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 120 of 1,797
- View details
burpsuite-project-parserSkillFiles & storage
Lets your agent search and explore Burp Suite project files, extracting security findings and HTTP traffic data.
Ready to connect★ 7k
- View details
c-reviewSkillDocs & knowledge
Lets your agent audit C/C++ code for memory bugs, integer overflows, and race conditions.
Ready to connect★ 7k
- View details
cairo-vulnerability-scannerSkillCommunication
Scans Cairo and StarkNet smart contracts for six critical vulnerability types before they cause problems.
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 connection problems with the Claude in Chrome browser extension.
Ready to connect★ 7k
- View details
code-improverSkillAI & models
Lets your agent run an automated review-and-fix loop over code, repeating fixes until issues stop improving.
Ready to connect★ 7k
- View details
code-maturity-assessorSkillDocs & knowledge
Lets your agent grade a codebase's quality across nine areas like testing, security, and documentation, then produce a scorecard.
Ready to connect★ 7k
- View details
constant-time-analysisSkillSecurity
Lets your agent find timing side-channel vulnerabilities in cryptographic code across many languages.
Ready to connect★ 7k
- View details
constant-time-testingSkillMonitoring & ops
Lets your agent test cryptographic code for timing leaks using statistical and dynamic analysis tools.
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 or code into Mermaid sequence diagrams of message flows.
Ready to connect★ 7k
- View details
diagramming-codeSkillDev tools
Lets your agent turn code into Mermaid diagrams like call graphs, class hierarchies, and dependency maps.
Ready to connect★ 7k
- View details
differential-reviewSkillDocs & knowledge
Lets your agent review code changes for security risks and produce a markdown report.
Ready to connect★ 7k
- View details
dimensional-analysisSkillSecurity
Lets your agent add comments to code documenting units, dimensions, and decimal scaling to catch arithmetic bugs.
Ready to connect★ 7k
- View details
dwarf-expertSkillDev tools
Gives your agent expert knowledge to analyze DWARF debug files and answer questions about the DWARF format.
Ready to connect★ 7k
- View details
entry-point-analyzerSkillSecurity
Lets your agent scan smart contract code and list the functions that can change state, sorted by who can call them.
Ready to connect★ 7k
- View details
firebase-apk-scannerSkillDatabases & data
Scans Android APK files for Firebase security issues like open databases and exposed cloud functions.
Ready to connect★ 7k
- View details
fp-checkSkillSecurity
Checks whether a suspected security bug is real or a false positive and gives a verdict with evidence.
Ready to connect★ 7k
- View details
fuzzing-dictionarySkillFiles & storage
Builds and applies fuzzing dictionaries so a fuzzer can produce the keywords, magic bytes, and tokens a target expects. Covers extracting tokens from source, headers, binaries, and specifications, dictionary syntax, and wiring one into libFuzzer or AFL++. Use when fuzzing a parser, protocol, or file
Ready to connect★ 7k
- View details
fuzzing-obstaclesSkillDev tools
Patches past the barriers that stop a fuzzer making progress — checksum and hash verification, magic-value validation, time-based seeds, and other non-deterministic global state. Covers locating the blocking check, neutering it behind a fuzzing build flag, and avoiding the false positives a patch ca
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
Steers your agent to use authenticated GitHub CLI commands instead of unauthenticated web requests when working with GitHub.
Ready to connect★ 7k
- View details
goal-promptSkillProductivity
Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex.
Ready to connect★ 7k
- View details
graph-evolutionSkillSecurity
Lets your agent compare code graphs between two commits to spot security-relevant changes like new attack paths.
Ready to connect★ 7k
- View details
guidelines-advisorSkillDocs & knowledge
Lets your agent review smart contract code against Trail of Bits best practices and flag pitfalls.
Ready to connect★ 7k
- View details
harness-writingSkillDev tools
Guides your agent in writing and improving 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, 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 interpret it to suggest next steps when you don't care what it does.
Ready to connect★ 7k
- View details
mermaid-to-proverifSkillSearch
Lets your agent turn 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
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.