docguide
Turn dense technical documentation and API references into actionable, source-grounded integration guides.
$5
Works with the AI tools you already use
docguide
Example session with this skill installed
I've attached the API docs for our new payment gateway. Can you explain how to set up the webhook listener for successful payments and what fields I need to verify?
- Read your context and instructions
- Compiled the docguide
I have analyzed the payment gateway documentation. The webhook setup is handled via the /v2/settings/webhooks endpoint.
Webhook Integration Guide
| Requirement | Documentation Specification | Source Reference |
|---|---|---|
| Endpoint URL | Must be HTTPS and accessible from public internet | Section 4.1: Webhook Security |
| Event Type | payment.succeeded | Appendix B: Event Types |
| Verification Field | x-gateway-signature header | Section 4.2: Signature Verification |
| Payload Format | JSON | Section 4.1: Webhook Security |
| Retry Logic | Exponential backoff over 24 hours | Section 4.5: Failure Handling |
Implementation Logic
- Configure Listener: Set your listener to accept
POSTrequests at your endpoint.
Validate Signature: Compute a HMAC-SHA256 hash using your WEBHOOK_SECRET and the raw request body. Compare this to the x-gateway-signature header.
3.
Process Data: Extract the object.id (Transaction ID) and amount from the data object to update your database.
4. Respond: Return a 200 OK status immediately to acknowledge receipt.
General Guidance
While not mentioned in the docs, it is standard practice to implement idempotency checks using the event_id to prevent processing the same notification twice if the gateway retries a successful delivery.
Next steps
- Retrieve your
WEBHOOK_SECRETfrom the developer dashboard. - Whitelist the gateway's IP addresses listed in Section 4.6 of the documentation.
- Test the flow using the
/v2/test/webhook-triggerendpoint.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Developers often struggle to digest bloated API documentation, leading to integration errors and missed requirements. Relying on general LLM knowledge for specific SDKs or internal docs results in dangerous hallucinations about endpoints and credentials.
What it does
- Extracts specific integration steps, prerequisites, and authentication flows from uploaded PDFs, URLs, or OpenAPI files.
- Maps and identifies conflicts between multiple documentation sources, version mismatches, and environment-specific (sandbox vs. production) differences.
- Translates complex technical jargon into plain-language summaries while maintaining a separate layer for low-level technical detail.
- Generates implementation code strictly grounded in the provided documentation versions and supported parameters.
Why this beats prompting it yourself
Standard prompts often mix general web knowledge with specific documentation, creating "frankenstein" code that doesn't work. This skill enforces a hard boundary between source facts and general guidance, requiring precise citations for every claim to ensure traceability and reliability.
Use cases
- Creating an actionable integration roadmap from a 100-page PDF developer guide.
- Comparing two versions of an API to identify breaking changes and deprecations.
- Troubleshooting cryptic error codes by searching documented causes across multiple READMEs.
- Explaining internal team documentation to new hires without losing technical accuracy.
Known limitations
Cannot access documentation behind authentication walls unless the content is provided directly as text or files. Reliability depends on the readability of the supplied source material.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 12 days ago
- Passed all security checks, Safe to install
Needs access to