CLI commands.
documentation-structure
Documentation architecture for this repository. Use when creating, updating, or reviewing README.md, CONTRIBUTING.md, or docs/ files. Covers separation of concerns, vendor documentation standards, cross-references, and validation.
skills-development
Use when authoring or revising plugin SKILL.md files in this repo. Captures the principles for keeping skills as compact shortcuts to MCP tool groups.
miro-code-explain-on-board
Use when the user wants to explain or visualize a codebase on a Miro board — produces a minimal, notation-correct set of architecture / structure / behavior diagrams (flowchart, UML class, UML sequence, ERD) plus a short companion document, grounded in real repo artifacts.
miro-code-review
Use when the user wants to create a visual code review on a Miro board from a pull/merge request (GitHub, GitLab, or any forge), local uncommitted changes, or a branch comparison — produces a file-changes table, summary/architecture/security docs, and architecture diagrams, then links them back from the PR/MR.
miro-code-spec
Use when the user wants to extract a Miro board's specs (documents, diagrams, prototypes, tables, frames, images) to local `.miro/specs/` files for AI-assisted planning and implementation — accepts a board URL or single-item URL.
Page 459 of 1656 · 82770 results