Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Scans and fetches the most up-to-date documentation for coding tasks. Use when building integrations (e.g. OpenRouter), implementing third-party APIs, or whe...
Scans and fetches the most up-to-date documentation for coding tasks. Use when building integrations (e.g. OpenRouter), implementing third-party APIs, or whe...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
When working on integrations or any coding task that depends on external APIs or services, fetch current documentation instead of relying on training data. Docs and model lists change frequently.
Building or debugging OpenRouter (or similar) integrations Implementing or updating third-party API usage User asks for "latest docs", "current API", "model list", or "official reference" Choosing models, parameters, or SDK usage for a service
Identify the canonical doc base for the task (e.g. https://openrouter.ai/docs for OpenRouter). Fetch the relevant URLs using the web fetch tool: Main docs/quickstart API reference Models/list page when model IDs, pricing, or capabilities matter Use the fetched content to implement or correct code (endpoints, headers, request/response shapes, model IDs). Cite the URLs you used so the user can verify or read more.
When the task involves OpenRouter, fetch these for current behavior: PurposeURLQuickstart & SDKhttps://openrouter.ai/docsAPI reference (request/response, params)https://openrouter.ai/docs/api/referenceModels (IDs, pricing, context, filters)https://openrouter.ai/modelsOpenAPI spechttps://openrouter.ai/openapi.json Integration checklist (OpenRouter): Base URL: https://openrouter.ai/api/v1 Chat completions: POST .../chat/completions Auth header: Authorization: Bearer <OPENROUTER_API_KEY> Optional headers: HTTP-Referer, X-Title for attribution Model IDs include provider prefix (e.g. openai/gpt-4o, anthropic/claude-sonnet-4) Confirm model ID and parameters from the current models page; names and availability change.
For other APIs or SDKs: Find the official docs root (e.g. https://<service>.com/docs or /developer). Fetch quickstart + API reference (and models/catalog if applicable). Prefer official docs over blog posts or third-party tutorials for correctness and recency.
Base implementation on fetched docs, not memory. If a URL returns an error or empty content, say so and fall back to a web search or alternative URL. Keep answers concise; link to the exact pages used for details.
Workflow acceleration for inboxes, docs, calendars, planning, and execution loops.
Largest current source with strong distribution and engagement signals.