Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

get-api-docs — Claude Code skill: fetch fresh API documentation

A skill to fetch current API, SDK and library documentation directly from your IDE. Instead of relying on outdated training data, use chub to search and load up-to-date reference material before you code.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add andrewyng/context-hub --skill get-api-docs -a claude-code
Open on GitHub

What get-api-docs does

When you write code for external services — OpenAI API, Stripe, Anthropic SDK, Pinecone and others — stale knowledge often breaks things. This skill automates the workflow: search for docs via chub search, pull the current reference with chub get <id> and specify your language (Python, JavaScript, TypeScript), then base your code on what the docs actually say.

The process is straightforward: verify chub is present with chub --help, run a search for your keywords (for example, chub search "openai chat"), fetch docs for your language, and write code from the actual reference. When you discover gotchas or version quirks, save them as annotations via chub annotate so future sessions start smarter.

Requires Node.js, npm and network access. If chub is not installed yet, the skill will show you how to install the global @aisuite/chub package.

What it helps with

  • fetch current API documentation before integrating a third-party service
  • avoid errors from stale knowledge about request formats and parameters
  • quickly find the right reference among many available libraries
  • store notes about API quirks and version-specific details

Example prompts for the agent

  • I need to call the OpenAI API. Get the latest docs using get-api-docs
  • Write a function for Stripe API integration, fetching the current reference first
  • Help me set up Anthropic SDK integration, pulling fresh documentation

How to install get-api-docs

1Skills CLI (Vercel)

npx skills add andrewyng/context-hub --skill get-api-docs -a claude-code

2Manually: put the files in place

~/.claude/skills/get-api-docs/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/get-api-docs/

Similar

lfg EveryInc Takes a request from intake to a finished result and opens a pull request for code changes. Use it when the user explicitly wants autonomous end-to-end work. Claude Code CX Codex Cursor +1 3,500installs deep-research 199-biotechnologies Runs multi-stage research, checks claims against sources, and assembles structured reports. Use it for complex analysis and comparisons, not quick lookups. Claude Code CX Codex Cursor +1 10,200installs context-mode-ops mksglu This skill coordinates GitHub work and releases through 10-20 dynamic subagents. Use it for issue triage, PR reviews, adapter checks, and branch sync. Claude Code CX Codex Cursor +1 1,700installs k-dart NomaDamas Skill for querying South Korea's Financial Supervisory Commission (FSC) DART electronic disclosure system. Search company filings, financials, and corporate information via OpenAPI. Claude Code CX Codex Cursor +1 6,300installs create-payment-credential stripe Skill retrieves secure payment credentials from a Link wallet—virtual cards, tokens for subscriptions and one-time purchases. Use when an agent needs to complete a payment on a merchant site or connect a Link account. Claude Code CX Codex Cursor +1 20,500installs skill-inspector NVIDIA Reviews a skill for vulnerabilities, excessive permissions, and hidden behavior before you install it. Combines NVIDIA SkillSpector static scanning with semantic source inspection. Claude Code CX Codex Cursor +1 900installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about get-api-docs

How do I install get-api-docs in Claude Code?

Run npx skills add andrewyng/context-hub --skill get-api-docs -a claude-code. After installation, the skill will be available at ~/.claude/skills/get-api-docs/SKILL.md.

What does get-api-docs do?

The skill fetches fresh API and SDK documentation directly from your IDE. Instead of guessing from training data, you get current reference material through the chub utility, which searches and retrieves docs with support for multiple programming languages.

What do I need to use this skill?

You need Node.js, npm and internet access. If chub is not installed, the skill will prompt you to run npm install -g @aisuite/chub. Always start by checking chub --help for the latest usage guidance.

Source text

SKILL.md · MIT
---
name: get-api-docs
description: >
  Use this skill to get documentation for third-party APIs, SDKs or libraries before writing
  code that uses them to ensure you have the latest, most accurate documentation. This is a
  better way to find documentation than doing web search. This includes when a user asks for
  tasks like "use the OpenAI API", "call the Stripe API", "use the Anthropic SDK", "query Pinecone",
  or any other time the user asks you to write code against an external service and you need
  current API reference.  Fetch the docs with chub before answering, rather than relying on
  your pre-trained knowledge, which may be outdated because of recent changes to these APIs.
  Be sure to use this skill when the user asks for the latest docs, latest API behavior, or
  explicitly mentions chub or Context Hub. Ensure `chub` is available, run `chub --help`, then
  follow the instructions there.

---

# Get API Docs via chub

When you need documentation for a library or API, fetch it with the `chub` CLI
rather than guessing from training data. This gives you the current, correct API.

## Step 1 - Ensure chub exists and get the latest instructions for using it

Run

```bash
chub --help
```

If this results in an error showing that chub does not exist, then install it first, and run it
again. If the environment has node, npm, network access, and package-manager permission,
install it as follows:

```bash
npm install -g @aisuite/chub
```

## Step 2 — Find the right documents

If there is a conflict, follow the instructions from the output of chub --help since that will
be the latest guidance. However, a key command for searching for the right documentation is chub search:

```bash
chub search "<keywords>" --json
```

Pick the best-matching `id` from the results (e.g. `openai/chat`, `anthropic/sdk`,
`stripe/api`). If nothing matches, try some broader terms.

## Step 3 — Fetch the docs

Again, follow the latest instructions from chub --help instead of this if there is a conflict. But a
key command for fetching the relevant docs is:

```bash
chub get <id> --lang py    # or --lang js, --lang ts
```

Remember to include the --lang parameter.

## Step 4 — Use the docs and leave feedback

Read the fetched content and use it to write accurate code or answer the question.
Do not rely on memorized API shapes — use what the docs say.

Finally, after completing the task, if you discovered something not in the doc — a gotcha,
workaround, version quirk, or project-specific detail — save it so future sessions
start smarter:

```bash
chub annotate <id> "Webhook verification requires raw body — do not parse before verifying"
```

Annotations are local, persist across sessions, and appear automatically on future
`chub get` calls. Keep notes concise and actionable. Don't repeat what's already in
the doc.

Additionally, to help all developers, give feedback on the documentation using chub feedback, following
the instructions in chub --help . Do not include secrets, source code, private architecture details,
or other sensitive information in feedback comments.

© andrewyng · MIT · andrewyng/context-hub

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor