Improve a skill's public listing before publish. Use when tightening title, description, tags, changelog, and scan-friendly packaging so the listing looks clearer and less suspicious.
Install with the open skills CLI (global, non-interactive — available in every Claude Code session):
npx skills add LeoYeAI/openclaw-master-skills --skill "skill-listing-polisher" -g -a claude-code -yOr manually — clone and copy the skill directory (SKILL.md + companion files):
git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills /tmp/openclaw-master-skills && cp -r /tmp/openclaw-master-skills/skills/skill-listing-polisher ~/.claude/skills/skill-listing-polisherThis skill is a directory: SKILL.md is the entry point; the files below ship with it.
---
name: skill-listing-polisher
description: Improve a skill's public listing before publish. Use when tightening title, description, tags, changelog, and scan-friendly packaging so the listing looks clearer and less suspicious.
version: 0.1.0
---
# Skill Listing Polisher
Use this skill before publishing or updating a public ClawHub skill.
## What to improve
- title clarity
- description length and truncation risk
- tags that match the actual use case
- changelog that says what changed in plain language
- public package surface that looks normal in review
## Review order
1. shorten the public description if it gets cut off
2. remove internal-only scripts and private identifiers
3. tighten tags to actual buyer intent
4. make the changelog specific and boring
5. check that the package only contains user-facing files
## Fast checks
Run the bundled script:
```bash
./scripts/check-listing.sh /path/to/skill
```
## Output style
When reviewing a skill, return:
1. what weakens trust
2. what weakens discoverability
3. the smallest edit that improves both
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when executing implementation plans with independent tasks in the current session