skill-polisher

Polish a skill's SKILL.md for ClawHub readability without sacrificing LLM effectiveness. Use when improving a skill's listing, making a skill look better on ClawHub, or preparing a skill for publish. Rewrites SKILL.md with better formatting, then audits the changes to ensure nothing the LLM needs was lost. Moved content goes to references/ — never deleted.

3,891 stars

Best use case

skill-polisher is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Polish a skill's SKILL.md for ClawHub readability without sacrificing LLM effectiveness. Use when improving a skill's listing, making a skill look better on ClawHub, or preparing a skill for publish. Rewrites SKILL.md with better formatting, then audits the changes to ensure nothing the LLM needs was lost. Moved content goes to references/ — never deleted.

Teams using skill-polisher should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/rebels-skill-polisher/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/99rebels/rebels-skill-polisher/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/rebels-skill-polisher/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skill-polisher Compares

Feature / Agentskill-polisherStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Polish a skill's SKILL.md for ClawHub readability without sacrificing LLM effectiveness. Use when improving a skill's listing, making a skill look better on ClawHub, or preparing a skill for publish. Rewrites SKILL.md with better formatting, then audits the changes to ensure nothing the LLM needs was lost. Moved content goes to references/ — never deleted.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Skill Polisher 🪚

Improve a skill's SKILL.md for ClawHub readability. Run after the skill is built and tested — never before.

## Priority Order

1. **LLM execution** — the agent must still be able to do the task correctly
2. **Triggering** — the skill must still activate on the right queries
3. **ClawHub display** — browsers should understand the skill at a glance

Readability supports these goals. Never sacrifice clarity for aesthetics.

## How It Works

```
1. Read the existing SKILL.md
2. Rewrite for readability (apply rules from references/)
3. Audit the rewrite against the original
4. Output: polished SKILL.md + audit report + any new reference files
```

## Before Polishing

Ensure the skill is:
- ✅ Functionally working (scripts tested)
- ✅ Validated (`quick_validate.py` passes)
- ✅ Description is correct (triggers on the right queries)

If any of these fail, fix them first. Don't polish a broken skill.

## Polishing Rules

Read [references/rules.md](references/rules.md) for the full set of formatting rules.

Key principles:
- Short paragraphs (1-2 lines) — dense blocks kill readability
- Code blocks for lists — renders as visual boxes on ClawHub
- Emoji as section anchors — 🔒 📊 ⚡ give instant visual context
- One code block per concept — not three variations for three platforms
- "Why" and "When to Use" sections — help browsers understand value

## What Gets Moved to references/

Content that's valuable but doesn't belong in the storefront:

- Platform-specific formatting examples (Slack, WhatsApp, Discord)
- Detailed credential setup tutorials
- Implementation notes (API rate limits, edge cases, gotchas)
- Extended configuration reference
- Historical changelogs

**Rule: Content is moved, never deleted. Every reference file must be valid and useful.**

## The Audit

After rewriting, compare the original against the polished version. Flag:

```
⚠ Potentially risky changes:
• Security notes removed
• Credential instructions lost
• Implementation details dropped without a reference file
• Trigger phrases removed from description
• Reference files created but empty or incomplete
```

See [references/audit-guide.md](references/audit-guide.md) for the full audit checklist.

## Output

Present three things to the user:

1. **The polished SKILL.md** — ready to review
2. **Any new reference files** — created from moved content
3. **Audit report** — what changed, what was moved, anything flagged

Wait for user approval before overwriting the original.

## When to Use

- "Make this skill look better on ClawHub"
- "Polish my SKILL.md"
- "Improve this skill's listing"
- "Ready to publish, but clean it up first"

## Not a Replacement for skill-creator

This skill polishes existing skills. Use the built-in `skill-creator` to build skills from scratch. Polish after building, not during.

Related Skills

response-tone-polisher

3891
from openclaw/skills

Polishes response letters by transforming defensive or harsh language.

medical-email-polisher

3891
from openclaw/skills

Transforms rough email drafts into polished, professional medical correspondence.

collab-offer-polisher

3891
from openclaw/skills

把合作邀约、商务私信、品牌合作需求和合作条款草稿,改写成更专业、更容易推进合作的版本。

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure