77,210 skills — best first
MUST use when writing Java scripts.
MUST use when writing PowerShell scripts.
Where writing artifacts live: kb/ for durable knowledge, work/ for scratch. Use when deciding where to read from or write to.
Writing improvement specialist for grammar, style, clarity, and structure
Write clean, atomic conventional commits from staged or uncommitted changes. Use when asked to commit, generate commit messages, or clean up git history.
Use when you have a spec or requirements for a multi-step task, before touching code
Use after a spec is approved - distills plan.md into context.md and a rolling markdown backlog
Use when creating or editing a skill and you need it to be discoverable, concise, and native to the target harness
Use when an agent needs to write user stories for a project
Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for managed-agent sessions with no open Office app.
Use when the user says "yeet" or "/yeet" to quickly stage, review, commit, and push all changes with a provided message
Clear description of what this skill does and when to use it. Use when the user asks about X or wants to work with Y. Include specific trigger phrases so agents auto-load it correctly. Max 1024 characters.
Download Zoom meeting transcripts. Use when asked to get transcripts from Zoom recordings, download Zoom meeting notes, or fetch Zoom call transcripts.
Search and read GitHub repository docs via the Zhipu CodePlan MCP zread server. Use when you need quick repo structure lookup or documentation search without cloning. Triggers: zread, search_doc, repo structure, read_file, GitHub docs search.
Zustand adapter for json-render's StateStore interface. Use when integrating json-render with Zustand for state management via @json-render/zustand.
2D game development principles. Sprites, tilemaps, physics, camera.
Prioritize brevity, directness, and clarity in all responses with minimal token usage.
`@expo/ui/swift-ui` package lets you use SwiftUI Views and modifiers in your app.
Write content to structured .txt files using markdown and XML formatting.
Send macOS notifications using display dialog method that works reliably in tmux.
Template for summarizing session state and context for continuity between Claude Code sessions. Use when ending a session or handing off work.
Reference Warren's Neovim configuration (~/.config/nvim) with LSP, plugins, and directory structure.
Design rigorous A/B tests with hypotheses, variants, metrics, and sample size calculations.
Guide human PO through manual acceptance testing. Optional - use when PO wants manual verification before merge.
Conduct a comprehensive accessibility audit against WCAG guidelines with severity ratings and remediation steps.
Create accessibility testing plans covering assistive technologies and WCAG criteria.
Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.
Run a cross-platform performance review for this brand. Use when the user asks for a performance review, weekly review, or wants to see how campaigns are doing across all platforms.
Find and fix wasted ad spend across all platforms. Use when the user wants to reduce wasted spend, find inefficiencies, or optimize budget.
Write brand-voice-compliant ad copy for a specific platform. Use when the user wants new headlines, descriptions, or ad creative.
Rules and patterns for writing agent definitions under claude/agents/. Use when creating or editing .md agent files.
This skill should be used when the user asks to "create an agent", "write an agent", "build an agent", or wants to add new agent capabilities to Claude Code.
Run test/build tools in AI-agent-friendly modes by setting AGENT=1, CLAUDECODE=1, and related environment flags when available.
Add Agentation visual feedback toolbar to a Next.js project
Generate -> annotate -> refine -> repeat using generate_image + Visual Annotator (Live Canvas).
Use when interacting with config via the agentio CLI.
Use when interacting with mcp via the agentio CLI.
Download AL symbol packages (.app files) for the current project's dependencies from Microsoft NuGet feeds. Reads app.json to determine required packages.
Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis.
Use to audit test quality with SRE scrutiny - identifies weak tests, missing cases, and creates task docs for improvements
Apply animation principles to UI motion for purposeful, polished interactions.
Fills Outcomes & Learnings in a plan file and renames it to .done.md.
Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
Track build processing, find latest builds, and clean up old builds with asc. Use when managing build retention or waiting on processing.
Resolve App Store Connect IDs (apps, builds, versions, groups, testers) from human-friendly names using asc. Use when commands require IDs.
Orchestrate TestFlight distribution, groups, testers, and What to Test notes using asc. Use when rolling out betas.
Fetch Ash Framework guidance for creating and managing Ash applications. Use when working with Ash Framework, creating new Ash projects, adding Ash extensions, or needing Ash-specific patterns.
Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
Stop dismissing pre-existing test/build failures. Use when reporting test results, build output, or any command output containing errors or failures.
# ASTM Standards Specialist
Astro 5.0 + Tailwind CSS landing page with blog, dark mode, and perfect PageSpeed scores.
Create brand-safe content for athletes. Personal branding strategy, engagement optimization, crisis communication, sponsor integration.
# /clickup:attach - Attach to Agent Session
Autonomous maintenance orchestrator that continuously finds and dispatches work
Gaming landing page with GSAP scroll animations, 3D effects, and video storytelling.
# AWS & Kubernetes Environment Setup for Judge
AWS development with infrastructure automation and cloud architecture patterns. Use when building or deploying services on Amazon Web Services.
Designer portfolio with Locomotive Scroll, GSAP, and Framer Motion animations.
Manage product backlog as an ordered priority list
Use BEFORE reading multiple files to understand code. Reminds you to use codebase-analyzer agent instead of manual file reading.
Use BEFORE running grep or glob commands. Reminds you to use codebase-locator agent instead of basic file search tools.
Use BEFORE using the Task tool. Ensures you select the correct specialized subagent_type instead of generic agents.
# Benchmark — Performance Baseline & Regression Detection
Use when the user wants to check usage, view invoices, or manage payment methods on Zilliz Cloud.
X/Twitter CLI for reading, searching, posting, and engagement via cookies.
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
March Madness, playoff brackets, tournament picks. Upset potential, chalk vs contrarian strategies, historical trends, confidence levels.
Scan documents and slides for off-brand colors, fonts, and logos. Validate against brand guidelines and suggest corrections.
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
# Browser QA — Automated Visual Testing & Interaction
Analyze spending patterns and find savings. 50/30/20 rule, subscription audit, debt payoff strategies, emergency fund roadmap.
Reuse cached file reads and diffs to avoid resending unchanged content. Use when repeated reads of the same files are inflating token cost.
# Canary Watch — Post-Deploy Monitoring
Analyze card sorting results to inform information architecture and navigation structure. Use after conducting open or closed card sort studies.
Craft portfolio-ready case studies that tell the story of a design project.
Compress and simplify prompts to preserve meaning while reducing use of context
Interactive review and promotion of high-confidence memories to CLAUDE.md
Create a memory from natural language or structured flags
Generate changelogs from git history. Use when you need release notes fast.
check network
Convert CLAUDE.md instructions into Codex-oriented AGENTS.md guidance. Use when the user wants Claude project rules made available to Codex.
This skill should be used when user asks to "clean gone branches", "remove deleted local branches", "prune branches removed from remote", or explicitly invokes "clean-gone-branches".
Write clean, efficient TypeScript code that follows common best practices
CLI guidelines. Use whenever using the Bash tool, which is almost always. Also use when you see "command not found: __zoxide_z" errors.
Zero friction. Full context. Competitive intelligence, M&A due diligence, and OSINT directly from your terminal. Uses Node.js/npx.
Control WaveTone 2.61 workflows through a JSON manifest and launch the real Windows WaveTone executable.
Design click/first-click tests to evaluate navigation and information findability.