Skip to content
cccskills
FreePublished on GitHub

Calliper-Compare2Markdown

Compare two local documents and convert differences into LLM-ready Markdown in one synchronous call. Supports PDF, Word, PPT, and image documents accepted by Calliper, and returns a structured markdown diff table suitable for change review, clause comparison, downstream extraction, and rule-based validation.

The English summary is being prepared. Showing the original description.

See how to install

Files included (3)

  • SKILL.md3.8 KB
  • agents/openai.yaml608 B
  • scripts/compare_to_markdown.js5.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Calliper-Compare2Markdown

Run a JavaScript workflow that submits two local files to the calliper synchronous API through PDRouter (POST /openapi/{serviceCode}/compare/markdown by default) and returns Markdown diff output in one step. This is suitable for document comparison, change extraction, compliance checks, and feeding structured diff content into follow-up scripts.

Installation

npx skills add PaodingAI/skills

Usage

node skills/calliper-compare2markdown/scripts/compare_to_markdown.js <left-file-path> <right-file-path> [output-markdown-path]

Execution Constraints

  • You must invoke scripts/compare_to_markdown.js directly. Do not reimplement the API flow yourself.
  • The behavior contract below explains what the script does, what it outputs, and when to use it. It is not a manual checklist for the model to imitate step by step.
  • For any task that depends on cross-document differences, you must run this script first and continue from the generated Markdown result.
  • Only inspect or modify the script implementation when the script itself is unavailable, failing, or needs a fix. Do not bypass it during normal use.

When to Use

  • Use this skill when the user wants to compare two documents and get structured differences in Markdown.
  • Use this skill when the user says things like "diff to markdown", "compare and output markdown", "导出差异 markdown", or asks for a machine-readable diff summary.
  • When downstream work depends on differences, such as clause extraction, mismatch validation, or rule checks, use this skill first.
  • When the diff content is only intermediate input, prefer writing to a working file and extract only required segments instead of returning full raw Markdown.
  • When the user explicitly asks for the original markdown diff output, return the full Markdown directly.

Environment Variables

  • PAODINGAI_API_KEY: Preferred bearer token used by the script.
  • CALLIPER_ACCESS_TOKEN: Optional fallback bearer token when PAODINGAI_API_KEY is absent.
  • PD_ROUTER_BASE_URL: Optional. Defaults to https://platform.paodingai.com/platform/.
  • PD_ROUTER_SERVICE_CODE: Optional. Defaults to calliper.
  • PD_ROUTER_COMPARE_ENDPOINT: Optional. Defaults to /compare/markdown. Use only when routing endpoint differs.
  • CALLIPER_COMPARE_CONFIG: Optional. JSON string forwarded as config form field. Default is {}.

Script Behavior

  1. Read bearer token from PAODINGAI_API_KEY; fallback to CALLIPER_ACCESS_TOKEN; fail if both are missing.
  2. Validate both local input files exist.
  3. Send one multipart request with file1, file2, and optional config to POST /openapi/{serviceCode}{compareEndpoint} using Authorization: Bearer <token>.
  4. Parse final response and output:
    • Markdown text directly when response is markdown/plain text.
    • Otherwise, resolve markdown from common JSON fields (data.markdown, markdown) or fallback to JSON text.
  5. If output-markdown-path is provided, also write the same output text to that file while still printing to stdout.
  6. Write progress and errors to stderr and return non-zero exit code on failure.
  7. For field/table extraction tasks, parse and return only required fragments unless user explicitly asks for the full markdown diff.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Audit one local prospectus PDF, DOC, or DOCX through PDRouter and download the annotated document with AutoDoc NEXT2.0.

The English summary is being prepared. Showing the original description.

PaodingAI/skills17Updated Oct 14, 2026

Create and operate ChatDOC Studio knowledge bases through pd_router using a Bearer API key and JavaScript helpers. Use when Codex needs to upload one or more PDF/DOC/DOCX files, skip failed files without aborting the whole job, create a knowledge base from successful uploads, or call the ChatDOC Studio knowledge-base skill endpoints through `https://platform.paodingai.com/openapi/chatdoc-studio/...`.

The English summary is being prepared. Showing the original description.

PaodingAI/skills17Updated Oct 14, 2026

Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and validation, knowledge retrieval, and intelligent Q&A.

The English summary is being prepared. Showing the original description.

PaodingAI/skills17Updated Oct 14, 2026

See all skills by PaodingAI

Report a problem with this skill