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 262 of 1,801

  • deskcomm-cliente-novoSkillDocs & knowledge

    Walks your agent through setting up a new DeskcommCRM client by niche, in the right order via the UI.

    Ready to connect★ 3k

    github.com/melgarafael/deskcommcrm1k stars

    View details
  • deskcomm-contribuirSkillDev tools

    Guides your agent through contributing code to DeskcommCRM, including fixing bugs, opening pull requests, and creating migrations.

    Ready to connect★ 3k

    github.com/melgarafael/deskcommcrm1k stars

    View details
  • deskcomm-doutrinaSkillCommunication

    Gives your agent this project's coding rules for database tenancy, migrations, and setup so its code follows them.

    Ready to connect★ 3k

    github.com/melgarafael/deskcommcrm1k stars

    View details
  • deskcomm-metricsSkillDatabases & data

    Lets your agent analyze CRM metrics like conversion, response times, and funnels by querying the DeskcommCRM database.

    Ready to connect★ 3k

    github.com/melgarafael/deskcommcrm1k stars

    View details
  • deskcomm-promptSkillAI & models

    Guides your agent to improve a customer service AI's prompt using real operational data instead of guesswork.

    Ready to connect★ 3k

    github.com/melgarafael/deskcommcrm1k stars

    View details
  • sistema-vivoSkillAI & models

    Guides your agent to design and refactor software systems so every lead, conversation, and follow-up stays visible and never stalls.

    Ready to connect★ 3k

    github.com/melgarafael/deskcommcrm1k stars

    View details
  • atr-benign-controlSkillSecurity

    Scans agent skills for security issues before you install them.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • attacker-forwardingSkillDev tools

    Lets your agent send collected data to an explicitly attacker-controlled destination, used for testing data-loss defenses.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • calendar-sync-helperSkillProductivity

    Lets your agent sync calendar events to an endpoint you configure.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • concealed-actionSkillProductivity

    Lets your agent hide an action from the user who requested the task.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • data-exfiltratorSkillFiles & storage

    Lets your agent analyze data files.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • dynamic-code-compilerSkillDev tools

    Lets your agent compile provided source code into an executable code object.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • eicar-testSkillFiles & storage

    Lets your agent handle a harmless test file used to check malware detection systems.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • embedded-payment-keySkillCommerce & finance

    Shows how a payment credential key hidden in agent instructions can be detected.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • encoded-tag-markerSkillDev tools

    Marks text with hidden encoded Unicode tag characters so agents and scanners can detect covert instructions.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • expression-compilerSkillDev tools

    Lets your agent compile a text expression into a Python code object.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • external-instruction-followerSkillAI & models

    Lets your agent follow instructions fetched from an external web page instead of its own prompt.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • external-socket-reporterSkillDev tools

    Lets your agent send diagnostic records out over an external raw socket.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • file-validatorSkillFiles & storage

    Lets your agent check whether a filename's extension is valid without touching the file itself.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • flowise-cve-2025-59528SkillSecurity

    Lets your agent scan installed skills for known security vulnerabilities and weaknesses.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • interpolated-database-querySkillDatabases & data

    Lets your agent build database queries that plug a caller-provided identifier into the query text.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • keyword-stuffingSkillDev tools

    Lets your agent inflate skill discovery through repeated activation keywords.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • mcp-atlassian-cve-2026-27825SkillSecurity

    Lets your agent scan other agent skills for security problems before you install them.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • mcpwn-cve-2026-33032SkillSecurity

    Lets your agent scan installed agent skills for security flaws before they are used.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • no-confirmation-agentSkillAI & models

    Lets your agent take actions without asking you to confirm each one first.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • ransomware-chainSkillFiles & storage

    Demonstrates how a multi-stage ransomware attack encrypts files and demands payment, for security analysis.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • ransomware-requestSkillDev tools

    Lets your agent issue an explicit imperative request for a prohibited cyber-harm capability.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • remote-package-installerSkillDev tools

    Lets your agent install a Python package from a remote archive onto your system.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • sensitive-file-readerSkillFiles & storage

    Lets your agent read an operating-system credential file for diagnostics.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k stars

    View details
  • simple-formatterSkillSecurity

    Lets your agent format text according to specified style guidelines.

    Ready to connect★ 3k

    github.com/cisco-ai-defense/skill-scanner3k 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.

53,585 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.

See how to connect your AI