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.
Filter by category
70,704 results · page 659 of 2,357
- View details
childcare-comparisonSkillAI & models
Lets your agent compare childcare options like nursery, childminder, or nanny based on your family's needs and budget.
Ready to connect★ 1k
- View details
decision-helperSkillAI & models
Lets your agent weigh and score options to help make architecture decisions.
Ready to connect★ 1k
- View details
demand-letterSkillCommerce & finance
Draft a firm, professional demand letter that states the facts, the legal/contractual basis, the specific demand, and a deadline. Use when asked to write a demand letter, send a formal demand for payment, draft a cease-and-desist, or formally request resolution before legal action. Produces a struct
Ready to connect★ 1k
- View details
demo-scriptSkillMedia
Script a product demo that lands — the audience's-workflow storyline (their day, not your feature list), the golden path rehearsed with fallbacks, the wow moment placed early, and the demo-death contingencies (the backup video, the reset state, the narration bridge). Use when asked script our produc
Ready to connect★ 1k
- View details
dpa-reviewSkillAI & models
Read a Data Processing Agreement before you sign it — sub-processors, transfer mechanism, breach-notice window, deletion, audit rights — in plain language with 🔴🟡🟢 risk. Use when asked to review a DPA, check a data processing agreement, is this DPA safe to sign, or what am I agreeing to on data. Pro
Ready to connect★ 1k
- View details
emergency-fundSkillAI & models
Lets your agent calculate an emergency fund target and track savings progress toward it.
Ready to connect★ 1k
- View details
employee-engagement-surveySkillMedia
Helps your agent design employee engagement surveys, analyze feedback, and build action plans.
Ready to connect★ 1k
- View details
experiment-readoutSkillAI & models
Lets your agent analyze A/B experiments and turn results into clear recommendations.
Ready to connect★ 1k
- View details
go-to-market-plannerSkillCommunication
Build a go-to-market plan for any product launch, feature release, or new market entry. Use when planning a product launch, writing a GTM strategy, defining launch tiers, or coordinating cross-functional launch activities. Produces a tiered GTM plan with messaging, cross-functional activity tracker,
Ready to connect★ 1k
- View details
hook-writerSkillCommunication
Writes attention-grabbing opening lines for social posts, videos, threads, and email subjects.
Ready to connect★ 1k
- View details
house-style-enforcerSkillDocs & knowledge
Apply a team's writing style consistently — extract the house style from exemplar documents into a checkable rule card, run the conformance pass on new drafts, and fix violations without flattening the author's voice. Use when asked make this match our style, why do our docs all sound different, bui
Ready to connect★ 1k
- View details
ip-lookupSkillCloud & infra
Look up IP addresses and your own public IP with zero API keys — geolocation, ISP/ASN, and hosting flags via ip-api.com and ipify through curl. Use when asked what's my public IP, where is this IP from, whose network is this address, or is this IP a VPN/datacenter. Produces the lookup with ISP, ASN,
Ready to connect★ 1k
- View details
job-description-writerSkillAI & models
Lets your agent draft inclusive job descriptions with clear requirements and salary transparency.
Ready to connect★ 1k
- View details
one-on-one-prepSkillAI & models
Lets your agent build a focused one-on-one agenda with your top topics and the outcome you want for each.
Ready to connect★ 1k
- View details
one-pagerSkillAI & models
Distil anything — a startup, product, project, or idea — into a single persuasive page. Use when asked to make a one-pager, a one-page summary, a leave-behind, a startup/product one-sheet, or a tl;dr brief. Produces a structured single page — headline + tagline, the problem, the solution, why-now/pr
Ready to connect★ 1k
- View details
performance-budgetSkillDocs & knowledge
Guides your agent through setting and checking page weight limits like bundle size and load speed during code review.
Ready to connect★ 1k
- View details
project-status-reportSkillAI & models
Lets your agent generate project status reports with RAG status, milestones, risks, blockers and executive summaries.
Ready to connect★ 1k
- View details
rfp-responseSkillAI & models
Lets your agent draft RFP and RFI responses by analyzing requirements and structuring compliant proposals.
Ready to connect★ 1k
- View details
runbook-writerSkillDocs & knowledge
Lets your agent write operations runbooks covering deployment, rollback, monitoring, and incident handling.
Ready to connect★ 1k
- View details
runway-calculatorSkillAI & models
Lets your agent calculate how many months of cash runway remain at the current burn rate.
Ready to connect★ 1k
- View details
subscription-auditSkillCommerce & finance
Lets your agent find recurring subscriptions, total their cost, and flag unused ones.
Ready to connect★ 1k
- View details
teaching-lesson-planSkillMedia
Lets your agent design a full lesson plan with objectives, timed activities, assessments, and differentiation.
Ready to connect★ 1k
- View details
test-case-writerSkillAI & models
Turn a requirement or user story into clear, executable test cases. Use when asked to write test cases, test scenarios, a test suite for a feature, or to derive tests from acceptance criteria. Produces structured test cases — preconditions, steps, test data, expected results — across happy path, edg
Ready to connect★ 1k
- View details
vendor-evaluationSkillAI & models
Lets your agent evaluate third-party vendors for engineering fit using a structured assessment.
Ready to connect★ 1k
- View details
vuln-triageSkillSecurity
Lets your agent assess a security vulnerability's real severity and urgency so you know what to patch first.
Ready to connect★ 1k
- View details
shinka-convertSkillFiles & storage
Lets your agent turn an existing codebase into a ShinkaEvolve optimization task with config and evaluation files.
Ready to connect★ 1k
- View details
shinka-inspectSkillDocs & knowledge
Lets your agent load top-performing Shinka programs and get a compact Markdown summary for planning improvements.
Ready to connect★ 1k
- View details
shinka-runSkillProductivity
Lets your agent launch an existing ShinkaEvolve evolution run from a task directory using the shinka_run CLI.
Ready to connect★ 1k
- View details
shinka-setupSkillProductivity
Lets your agent set up ShinkaEvolve task folders with evaluation and baseline starter files from a description.
Ready to connect★ 1k
- View details
crosslink-guideSkillDev tools
Lets your agent follow a repo's crosslink workflow for issues, sessions, locks, and knowledge pages using the CLI.
Ready to connect★ 1k
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
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.
68,574 of the 70,704 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 workspace 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.