An index and topic collection covering Agent Skills, the packaged, file-based capability units that AI coding agents load to extend their behavior. Agent Skills bundle instructions, scripts, schemas, and reference material into directories that agents discover, plan against, and execute at runtime, giving organizations a portable way to govern how AI assistants interact with their products and APIs. This collection tracks vendor-published skill repositories (Claude Code skills, Claude Agent SDK skills, Cursor rules, OpenAI Apps SDK skills, and capability packages) shipped by API providers across developer tools, data platforms, SaaS, and infrastructure.
Agent Skills is profiled on the APIs.io network. Tagged areas include Agent Skills, Claude Skills, Capability Packages, AI Agents, and Developer Tooling.
The Agent Skills catalog on APIs.io includes 1 JSON-LD context.
Agent Skills’ developer surface includes developer portal and 1 more developer resources.
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for
this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero:
never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and
several others — scorable at all.
The six quality facets above are damped to 85 points between them,
because the conditional facet above carries the other
15. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 85% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Agent Skills bundle markdown instructions, executable scripts, schemas, and reference material into versioned directories that agents can load deterministically at runtime.
Vendor-Published Skill Repositories
API providers ship official GitHub repositories such as resend-skills, ngrok/agent-skills, postman-skills, and jfrog-skills to deliver first-party automation behavior for their ...
Progressive Disclosure of Context
Skills surface a short SKILL.md frontmatter for discovery, then load deeper instructions, scripts, and assets only when an agent activates them, keeping token usage low.
Agent-Executable Tooling
Skills package shell, Python, or Node scripts alongside instructions so agents can perform multi-step work (auth, file generation, API calls) instead of relying on prose-only pr...
Multi-Runtime Compatibility
Skill formats are emerging across Claude Code, Claude Agent SDK, Cursor, OpenAI Apps SDK, and Gemini, with vendors publishing parallel skill sets for each runtime.
Skill Discovery and Governance
Organizations curate skill catalogs, sign skill manifests, and gate skill activation through allow lists so AI agents only run vetted capability packages.
API-First Skill Generation
Skills are increasingly generated from OpenAPI, AsyncAPI, and APIs.json descriptions so each API operation becomes a callable, governed capability inside an agent.
Open Skill Ecosystem
A growing ecosystem of community-maintained skill registries and indexes complements vendor repos, mirroring how the npm and PyPI ecosystems formed around packages.
SaaS vendors ship official skill repos so AI agents in Claude Code or Cursor can create resources, run reports, and operate their products without bespoke prompt engineering.
Internal Developer Platform Skills
Platform teams package their CI/CD, deployment, and observability workflows as governed skills so every engineering agent uses the same approved automations.
API Onboarding and Education
API providers use skills to walk agents through authentication, sandbox setup, and "hello world" requests, accelerating time-to-first-call for developer-led agents.
Governed Capability Distribution
Compliance-sensitive organizations distribute skills with allow-lists, signing, and audit trails to ensure only approved AI behaviors run against production systems.
API Specification to Skill Pipelines
Teams convert OpenAPI specs into skill bundles (one operation per tool) so agents get typed, governed access to every endpoint without writing custom wrappers.
Cross-Runtime Skill Portability
Vendors maintain mirror skill sets for Claude, Cursor, and OpenAI Apps SDK, giving customers a consistent experience across whichever coding agent they choose.
Skill-Driven Customer Support
Support and DevRel teams publish skills that diagnose common issues, pull logs, and open tickets, letting customer-side agents resolve problems autonomously.
Sandbox and Test Environment Skills
Skill bundles provision throwaway environments, seed test data, and tear down resources so agents can exercise APIs safely during development and CI.
Pre-built integrations with other platforms and tools.
Claude Code
Anthropic's official coding agent loads skills from the .claude/skills directory and surfaces them as plan-then-execute capabilities.
Claude Agent SDK
The Claude Agent SDK lets developers embed skill loading and execution into their own agent harnesses with the same SKILL.md contract as Claude Code.
Cursor
Cursor consumes vendor rules and skill-style instruction bundles to extend its in-editor coding agent with provider-specific behavior.
