ahel is live on Product Hunt today. Upvote

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

53,863 results · page 163 of 1,796

  • sql-insightSkillDatabases & data

    Lets your agent turn plain questions into SQL, speed up slow queries, and explain query plans for SQLite and PostgreSQL.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • sqlmap-database-pentestingSkillDatabases & data

    Lets your agent detect and test SQL injection vulnerabilities in databases using SQLMap.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • test-driven-devSkillAI & models

    Guides your agent to build features by writing failing tests first, then making them pass.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • test-suite-architectSkillMonitoring & ops

    Lets your agent build QA test strategies, write test cases, run test plans, and track bugs by priority.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • timeline-builderSkillAI & models

    Lets your agent turn JSON data into an interactive timeline web page with layouts, collapsible details, and custom colors.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • top-web-vulnerabilitiesSkillSecurity

    Gives your agent a structured reference of the 100 most critical web vulnerabilities with impact and fix guidance.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • tos-clause-scannerSkillAI & models

    Lets your agent review terms of service and privacy policies and flag unfair clauses and privacy risks.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • vc-industry-researchSkillDocs & knowledge

    Lets your agent create professional industry research reports and investment memos as PDFs.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • windows-privilege-escalationSkillAI & models

    Guides your agent through finding and exploiting Windows privilege escalation flaws during penetration tests.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • wireshark-analysisSkillFiles & storage

    Lets your agent capture and inspect network packets to investigate security issues, slow performance, and connection problems.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • wordpress-penetration-testingSkillSecurity

    Lets your agent check a WordPress site for common security vulnerabilities.

    Ready to connect★ 5k

    github.com/zebbern/claude-code-guide5k stars

    View details
  • hami_vgpu_metrics_summarizerSkillDocs & knowledge

    Lets your agent summarize HAMi vGPU metrics into reports on GPU allocation, memory, and sharing across nodes and pods.

    Ready to connect★ 5k

    github.com/project-hami/hami4k stars

    View details
  • k8s-debug-pending-podSkillMedia

    Lets your agent diagnose why Kubernetes pods are stuck in Pending, CrashLoopBackOff, or ImagePullBackOff states.

    Ready to connect★ 5k

    github.com/project-hami/hami4k stars

    View details
  • address-pr-commentsSkillDev tools

    Lets your agent read GitHub pull request review comments and implement the requested fixes.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • binary-loopSkillDev tools

    Lets your agent shrink a Rust binary's size by repeatedly measuring and analyzing builds with cargo-bloat.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • browser-smoke-reviewSkillWeb & browsing

    Lets your agent open web pages in a browser and review them with screenshots.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • ci-formats-reviewSkillDocs & knowledge

    Lets your agent check that CI report outputs like SARIF and CodeClimate files are correctly formatted.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • cli-output-reviewSkillDev tools

    Lets your agent review CLI text output for readability, formatting, and terminal compatibility.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • conformance-loopSkillDev tools

    Lets your agent iteratively improve Fallow analysis accuracy by comparing results against competing tools and verified sources.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • coverage-loopSkillDev tools

    Lets your agent find untested parts of a Rust codebase and add tests to improve coverage.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • debug-false-positiveSkillDev tools

    Lets your agent diagnose and fix false positives or false negatives reported by the Fallow checker.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • fallowSkillSecurity

    Lets your agent analyze a TypeScript or JavaScript codebase for risk, duplication, complexity, and cleanup opportunities.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • fix-gh-actionsSkillDev tools

    Lets your agent investigate and fix failing GitHub Actions checks in your repo or pull requests.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • github-action-reviewSkillDev tools

    Lets your agent review GitHub Action workflows, shell scripts, and jq filters for correctness.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • gitlab-ci-reviewSkillDev tools

    Lets your agent review GitLab CI changes, scripts, jq filters, and MR comment formatting.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • json-output-reviewSkillDev tools

    Reviews changes to JSON output for schema stability, determinism, and downstream usability.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • lsp-reviewSkillDev tools

    Lets your agent review the LSP server's diagnostics, code actions, and editor-facing behavior in fallow.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • mcp-reviewSkillAI & models

    Reviews MCP server code for clear tool contracts, stable outputs, and agent usability.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • open-draft-prSkillDev tools

    Lets your agent commit local changes, push them, and open a pull request ready for review.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details
  • panel-review-loopSkillDev tools

    Lets your agent iteratively review and improve a user-facing surface across real-world projects until a review panel has no blocking concerns.

    Ready to connect★ 5k

    github.com/fallow-rs/fallow4k stars

    View details

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.

53,430 of the 53,863 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.

See how to connect your AI