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
54,221 results · page 135 of 1,808
- View details
harness-writingSkillDev tools
Helps your agent write and improve fuzzing harnesses for C/C++ and Rust code.
Ready to connect★ 7k
- View details
interpreting-culture-indexSkillDev tools
Lets your agent interpret Culture Index personality surveys and analyze team fit, burnout risk, and hiring profiles.
Ready to connect★ 7k
- View details
let-fate-decideSkillAI & models
Lets your agent draw a tarot spread and use it to suggest next steps when you give vague or undecided prompts.
Ready to connect★ 7k
- View details
mermaid-to-proverifSkillSearch
Lets your agent convert Mermaid sequence diagrams of cryptographic protocols into ProVerif verification models.
Ready to connect★ 7k
- View details
modern-cppSkillSecurity
Guides your agent to write C++ using modern idioms like smart pointers, concepts, and std::print.
Ready to connect★ 7k
- View details
mutation-testingSkillDev tools
Lets your agent set up and run mutation testing campaigns and analyze surviving mutants to find test gaps.
Ready to connect★ 7k
- View details
open-sourcingSkillDev tools
Prepares your agent to get a repository ready for public open-source release, including license choices and release checks.
Ready to connect★ 7k
- View details
ossfuzzSkillCloud & infra
Lets your agent set up a project on Google's free OSS-Fuzz service and reproduce fuzzing crash reports.
Ready to connect★ 7k
- View details
panel-reviewSkillAI & models
Lets your agent review code by running several specialist auditor agents and merging their findings into one report.
Ready to connect★ 7k
- View details
pr-improverSkillDev tools
Lets your agent automatically review and fix code changes on a branch until PR review findings are resolved.
Ready to connect★ 7k
- View details
property-based-testingSkillDev tools
Lets your agent write and debug property-based tests that check whole input ranges instead of a few examples.
Ready to connect★ 7k
- View details
rust-reviewSkillDocs & knowledge
Lets your agent review Rust code for unsafe memory, concurrency, FFI, and panic-related security issues.
Ready to connect★ 7k
- View details
ruzzySkillDocs & knowledge
Guides your agent to fuzz Ruby code and gems, including C extensions, to find crashes and bugs.
Ready to connect★ 7k
- View details
sarif-parsingSkillFiles & storage
Lets your agent parse and organize security scan results from static analysis tools.
Ready to connect★ 7k
- View details
second-opinionSkillAI & models
Lets your agent get a second-opinion code review of your changes from external AI tools like Codex.
Ready to connect★ 7k
- View details
secure-workflow-guideSkillDocs & knowledge
Lets your agent run code security scans and follow a five-step secure development workflow with reports and diagrams.
Ready to connect★ 7k
- View details
semgrepSkillSecurity
Lets your agent run Semgrep security scans on a codebase and export results to SARIF.
Ready to connect★ 7k
- View details
semgrep-rule-creatorSkillSecurity
Lets your agent write custom Semgrep rules to detect security bugs and code patterns in codebases.
Ready to connect★ 7k
- View details
semgrep-rule-variant-creatorSkillDev tools
Lets your agent convert an existing Semgrep rule into versions for other programming languages, with tests.
Ready to connect★ 7k
- View details
skill-improverSkillAI & models
Lets your agent automatically review and fix a Claude Code skill until it passes quality checks.
Ready to connect★ 7k
- View details
slicing-code-contextSkillProductivity
Lets your agent extract focused slices of code and hand small analysis or patch tasks to a smaller model.
Ready to connect★ 7k
- View details
solana-vulnerability-scannerSkillSecurity
Lets your agent scan Solana programs for critical security vulnerabilities like missing signer checks and CPI issues.
Ready to connect★ 7k
- View details
substrate-vulnerability-scannerSkillSecurity
Lets your agent scan Substrate blockchain code for common vulnerabilities like overflow bugs and weak permission checks.
Ready to connect★ 7k
- View details
supply-chain-risk-auditorSkillDev tools
Lets your agent audit a project's dependencies for advisories, abandoned packages, and risky install scripts.
Ready to connect★ 7k
- View details
testing-handbook-generatorSkillFiles & storage
Lets your agent turn Testing Handbook pages into ready-to-use Claude Code skill files.
Ready to connect★ 7k
- View details
token-integration-analyzerSkillDev tools
Lets your agent analyze crypto token contracts for standards compliance, unusual patterns, and owner privileges.
Ready to connect★ 7k
- View details
ton-vulnerability-scannerSkillSecurity
Lets your agent scan TON smart contracts for three common critical vulnerabilities.
Ready to connect★ 7k
- View details
trailmarkSkillSecurity
Lets your agent build and query code graphs to find security issues like taint flows and privilege boundaries.
Ready to connect★ 7k
- View details
trailmark-finding-triageSkillSecurity
Lets your agent triage a security finding using reachability, taint, and blast-radius evidence.
Ready to connect★ 7k
- View details
trailmark-review-gateSkillDev tools
Lets your agent review code changes for security issues like new entrypoints, removed validation, and privilege drift.
Ready to connect★ 7k
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.
53,789 of the 54,221 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.