OpenAI Apps SDK
The OpenAI Apps SDK provides a skill-equivalent surface so apps and agents on the OpenAI platform can ship packaged capabilities to ChatGPT and developer tools.
Google Gemini
Gemini's GEMINI.md and skill-style instruction files let vendors target Google's coding agent surface alongside Claude and Cursor.
GitHub
GitHub hosts the canonical distribution channel for skill repositories, including vendor-published agent-skills, claude-skills, and *-skills repos.
Postman
Postman's skill repository ships first-party capabilities for working with Postman collections, workspaces, and the Postman API from coding agents.
Anthropic
Anthropic publishes the SKILL.md format, reference skill repositories, and the Skills feature in Claude Code that anchors the broader ecosystem.
aid: agents-skills
name: Agent Skills
description: An index and topic collection covering Agent Skills, the packaged, file-based capability units that AI coding
agents load to extend their behavior. Agent Skills bundle instructions, scripts, schemas, and reference material into directories
that agents discover, plan against, and execute at runtime, giving organizations a portable way to govern how AI assistants
interact with their products and APIs. This collection tracks vendor-published skill repositories (Claude Code skills, Claude
Agent SDK skills, Cursor rules, OpenAI Apps SDK skills, and capability packages) shipped by API providers across developer
tools, data platforms, SaaS, and infrastructure.
type: Index
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- Agent Skills
- Claude Skills
- Capability Packages
- AI Agents
- Developer Tooling
url: https://raw.githubusercontent.com/api-evangelist/agents-skills/refs/heads/main/apis.yml
created: '2026-05-19'
modified: '2026-05-19'
specificationVersion: '0.19'
apis: []
network:
- name: ActiveCampaign
url: https://raw.githubusercontent.com/api-evangelist/activecampaign/refs/heads/main/apis.yml
- name: Airbyte
url: https://raw.githubusercontent.com/api-evangelist/airbyte/refs/heads/main/apis.yml
- name: Airtable
url: https://raw.githubusercontent.com/api-evangelist/airtable/refs/heads/main/apis.yml
- name: Android
url: https://raw.githubusercontent.com/api-evangelist/android/refs/heads/main/apis.yml
- name: Angular
url: https://raw.githubusercontent.com/api-evangelist/angular/refs/heads/main/apis.yml
- name: Anthropic
url: https://raw.githubusercontent.com/api-evangelist/anthropic/refs/heads/main/apis.yml
- name: Anthropic Claude
url: https://raw.githubusercontent.com/api-evangelist/anthropic-claude/refs/heads/main/apis.yml
- name: Apify
url: https://raw.githubusercontent.com/api-evangelist/apify/refs/heads/main/apis.yml
- name: Apollo Config
url: https://raw.githubusercontent.com/api-evangelist/apollo-config/refs/heads/main/apis.yml
- name: Apollo GraphQL
url: https://raw.githubusercontent.com/api-evangelist/apollo-graphql/refs/heads/main/apis.yml
- name: Appium
url: https://raw.githubusercontent.com/api-evangelist/appium/refs/heads/main/apis.yml
- name: Appwrite
url: https://raw.githubusercontent.com/api-evangelist/appwrite/refs/heads/main/apis.yml
- name: Atlassian
url: https://raw.githubusercontent.com/api-evangelist/atlassian/refs/heads/main/apis.yml
- name: Auth0
url: https://raw.githubusercontent.com/api-evangelist/auth0/refs/heads/main/apis.yml
- name: Box
url: https://raw.githubusercontent.com/api-evangelist/box/refs/heads/main/apis.yml
- name: Canva
url: https://raw.githubusercontent.com/api-evangelist/canva/refs/heads/main/apis.yml
- name: Cerbos
url: https://raw.githubusercontent.com/api-evangelist/cerbos/refs/heads/main/apis.yml
- name: Claude
