Agent skills SDK: run Claude skills and AI agent skills from code

SkillGild has released open-source TypeScript, Python and Go SDKs under the MIT license that let developers search its skill catalog, run hosted skills and drive hybrid skill sessions from their own code, scripts, backends or custom agents. Each SDK is a dependency-free client for the SkillGild REST API, with catalog browsing requiring no API key and hosted runs, hybrid sessions and account operations requiring one; access decisions stay server-side so paid skills remain paid regardless of client. The company demonstrated the TypeScript SDK against its production API, showing catalog search, tool listing and typed error handling.

Agent skills are packaged instructions and tools that teach an AI agent a specific job, like designing a logo or plotting research data. Claude skills https://skillgild.dev/learn/claude-skills are the best-known example. Usually you use skills inside a coding agent such as Claude Code. An agent skills SDK lets your own code use them too. SkillGild now has open-source SDKs for TypeScript, Python and Go that search the skill catalog https://skillgild.dev/skills , run hosted skills and drive hybrid skill sessions from any app, script, backend or custom agent. The same skills keep working in Claude Code, Codex, Cursor and any MCP client. The source is public at github.com/SkillGild/sdks https://github.com/SkillGild/sdks under the MIT license. This guide shows how the SDKs work, what a real run looks like, and how they compare with the other ways to call agent skills from code. Each SDK is a small, dependency-free client for the SkillGild REST API https://skillgild.dev/docs/api ; the developer quickstart https://skillgild.dev/docs/quickstart-developers gets you from an API key to a first run. All three cover the same operations: | Area | What you can do | Needs an API key | |---|---|---| | Catalog | List and search skills, read a skill's input schema, tools, media and page copy, browse categories, tags, collections and featured skills | No | | Hosted runs | Run a prompt pipeline skill in one call, with an idempotency key for safe retries | Yes | | Hybrid sessions | Start or resume a session, call the skill's server tools, end the session | Yes | | Account | Read the key's account, revoke the current key, sign in a device | Yes, except device sign-in | Errors come back as one typed error with the HTTP status, the API's error code and, for rate limits and quotas, the Retry-After delay. Access decisions stay on the server: the SDK never holds skill prompts, so a paid skill stays paid no matter which client calls it. TypeScript / JavaScript Node 20+, Bun, Deno, browsers npm install @skillgild/sdk Python 3.9+ pip install skillgild Go 1.22+ go get github.com/skillgild/sdks/go The packages are on npm https://www.npmjs.com/package/@skillgild/sdk , PyPI https://pypi.org/project/skillgild/ and pkg.go.dev https://pkg.go.dev/github.com/skillgild/sdks/go/skillgild . Create an API key under Settings → API keys in your account https://skillgild.dev/account?section=settings and export it as SKILLGILD API KEY . Browsing the catalog needs no key. We ran this script with the TypeScript SDK, built from the 0.1.0 source, against the production API on October 6, 2026. It searches the catalog, reads a skill's tools, then calls startSession with a deliberately invalid key to show the error you get back. js import { SkillGildClient, SkillGildError } from "@skillgild/sdk"; const client = new SkillGildClient ; // no key needed for the catalog const { items } = await client.listSkills { query: "design", limit: 5 } ; for const s of items console.log s.slug, s.access tier, s.runtime type ; const skill = await client.getSkill "logo-design" ; for const t of skill.tools ?? console.log "tool:", t.name ; try { await new SkillGildClient { apiKey: "sg invalid" } .startSession "logo-design" ; } catch e { if e instanceof SkillGildError console.log e.status, e.code ; } Every skill in that result is a hybrid skill. That is typical of the current catalog, so most integrations use sessions rather than a single run call. A hybrid skill splits the work. Your agent and your model do the creative part by following the skill's guide . SkillGild runs the parts that need its code, such as validating an SVG, through server tools . The same flow in each language: js // TypeScript const session = await