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 134 of 1,808
- View details
aflppSkillDev tools
Lets your agent run AFL++ multi-core fuzzing on C/C++ projects, including parallel campaigns and crash triage.
Ready to connect★ 7k
- View details
algorand-vulnerability-scannerSkillSecurity
Lets your agent scan Algorand smart contracts for 11 common security vulnerabilities.
Ready to connect★ 7k
- View details
atherisSkillDocs & knowledge
Lets your agent set up and run the Atheris fuzzer to find bugs in Python code and its C extensions.
Ready to connect★ 7k
- View details
audit-augmentationSkillFiles & storage
Lets your agent merge code audit findings into code graphs, matching issues to files and lines.
Ready to connect★ 7k
- View details
audit-prep-assistantSkillDocs & knowledge
Prepares your codebase for a security review by setting goals, running static analysis, and adding docs.
Ready to connect★ 7k
- View details
burpsuite-project-parserSkillFiles & storage
Lets your agent search and extract data from Burp Suite project files, like proxy history, HTTP traffic, and audit findings.
Ready to connect★ 7k
- View details
c-reviewSkillDocs & knowledge
Lets your agent review C/C++ code for memory corruption, integer overflows, race conditions, and other security bugs.
Ready to connect★ 7k
- View details
cairo-vulnerability-scannerSkillCommunication
Scans your Cairo and StarkNet smart contracts for critical vulnerabilities like arithmetic overflow and signature replay.
Ready to connect★ 7k
- View details
cargo-fuzzSkillDev tools
Lets your agent set up and run fuzzing tests on Rust projects to find crashes automatically.
Ready to connect★ 7k
- View details
chrome-mcp-troubleshootingSkillWeb & browsing
Lets your agent diagnose and fix Chrome extension connection problems when browser tools stop working.
Ready to connect★ 7k
- View details
code-improverSkillAI & models
Lets your agent automatically review and fix code issues in a project using a reviewer you choose.
Ready to connect★ 7k
- View details
code-maturity-assessorSkillDocs & knowledge
Lets your agent score a codebase's maturity across nine areas like testing, access controls, and documentation.
Ready to connect★ 7k
- View details
constant-time-analysisSkillSecurity
Lets your agent check cryptographic code for timing side-channel vulnerabilities where secrets leak through execution time.
Ready to connect★ 7k
- View details
constant-time-testingSkillMonitoring & ops
Lets your agent test cryptographic code for timing side channels using statistical and dynamic analysis.
Ready to connect★ 7k
- View details
cosmos-vulnerability-scannerSkillSecurity
Lets your agent scan Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities.
Ready to connect★ 7k
- View details
crypto-protocol-diagramSkillCommunication
Lets your agent turn crypto protocol descriptions into Mermaid sequence diagrams showing message and key exchange flow.
Ready to connect★ 7k
- View details
diagramming-codeSkillDev tools
Lets your agent generate Mermaid diagrams of code architecture, like call graphs and class hierarchies.
Ready to connect★ 7k
- View details
differential-reviewSkillDocs & knowledge
Lets your agent review code changes for security issues and produce a markdown report.
Ready to connect★ 7k
- View details
dimensional-analysisSkillSecurity
Lets your agent add comments to code documenting units and dimensions to catch unit-mismatch bugs.
Ready to connect★ 7k
- View details
dwarf-expertSkillDev tools
Lets your agent analyze DWARF debug information in compiled binaries and answer questions about debug info.
Ready to connect★ 7k
- View details
entry-point-analyzerSkillSecurity
Lets your agent scan a smart contract codebase and list its state-changing functions grouped by access level.
Ready to connect★ 7k
- View details
firebase-apk-scannerSkillDatabases & data
Lets your agent scan Android APK files for Firebase security issues like open databases and exposed functions.
Ready to connect★ 7k
- View details
fp-checkSkillSecurity
Lets your agent verify whether a suspected security bug is real or a false positive, with evidence for the verdict.
Ready to connect★ 7k
- View details
fuzzing-dictionarySkillFiles & storage
Lets your agent build and apply fuzzing dictionaries of tokens, magic bytes, and keywords for fuzzing parsers or protocols.
Ready to connect★ 7k
- View details
fuzzing-obstaclesSkillDev tools
Lets your agent patch code barriers like checksums and magic values so a fuzzer can make progress.
Ready to connect★ 7k
- View details
genotoxicSkillDev tools
Lets your agent triage mutation testing results by finding false positives, coverage gaps, and fuzzing targets.
Ready to connect★ 7k
- View details
gh-cliSkillSecurity
Lets your agent use the authenticated GitHub command-line tool instead of unauthenticated web requests.
Ready to connect★ 7k
- View details
goal-promptSkillProductivity
Helps your agent draft copy-paste-ready /goal commands for setting up long-running tasks in coding assistants.
Ready to connect★ 7k
- View details
graph-evolutionSkillSecurity
Compares two snapshots of your codebase to reveal security-relevant structural changes that text diffs miss.
Ready to connect★ 7k
- View details
guidelines-advisorSkillDocs & knowledge
Gives your agent smart contract development advice and code reviews based on Trail of Bits best practices.
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.