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
53,895 results · page 121 of 1,797
- View details
mutation-testingSkillDev tools
Lets your agent set up and tune mutation testing runs, including scoping targets and optimizing long-running campaigns.
Ready to connect★ 7k
- View details
open-sourcingSkillDev tools
Helps your agent prepare a code repository for public release, including license choice and release checks.
Ready to connect★ 7k
- View details
ossfuzzSkillCloud & infra
Lets your agent set up and run Google's free continuous fuzzing service for an open source project, including reproducing crash reports.
Ready to connect★ 7k
- View details
panel-reviewSkillAI & models
Lets your agent review code by running a panel of specialist auditor agents and merging their findings.
Ready to connect★ 7k
- View details
pr-improverSkillDev tools
Lets your agent automatically review and fix code changes on a branch until a PR review passes.
Ready to connect★ 7k
- View details
property-based-testingSkillDev tools
Lets your agent write and debug property-based tests that cover 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 block, concurrency, panic, and FFI security issues.
Ready to connect★ 7k
- View details
ruzzySkillDocs & knowledge
Sets up and runs Ruzzy, Trail of Bits' coverage-guided Ruby fuzzer and the only production-ready one for the language. Covers harness structure, fuzzing pure Ruby and the native C extensions in gems, and sanitizer builds. Use when fuzzing a Ruby library or gem, testing a Ruby C extension for memory
Ready to connect★ 7k
- View details
sarif-parsingSkillFiles & storage
Lets your agent read and summarize security scan results from tools like CodeQL or Semgrep.
Ready to connect★ 7k
- View details
second-opinionSkillAI & models
Lets your agent get a second AI opinion by sending code changes to an external reviewer like Codex or Gemini.
Ready to connect★ 7k
- View details
secure-workflow-guideSkillDocs & knowledge
Walks your agent through a 5-step smart contract security workflow with Slither scans and security diagrams.
Ready to connect★ 7k
- View details
semgrepSkillSecurity
Lets your agent run Semgrep security scans on a codebase and get findings merged into SARIF output.
Ready to connect★ 7k
- View details
semgrep-rule-creatorSkillSecurity
Lets your agent write custom Semgrep rules to detect security vulnerabilities and bug patterns in code.
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.
Ready to connect★ 7k
- View details
skill-improverSkillAI & models
Lets your agent automatically review and fix one of its skills until the review passes.
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 lighter subagent.
Ready to connect★ 7k
- View details
solana-vulnerability-scannerSkillSecurity
Scans Solana programs for six critical vulnerabilities like missing signer checks and improper PDA validation.
Ready to connect★ 7k
- View details
substrate-vulnerability-scannerSkillSecurity
Lets your agent scan Substrate and Polkadot pallets for critical vulnerabilities like overflow and bad origin checks.
Ready to connect★ 7k
- View details
supply-chain-risk-auditorSkillDev tools
Lets your agent audit project dependencies for supply-chain risks like abandoned packages and risky install scripts.
Ready to connect★ 7k
- View details
testing-handbook-generatorSkillFiles & storage
Lets your agent create skill files from the Trail of Bits Testing Handbook content.
Ready to connect★ 7k
- View details
token-integration-analyzerSkillDev tools
Lets your agent check a token contract for ERC20/ERC721 conformity, odd token patterns, owner privileges, and scarcity.
Ready to connect★ 7k
- View details
ton-vulnerability-scannerSkillSecurity
Scans TON smart contracts for critical vulnerabilities like fake Jetton contracts and missing gas checks.
Ready to connect★ 7k
- View details
trailmarkSkillSecurity
Lets your agent map how code and binaries connect to find security weak spots and trace how bugs spread.
Ready to connect★ 7k
- View details
trailmark-finding-triageSkillSecurity
Lets your agent triage a single security finding using reachability, taint, and blast-radius evidence.
Ready to connect★ 7k
- View details
trailmark-review-gateSkillDev tools
Lets your agent scan code changes for new security risks like removed validation, privilege drift, or newly exposed entrypoints.
Ready to connect★ 7k
- View details
trailmark-structuralSkillDev tools
Lets your agent run Trailmark code analysis to report hotspots, taint flows, blast radius, and attack surface.
Ready to connect★ 7k
- View details
trailmark-summarySkillDev tools
Lets your agent scan a codebase and report its languages, entry points, and dependencies.
Ready to connect★ 7k
- View details
trailmark-variant-neighborhoodSkillSecurity
Lets your agent expand one confirmed vulnerability into a graph of related variant candidates for analysis.
Ready to connect★ 7k
- View details
variant-analysisSkillFiles & storage
Lets your agent hunt for other places in a codebase where a bug you already found might also occur.
Ready to connect★ 7k
- View details
vector-forgeSkillCommerce & finance
Lets your agent generate new test vectors for cryptographic code by finding uncovered paths via mutation testing.
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.
53,462 of the 53,895 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.