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
54,017 results · page 180 of 1,801
- View details
meme-coin-auditSkillSecurity
Lets your agent check a crypto token for scams like honeypots, hidden minting, and risky liquidity pools before you buy.
Ready to connect★ 4k
- View details
mid-engagement-ir-detectionSkillSecurity
Lets your agent detect when a target's security state changes mid-penetration-test and turn those changes into reportable findings.
Ready to connect★ 4k
- View details
okta-attackSkillCommunication
Lets your agent simulate Okta identity provider attacks like user enumeration, password spraying, and phishing scenarios.
Ready to connect★ 4k
- View details
osint-methodologySkillAI & models
Gives your agent a step-by-step method for gathering public information about a target's systems and assets.
Ready to connect★ 4k
- View details
recon-scope-triageSkillAI & models
Lets your agent sort security recon results into your target's real assets versus unrelated same-named noise.
Ready to connect★ 4k
- View details
redteam-mindsetSkillAI & models
Guides your agent to think like an offensive security tester when starting an authorized red-team engagement.
Ready to connect★ 4k
- View details
redteam-report-templateSkillAI & models
Lets your agent write client-facing red-team findings in a standard Subject/Observations/Impact/Recommendation format.
Ready to connect★ 4k
- View details
report-writingSkillAI & models
Lets your agent draft and score bug bounty reports with templates, severity guidance, and a pre-submit checklist.
Ready to connect★ 4k
- View details
security-arsenalSkillSecurity
Gives your agent ready-made security test payloads, bypass techniques, and wordlists for finding web vulnerabilities.
Ready to connect★ 4k
- View details
supply-chain-attack-reconSkillSecurity
Lets your agent scan a software project's supply chain for weaknesses like dependency confusion and exposed CI/CD settings.
Ready to connect★ 4k
- View details
triage-validationSkillAI & models
Lets your agent validate and score security findings against a checklist before writing a bug report.
Ready to connect★ 4k
- View details
vmware-vcenter-attackSkillFiles & storage
Lets your agent run known attack checks against VMware vCenter and vSphere servers to find exploitable vulnerabilities.
Ready to connect★ 4k
- View details
web2-reconSkillWeb & browsing
Lets your agent discover and map a website's attack surface: subdomains, live hosts, URLs, and exposed JS secrets.
Ready to connect★ 4k
- View details
web3-auditSkillSecurity
Lets your agent audit smart contracts for 10 common DeFi bug classes using checklists, grep patterns, and PoC templates.
Ready to connect★ 4k
- View details
codex-with-chatgptSkillDev tools
Lets your agent use ChatGPT on the web to plan and review its Codex coding work while it keeps writing the code.
Ready to connect★ 5k
- View details
address-pr-commentsSkillDev tools
Lets your agent review GitHub pull request comments and implement the agreed code fixes.
Ready to connect★ 5k
- View details
binary-loopSkillDev tools
Lets your agent shrink the Fallow binary size by repeatedly measuring and analyzing builds while keeping features intact.
Ready to connect★ 5k
- View details
browser-smoke-reviewSkillWeb & browsing
Lets your agent open web pages in a browser and review them with screenshots, such as docs sites or preview deployments.
Ready to connect★ 5k
- View details
ci-formats-reviewSkillDocs & knowledge
Lets your agent check that CI report outputs like SARIF or markdown are correctly formatted.
Ready to connect★ 5k
- View details
cli-output-reviewSkillDev tools
Reviews your agent's CLI text output for readability, formatting, and terminal compatibility.
Ready to connect★ 5k
- View details
conformance-loopSkillDev tools
Lets your agent improve code analysis accuracy by checking results against trusted sources over a fixed test corpus.
Ready to connect★ 5k
- View details
coverage-loopSkillDev tools
Lets your agent iteratively find and fill untested parts of a Rust codebase using coverage reports.
Ready to connect★ 5k
- View details
debug-false-positiveSkillDev tools
Lets your agent diagnose and fix false positives or false negatives through extraction, analysis, and verification.
Ready to connect★ 5k
- View details
fallowSkillSecurity
Lets your agent analyze TypeScript and JavaScript codebases for risk, duplication, complexity, and cleanup opportunities.
Ready to connect★ 5k
- View details
fix-gh-actionsSkillDev tools
Lets your agent investigate and fix failing GitHub Actions checks for a repo or its pull requests.
Ready to connect★ 5k
- View details
github-action-reviewSkillDev tools
Lets your agent review GitHub Action configs, shell scripts, jq filters, and review comment formatting.
Ready to connect★ 5k
- View details
gitlab-ci-reviewSkillDev tools
Lets your agent review GitLab CI changes, scripts, jq filters, and MR comment formatting.
Ready to connect★ 5k
- View details
json-output-reviewSkillDev tools
Lets your agent review JSON output changes for schema stability, determinism, and downstream usability.
Ready to connect★ 5k
- View details
lsp-reviewSkillDev tools
Lets your agent review the LSP server's diagnostics, code actions, and code lens behavior.
Ready to connect★ 5k
- View details
mcp-reviewSkillAI & models
Reviews your MCP server code for clear tool contracts, stable outputs, and agent usability.
Ready to connect★ 5k
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.
53,585 of the 54,017 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.