Features
Organize incoming messages, confirmed facts and supplied policies, then use your connected model to write an email or support reply. Check recipients, evidence, numbers, links and commitment wording. Save a local draft.txt and checklist for your review.
Usage examples
After installation, send any example below to your AI. Include the files or URLs it refers to.
Draft a polite Chinese response to a customer's order-status inquiry using my processing records.
Draft an English reply using this email and refund policy; check amounts, dates and links, and list unresolved facts.
Make this reply shorter, retain confirmed facts, and save draft.txt for my review.
Advanced usage: run in a terminal
These commands are for manual execution in the terminal on the computer or server running OpenClaw. For everyday use, send one of the chat examples above.
Replace these placeholders with actual paths before running:
SKILL_DIRECTORY: the installed Skill folder.WORKSPACE: the agent workspace path.INPUT_JSON: the prepared input JSON file.
Have OpenClaw prepare the message, facts and draft using samples/reply.json, then run:
node "SKILL_DIRECTORY/scripts/check.mjs" --input "INPUT_JSON" --output-dir "WORKSPACE"
Use actual file paths and an existing workspace. Results include the reply draft, checklist.md and a structured report.