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
9,019 results · page 73 of 301
- View details
agentic-evaluation-frameworkSkillAI & models
This skill should be used when the user asks to "evaluate LLM output quality", "set up LLM-as-judge", "build an eval rubric", "compare model outputs pairwise", or "measure agent quality".
Ready to connect★ 752
- View details
claude-code-masterySkillAI & models
368 AI skills, 76 expert agents, and 859 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, and research. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
Ready to connect★ 752
- View details
codex-cli-specialistSkillAI & models
OpenAI Codex CLI and cross-platform skill authoring. Use when setting up Codex CLI, converting or syncing skills between Claude Code and Codex, configuring agents/openai.yaml, or validating cross-platform skill compatibility.
Ready to connect★ 752
- View details
cto-advisorSkillAI & models
Gives your agent CTO-style guidance on tech debt, architecture decisions, team scaling, and technology strategy.
Ready to connect★ 752
- View details
culture-architectSkillAI & models
Guides your agent through building company values, translating them into behaviors, and assessing culture health.
Ready to connect★ 752
- View details
customer-success-managerSkillAI & models
Scores customer health, flags churn-risk accounts, and finds upsell opportunities from your customer data files.
Ready to connect★ 752
- View details
data-scientistSkillAI & models
Data science across machine learning, statistical modeling, and experimentation. Use when selecting ML algorithms, engineering features, designing A/B tests, evaluating model performance, or building predictive pipelines.
Ready to connect★ 752
- View details
deal-deskSkillAI & models
Scores inbound deals, routes discount approvals to named approvers, and flags risky contract terms before close.
Ready to connect★ 752
- View details
feature-flags-architectSkillAI & models
Lets your agent plan feature flag rollouts, audit code for stale flags, and verify kill switches.
Ready to connect★ 752
- View details
founder-coachSkillAI & models
Gives your agent a leadership coach for founders, covering delegation, energy management, and CEO growth.
Ready to connect★ 752
- View details
git-worktree-managerSkillAI & models
Lets your agent create and manage separate Git worktrees so multiple branches can run in parallel without conflicts.
Ready to connect★ 752
- View details
internal-commsSkillAI & models
Plan, sequence, and pressure-test internal announcements before they send. Use when announcing a reorg, policy, or product change, drafting an all-hands or exec update, or deciding who hears what and in which order.
Ready to connect★ 752
- View details
intl-expansionSkillAI & models
Lets your agent plan international expansion with market scoring, entry mode choices, localization checklists, and regional go-to-market guidance.
Ready to connect★ 752
- View details
llm-cost-optimizerSkillAI & models
Lets your agent analyze your AI API costs and suggest ways to cut spending, like routing tasks to cheaper models.
Ready to connect★ 752
- View details
ma-playbookSkillAI & models
Guides your agent through M&A deals with due diligence checklists, valuation methods, and integration plans.
Ready to connect★ 752
- View details
mcp-server-builderSkillAI & models
Lets your agent generate ready-to-run server code that turns an OpenAPI API spec into tools for AI assistants.
Ready to connect★ 752
- View details
monorepo-navigatorSkillAI & models
Guides your agent through setting up, optimizing, and migrating monorepos with Turborepo, Nx, pnpm workspaces, and Lerna.
Ready to connect★ 752
- View details
org-health-diagnosticSkillAI & models
Lets your agent score company health across 8 areas like finance, product, and people, with traffic-light ratings and recommendations.
Ready to connect★ 752
- View details
page-croSkillAI & models
Landing page and marketing page conversion rate optimization covering value proposition clarity, headline effectiveness, CTA hierarchy, visual flow, social proof placement, objection handling, and structured A/B testing.
Ready to connect★ 752
- View details
process-mapperSkillAI & models
Lets your agent map a business process step by step, measure cycle times, and pinpoint where work gets stuck.
Ready to connect★ 752
- View details
procurement-optimizerSkillAI & models
Lets your agent audit company spending, categorize it, and plan which suppliers to consolidate.
Ready to connect★ 752
- View details
prompt-engineer-toolkitSkillAI & models
Helps your agent test, score, and version marketing prompts so AI-generated copy is measurable and safe before use.
Ready to connect★ 752
- View details
release-managerSkillAI & models
Automates release management with changelog generation, semantic versioning, and release readiness checks. Use when preparing releases, generating changelogs, bumping versions, or validating release candidates.
Ready to connect★ 752
- View details
senior-cloud-architectSkillAI & models
368 AI skills, 76 expert agents, and 859 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, and research. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
Ready to connect★ 752
- View details
senior-data-scientistSkillAI & models
Lets your agent design A/B tests, build feature pipelines, and train and evaluate prediction models with Python, R, or SQL.
Ready to connect★ 752
- View details
senior-fullstackSkillAI & models
Lets your agent scaffold fullstack projects in Next.js, FastAPI, MERN, or Django and score your code for security and quality issues.
Ready to connect★ 752
- View details
senior-mobileSkillAI & models
368 AI skills, 76 expert agents, and 859 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, and research. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
Ready to connect★ 752
- View details
senior-prompt-engineerSkillAI & models
Lets your agent optimize prompts, evaluate LLM outputs with eval sets, and measure RAG retrieval quality.
Ready to connect★ 752
- View details
skill-testerSkillAI & models
Lets your agent validate, test, and score the quality of skills it writes, including running their Python scripts safely.
Ready to connect★ 752
- View details
spec-driven-workflowSkillAI & models
Guides your agent to write a full specification with acceptance criteria before writing any code.
Ready to connect★ 752
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.
54,764 of the 55,196 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.