发现优质的 AI Agent 技能

You are about to mint an **Exoskeleton** — an onchain identity NFT built specifically for AI agents. This document teaches you everything you need to create, configure, and use your Exoskeleton.

**Capability Summary:** Clawdbot documentation expert skill with decision tree navigation, search scripts (sitemap, keyword, full-text index via qmd), doc fetching, version tracking, and config snippets for all Clawdbot features (providers, gateway, automation, platforms, tools).

User-related Meegle OpenAPIs (e.g. user info, list members). **Domain, token, context (project_key, user_key), and request headers** are all obtained from skill **meegle-api-credentials**; this skill only documents the user APIs.

This skill uses the `pandoc` command-line utility to convert documents between numerous markup formats.

> **This skill is deprecated.** All functionality has been merged into **doc-process v4.0.0** with a significantly improved scanner engine. Please use `doc-process` instead. > > To scan a document photo: install `doc-process` and say "scan this photo", "correct perspective", "dewarp this document", or any equivalent phrase.

Detect, extract, clean, and output structured tabular data from PDFs, images, HTML, and text documents as CSV, JSON, or Markdown. Handle merged cells, multi-level headers, footnotes, and multi-table documents.

Extract fully structured meeting minutes — action items, decisions, attendees, discussion points, risks, open questions — from notes, documents, transcripts, or audio files. Produce outputs ready for team distribution.

Convert lab reports, prescriptions, discharge summaries, imaging reports, pathology reports, and other medical documents into clear, plain-English summaries that a non-specialist patient can understand. Flag critical values and provide actionable next-step guidance.

Identify and redact personally identifiable information (PII), financial data, health information, and other sensitive content from documents before sharing, filing, or publishing. Produce a verifiable redaction log.

Extract all machine-readable and visual fields from identity documents: passports, national ID cards, driver's licenses, visas, residence permits, and birth certificates. Decode MRZ codes, validate check digits, and flag expiry / integrity issues.

Translate any document between any languages with high fidelity, preserving structure, formatting, register, and domain-specific terminology. Support specialized domain glossaries for legal, medical, technical, and financial content.

Provide an **opt-in** session log of documents processed. The user must explicitly consent before any entry is written. Once enabled for a session, the log records document type, filename, and a PII-free one-line summary to `~/.doc-process-timeline.json`.