Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
9,105 results · page 173 of 304
- View details
sales-and-revenue-operationsSkillAI & models
Comprehensive sales and revenue operations skill. Use when building a sales team, doing founder-led sales, hiring first sales reps, navigating enterprise deals, implementing product-led sales, designing sales compensation plans, defining ICP, mapping buyer personas, or optimizing the revenue engine
Ready to connect★ 100
- View details
x-impact-checkerSkillAI & models
Analyze and optimize X (Twitter) posts for viral potential and reach using heuristics inspired by X's published open-source recommendation architecture. Use when user wants to: (1) Check if a post will go viral, (2) Score a tweet for engagement potential, (3) Optimize or rewrite a tweet for algorith
Ready to connect★ 100
- View details
build-mcpSkillAI & models
Build an MCP server end to end, tailored to how it will be used. Use when asked to build an MCP, create an MCP server, wrap an API as a tool, make a tool for Claude, expose a service to an agent, build a Claude connector, or turn a service into MCP tools. Asks up front who the server is for (just me
Ready to connect★ 99
- View details
build-pluginSkillAI & models
Bundle skills, hooks, agents, or an MCP server into one installable Claude Code plugin and ship it. Use when asked to bundle tools into one plugin, package tools for a colleague, publish a plugin to a marketplace, share my tools with my team, or ship a plugin. Asks who it's for and where it's hosted
Ready to connect★ 99
- View details
issue-to-prSkillAI & models
Take one or more GitHub issues and drive each to a review-ready pull request, holding one belief throughout: an issue is a hypothesis, not a spec. The pipeline VERIFIES BEFORE IT TRUSTS and runs TWO ADVERSARIES before it commits: multi-agent investigation of the real cause (flagging any "landmine" —
Ready to connect★ 99
- View details
opentraces-skill-verifierSkillAI & models
Author a trace-grounded, CALIBRATED verifier for one skill, two ways: an interactive ALIGNMENT SESSION (manual) or AUTOVERIFY (the agent self-aligns to the skill's goal). Use this skill when asked to build, align, calibrate, or autoverify a verifier/rubric for a skill. The agent proposes a rubric; t
Ready to connect★ 99
- View details
release-schemaSkillAI & models
Release a new version of the opentraces-schema package to PyPI. Use when the user says "release schema", "bump schema", "schema release", "publish schema", "release-schema", or when schema models have changed and need publishing independently of the CLI. This handles the schema package only, not the
Ready to connect★ 99
- View details
relentlessSkillAI & models
Convert PRDs to prd.json format for the Relentless autonomous agent system. Use when you have an existing PRD and need to convert it to Relentless JSON format. Triggers on: convert this prd, turn this into relentless format, create prd.json from this, relentless json.
Ready to connect★ 99
- View details
token-doctorSkillAI & models
Personal diagnosis of where your Claude Code + Cowork spend goes. Reads local transcripts, prints your conversation length distribution, marathon share, cache rebuild costs, and per-project diagnosis (good projects and problem projects) right in the terminal. Then offers a deeper dive that fans out
Ready to connect★ 99
- View details
waitSkillAI & models
Check rate-limit state and manage auto-resume behavior for blocked Gemini work.
Ready to connect★ 99
- View details
address-github-commentsSkillAI & models
Lets your agent respond to and resolve reviewer and issue comments on a GitHub pull request using the gh CLI.
Ready to connect★ 98
- View details
ai-engineerSkillAI & models
Build production-ready LLM applications, advanced RAG systems, and
Ready to connect★ 98
- View details
angularSkillAI & models
Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns. Use PROACTIVELY for Angular development, component architecture, state management, performance optimization, and migration to modern patterns.
Ready to connect★ 98
- View details
angular-ui-patternsSkillAI & models
Gives your agent guidance on modern Angular UI patterns for loading states, error handling, and data display.
Ready to connect★ 98
- View details
anti-reversing-techniquesSkillAI & models
Understand anti-reversing, obfuscation, and protection techniques encountered during software analysis. Use when analyzing protected binaries, bypassing anti-debugging for authorized analysis, or understanding software protection mechanisms.
Ready to connect★ 98
- View details
architect-reviewSkillAI & models
Master software architect specializing in modern architecture
Ready to connect★ 98
- View details
avalonia-layout-zafiroSkillAI & models
Guides your agent to build Avalonia UI layouts with Zafiro.Avalonia using shared styles and reusable components.
Ready to connect★ 98
- View details
avalonia-zafiro-developmentSkillAI & models
Lets your agent follow Avalonia UI and Zafiro toolkit conventions when writing desktop app code.
Ready to connect★ 98
- View details
bash-linuxSkillAI & models
Gives your agent reference patterns for using the Linux or macOS terminal, including commands, piping, and scripting.
Ready to connect★ 98
- View details
bats-testing-patternsSkillAI & models
Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.
Ready to connect★ 98
- View details
bazel-build-optimizationSkillAI & models
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
Ready to connect★ 98
- View details
binary-analysis-patternsSkillAI & models
Master binary analysis patterns including disassembly, decompilation, control flow analysis, and code pattern recognition. Use when analyzing executables, understanding compiled code, or performing static analysis on binaries.
Ready to connect★ 98
- View details
blockchain-developerSkillAI & models
Build production-ready Web3 applications, smart contracts, and
Ready to connect★ 98
- View details
build-sdf-liquid-glassSkillAI & models
Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.
Ready to connect★ 98
- View details
busybox-on-windowsSkillAI & models
Lets your agent use standard Unix command line tools on Windows via a Win32 BusyBox build.
Ready to connect★ 98
- View details
cc-skill-continuous-learningSkillAI & models
Lets your agent learn from past coding tasks and apply those lessons to future work.
Ready to connect★ 98
- View details
cc-skill-strategic-compactSkillAI & models
Lets your agent condense long coding sessions on purpose while keeping important context.
Ready to connect★ 98
- View details
clarity-gateSkillAI & models
Lets your agent check and qualify documents before adding them to a knowledge base.
Ready to connect★ 98
- View details
Claude Code GuideSkillAI & models
Lets your agent answer questions about how to set up and use Claude Code with best practices and configuration examples.
Ready to connect★ 98
- View details
clean-codeSkillAI & models
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
Ready to connect★ 98
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
55,111 of the 55,543 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.