client.startSession "logo-design" ; // give session.guide and session.tools to your agent, then: const check = await client.callTool session.session id, "validate svg", { svg } ; await client.endSession session.session id ; Python session = client.start session "logo-design" check = client.call tool session "session id" , "validate svg", {"svg": svg} client.end session session "session id" // Go session, err := client.StartSession ctx, "logo-design" if err = nil { return err } defer client.EndSession ctx, session.SessionID check, err := client.CallTool ctx, session.SessionID, "validate svg", map string any{"svg": svg} Starting a new session uses one run from your monthly allowance. Calling startSession again while a session for the same skill version is open returns that session at no extra cost. Tool input is processed by SkillGild code only; it is not sent to a model provider and not stored. The session limits https://skillgild.dev/docs/api session-limits list how many tool calls a session allows and when it expires. A hosted prompt pipeline skill runs entirely on SkillGild and returns its output in one call. Pass an idempotency key so a retry after a timeout cannot charge you twice: python import os, time, uuid from skillgild import SkillGildClient, SkillGildError client = SkillGildClient api key=os.environ "SKILLGILD API KEY" key = str uuid.uuid4 try: run = client.run skill "your-skill", {"prompt": "..."}, idempotency key=key except SkillGildError as error: if error.status == 429: time.sleep error.retry after or 2 then retry with the same key The API stores a successful response for 24 hours and replays it for the same key. Reusing a key with a different request is rejected. See idempotency https://skillgild.dev/docs/api idempotency for the exact rules. "Agent skills SDK" means different things depending on where the skill lives. Here is how the main options compare: | | SkillGild SDKs | Claude Agent SDK | Claude API skills | Community registries | |---|---|---|---|---| | Where skills live | Hosted on SkillGild | SKILL.md folders on disk | Uploaded to your Anthropic account | Any source you configure | | Languages | TypeScript, Python, Go | TypeScript, Python | Any HTTP client | Varies for example Python | | Model | Your choice; hybrid skills run in your agent | Claude | Claude | Your choice | | You maintain the skill files | No | Yes | Yes | Yes | | Server-side tools and access control | Yes | No | Code execution in Anthropic's container | No | SKILL.md skills from any source and expose them to your own agent. These are not either-or. A common setup keeps your own skills as local files and calls hosted SkillGild skills, which bring server-side tools and stay up to date, through the SDK. If you only use skills inside a coding agent, you don't need an SDK at all: connect Claude Code https://skillgild.dev/learn/install-claude-code-skills , Codex https://skillgild.dev/learn/install-codex-skills or Cursor https://skillgild.dev/learn/cursor-mcp-setup over MCP instead. Agent skills vs MCP https://skillgild.dev/learn/agent-skills-vs-mcp explains the difference. All of these are free and work through the SDK today: Browse by job: Design https://skillgild.dev/categories/design , Video & Media https://skillgild.dev/categories/video-media , Research https://skillgild.dev/categories/research , Development https://skillgild.dev/categories/development . Yes. SkillGild publishes open-source SDKs for TypeScript, Python and Go that search, run and orchestrate hosted agent skills over a REST API. Anthropic's Claude Agent SDK also loads skills, from SKILL.md folders on disk. Yes, in two ways. Anthropic's Claude API accepts skills you upload to your account. SkillGild's API runs hosted skills, including ones made for Claude Code, from any language, and hybrid skills run with whichever model your agent uses. The SDKs are free and MIT-licensed. Running skills uses your SkillGild allowance: free skills include monthly runs, and paid skills need a purchase or a Pro plan. See pricing https://skillgild.dev/pricing . Only to run skills, open sessions or read your account. Listing and searching the catalog works without a key. TypeScript and JavaScript Node 20+, Bun, Deno and browsers , Python 3.9+ and Go 1.22+. Any other language can call the REST API https://skillgild.dev/docs/api directly. Originally published at skillgild.dev https://skillgild.dev/learn/agent-skills-sdk .