url: https://raw.githubusercontent.com/api-evangelist/claude/refs/heads/main/apis.yml
- name: Contentful
url: https://raw.githubusercontent.com/api-evangelist/contentful/refs/heads/main/apis.yml
- name: Databricks
url: https://raw.githubusercontent.com/api-evangelist/databricks/refs/heads/main/apis.yml
- name: Docsify
url: https://raw.githubusercontent.com/api-evangelist/docsify/refs/heads/main/apis.yml
- name: Figma
url: https://raw.githubusercontent.com/api-evangelist/figma/refs/heads/main/apis.yml
- name: Fivetran
url: https://raw.githubusercontent.com/api-evangelist/fivetran/refs/heads/main/apis.yml
- name: GEMINI.md
url: https://raw.githubusercontent.com/api-evangelist/gemini-md/refs/heads/main/apis.yml
- name: GitHub
url: https://raw.githubusercontent.com/api-evangelist/github/refs/heads/main/apis.yml
- name: Google Gemini
url: https://raw.githubusercontent.com/api-evangelist/google-gemini/refs/heads/main/apis.yml
- name: Hookdeck
url: https://raw.githubusercontent.com/api-evangelist/hookdeck/refs/heads/main/apis.yml
- name: HubSpot
url: https://raw.githubusercontent.com/api-evangelist/hubspot/refs/heads/main/apis.yml
- name: Hugging Face
url: https://raw.githubusercontent.com/api-evangelist/hugging-face/refs/heads/main/apis.yml
- name: Jentic
url: https://raw.githubusercontent.com/api-evangelist/jentic/refs/heads/main/apis.yml
- name: JFrog
url: https://raw.githubusercontent.com/api-evangelist/jfrog/refs/heads/main/apis.yml
- name: MailerLite
url: https://raw.githubusercontent.com/api-evangelist/mailerlite/refs/heads/main/apis.yml
- name: Microsoft TypeScript
url: https://raw.githubusercontent.com/api-evangelist/microsoft-typescript/refs/heads/main/apis.yml
- name: MongoDB
url: https://raw.githubusercontent.com/api-evangelist/mongodb/refs/heads/main/apis.yml
- name: ngrok
url: https://raw.githubusercontent.com/api-evangelist/ngrok/refs/heads/main/apis.yml
- name: OpenAI
url: https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/apis.yml
- name: Postman
url: https://raw.githubusercontent.com/api-evangelist/postman/refs/heads/main/apis.yml
- name: Prisma
url: https://raw.githubusercontent.com/api-evangelist/prisma/refs/heads/main/apis.yml
- name: Pulumi
url: https://raw.githubusercontent.com/api-evangelist/pulumi/refs/heads/main/apis.yml
- name: Replicate
url: https://raw.githubusercontent.com/api-evangelist/replicate/refs/heads/main/apis.yml
- name: Resend
url: https://raw.githubusercontent.com/api-evangelist/resend/refs/heads/main/apis.yml
- name: Sanity
url: https://raw.githubusercontent.com/api-evangelist/sanity/refs/heads/main/apis.yml
- name: Speakeasy
url: https://raw.githubusercontent.com/api-evangelist/speakeasy/refs/heads/main/apis.yml
- name: Supabase
url: https://raw.githubusercontent.com/api-evangelist/supabase/refs/heads/main/apis.yml
- name: Temporal
url: https://raw.githubusercontent.com/api-evangelist/temporal/refs/heads/main/apis.yml
- name: TypeScript
url: https://raw.githubusercontent.com/api-evangelist/typescript/refs/heads/main/apis.yml
- name: Webflow
url: https://raw.githubusercontent.com/api-evangelist/webflow/refs/heads/main/apis.yml
- name: WorkOS
url: https://raw.githubusercontent.com/api-evangelist/workos/refs/heads/main/apis.yml
- name: Zoom
url: https://raw.githubusercontent.com/api-evangelist/zoom/refs/heads/main/apis.yml
common:
- type: Portal
url: https://apievangelist.com
- type: GitHubOrganization
url: https://github.com/api-evangelist
- type: Features
data:
- name: File-Based Capability Packaging
description: Agent Skills bundle markdown instructions, executable scripts, schemas, and reference material into versioned
directories that agents can load deterministically at runtime.
- name: Vendor-Published Skill Repositories
description: API providers ship official GitHub repositories such as resend-skills, ngrok/agent-skills, postman-skills,
and jfrog-skills to deliver first-party automation behavior for their products.
- name: Progressive Disclosure of Context
description: Skills surface a short SKILL.md frontmatter for discovery, then load deeper instructions, scripts, and assets
only when an agent activates them, keeping token usage low.
- name: Agent-Executable Tooling
description: Skills package shell, Python, or Node scripts alongside instructions so agents can perform multi-step work
(auth, file generation, API calls) instead of relying on prose-only prompting.
- name: Multi-Runtime Compatibility
description: Skill formats are emerging across Claude Code, Claude Agent SDK, Cursor, OpenAI Apps SDK, and Gemini, with
vendors publishing parallel skill sets for each runtime.
- name: Skill Discovery and Governance
description: Organizations curate skill catalogs, sign skill manifests, and gate skill activation through allow lists
so AI agents only run vetted capability packages.
- name: API-First Skill Generation
description: Skills are increasingly generated from OpenAPI, AsyncAPI, and APIs.json descriptions so each API operation
becomes a callable, governed capability inside an agent.
- name: Open Skill Ecosystem
description: A growing ecosystem of community-maintained skill registries and indexes complements vendor repos, mirroring
how the npm and PyPI ecosystems formed around packages.
- type: UseCases
data:
- name: First-Party Product Skills
description: SaaS vendors ship official skill repos so AI agents in Claude Code or Cursor can create resources, run reports,
and operate their products without bespoke prompt engineering.
- name: Internal Developer Platform Skills
description: Platform teams package their CI/CD, deployment, and observability workflows as governed skills so every engineering
agent uses the same approved automations.
- name: API Onboarding and Education
description: API providers use skills to walk agents through authentication, sandbox setup, and "hello world" requests,
accelerating time-to-first-call for developer-led agents.
- name: Governed Capability Distribution
description: Compliance-sensitive organizations distribute skills with allow-lists, signing, and audit trails to ensure
only approved AI behaviors run against production systems.
- name: API Specification to Skill Pipelines
description: Teams convert OpenAPI specs into skill bundles (one operation per tool) so agents get typed, governed access
to every endpoint without writing custom wrappers.
- name: Cross-Runtime Skill Portability
description: Vendors maintain mirror skill sets for Claude, Cursor, and OpenAI Apps SDK, giving customers a consistent
experience across whichever coding agent they choose.
- name: Skill-Driven Customer Support
description: Support and DevRel teams publish skills that diagnose common issues, pull logs, and open tickets, letting
customer-side agents resolve problems autonomously.
- name: Sandbox and Test Environment Skills
description: Skill bundles provision throwaway environments, seed test data, and tear down resources so agents can exercise
APIs safely during development and CI.
- type: Integrations
data:
- name: Claude Code
description: Anthropic's official coding agent loads skills from the .claude/skills directory and surfaces them as plan-then-execute
capabilities.
- name: Claude Agent SDK
description: The Claude Agent SDK lets developers embed skill loading and execution into their own agent harnesses with
the same SKILL.md contract as Claude Code.
- name: Cursor
description: Cursor consumes vendor rules and skill-style instruction bundles to extend its in-editor coding agent with
provider-specific behavior.
- name: OpenAI Apps SDK
description: The OpenAI Apps SDK provides a skill-equivalent surface so apps and agents on the OpenAI platform can ship
packaged capabilities to ChatGPT and developer tools.
- name: Google Gemini
description: Gemini's GEMINI.md and skill-style instruction files let vendors target Google's coding agent surface alongside
Claude and Cursor.
- name: GitHub
description: GitHub hosts the canonical distribution channel for skill repositories, including vendor-published agent-skills,
claude-skills, and *-skills repos.
- name: Postman
description: Postman's skill repository ships first-party capabilities for working with Postman collections, workspaces,
and the Postman API from coding agents.
- name: Anthropic
description: Anthropic publishes the SKILL.md format, reference skill repositories, and the Skills feature in Claude Code
that anchors the broader ecosystem.
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com
humanURL: https://apievangelist.com
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.
Kin Score
How this is scored →