Tech API Integration

What it does

When your agent uses it

• The user needs to connect to a third-party API
• Design an API client
• Troubleshoot API errors
• Understand API concepts — even if they say connect to this API

Example prompts

• “connect to this API”
• “why is the API returning errors”
• “how do I authenticate”
• “/tech-api-integration”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

1. 1[ ] Read API documentation completely
2. 2[ ] Test auth flow (get valid token/key)
3. 3[ ] Test each endpoint with curl/Postman first
4. 4[ ] Implement error handling for all status code ranges
5. 5[ ] Implement rate limit handling
6. 6[ ] Implement retry logic with backoff
7. 7[ ] Log all requests and responses (redact secrets)
8. 8[ ] Handle API versioning (pin to specific version)
9. 9[ ] Set timeouts (connect: 5s, read: 30s)
10. 10[ ] Monitor for API deprecation notices

What it can do on your machine

Read from SKILL.md and the folder at commit 4e7f4f8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tech API Integration loads about 1.3k tokens when it runs, and up to ~8.7k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 394 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~99

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~8.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from asgard-ai-platform/skills at commit 4e7f4f8, republished under its MIT licence (© asgard-ai-platform). 394 words, ~1,320 tokens.

name

tech-api-integration

description

Guide REST API integration including HTTP methods, authentication, error handling, and rate limiting. Use this skill when the user needs to connect to a third-party API, design an API client, troubleshoot API errors, or understand API concepts — even if they say 'connect to this API', 'why is the API returning errors', 'how do I authenticate', or 'build an API integration'.

metadata.category

WP-11 通用技術

metadata.tags

technology, api, rest, integration

IRON LAW: Read the Docs, Then Build, Then Handle Errors

1. Read the API documentation completely (auth, endpoints, rate limits, errors)
2. Get a successful request working in isolation (curl/Postman)
3. Build error handling BEFORE building features

Skipping step 1 wastes hours on trial-and-error. Skipping step 3
creates fragile integrations that break silently in production.

try:
    response = api.call(request)
    if response.status == 429:  # Rate limited
        wait(response.headers['Retry-After'])
        retry()
    elif response.status >= 500:  # Server error
        retry_with_backoff(max_retries=3)
    elif response.status >= 400:  # Client error
        log_error(response.body)
        raise ClientError(response.body['message'])
    else:
        return response.json()

# API Integration Plan: {API Name}

## API Overview
- Base URL: {url}
- Auth: {type}
- Rate limit: {N requests/period}
- Documentation: {link}

## Endpoints Used
| Endpoint | Method | Purpose | Auth |
|----------|--------|---------|------|
| {path} | GET/POST | {what it does} | {auth type} |

## Error Handling
| Error | Response | Our Action |
|-------|----------|-----------|
| 401 | Unauthorized | Refresh token, retry |
| 429 | Rate limited | Backoff, retry after Retry-After |
| 500 | Server error | Retry 3x with exponential backoff |

## Implementation Timeline
| Phase | Task | Duration |
|-------|------|----------|
| 1 | Auth + basic call | {days} |
| 2 | Full integration | {days} |
| 3 | Error handling + monitoring | {days} |

© asgard-ai-platform, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in tech-api-integration of asgard-ai-platform/skills.

• SKILL.md
• examples/sample_scenario.md
• references/oauth-guide.md
• references/webhook-patterns.md

Open the folder on GitHubat commit 4e7f4f8