skill-refiner

Audit and fix all skills in the workspace for compliance with skill-creator requirements. Use when asked to "refine skills", "audit skills", "check skill quality", or "fix non-compliant skills". Exhaustively searches the entire workspace (not just skills/) to find every SKILL.md, then audits and repairs each one.

3,891 stars

byopenclaw

View on GitHub Installation ↓

Best use case

skill-refiner is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Audit and fix all skills in the workspace for compliance with skill-creator requirements. Use when asked to "refine skills", "audit skills", "check skill quality", or "fix non-compliant skills". Exhaustively searches the entire workspace (not just skills/) to find every SKILL.md, then audits and repairs each one.

Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.

Practical example

Example input

Use the "skill-refiner" skill to help with this workflow task. Context: Audit and fix all skills in the workspace for compliance with skill-creator requirements. Use when asked to "refine skills", "audit skills", "check skill quality", or "fix non-compliant skills". Exhaustively searches the entire workspace (not just skills/) to find every SKILL.md, then audits and repairs each one.

Example output

A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.

When to use this skill

Use this skill when you want a reusable workflow rather than writing the same prompt again and again.

When not to use this skill

Do not use this when you only need a one-off answer and do not need a reusable workflow.
Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill-refiner/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/1va7/skill-refiner/SKILL.md"

Manual Installation

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

How skill-refiner Compares

Feature / Agent	skill-refiner	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

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

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

AI Agents for Startups

Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.

SKILL.md Source

# Skill Refiner

Finds every skill in the workspace, audits each against skill-creator requirements, and fixes non-compliant ones.

## Workflow

### Step 1 — Discover all skills

```bash
bash scripts/find_skills.sh [workspace_dir]
```

This searches the **entire workspace** for `SKILL.md` files (not just `skills/`). Skills created without following skill-creator conventions may end up anywhere.

### Step 2 — Audit each skill

```bash
python3 scripts/audit_skill.py <skill-dir>
```

Returns JSON with:
- `issues` — blocking problems that must be fixed
- `warnings` — advisory improvements
- `compliant` — true only when issues is empty

Run this on every path returned by Step 1. Batch example:

```bash
bash scripts/find_skills.sh | while read dir; do
  python3 scripts/audit_skill.py "$dir"
done
```

### Step 3 — Report findings

Summarize results in a table:

| Skill | Location | Issues | Warnings | Status |
|-------|----------|--------|----------|--------|
| my-skill | skills/my-skill | 0 | 1 | ⚠️ |
| bad-skill | temp/bad-skill | 2 | 0 | ❌ |

### Step 4 — Fix non-compliant skills

For each skill with issues, fix in this order:

1. **Missing/malformed frontmatter** — Add or correct the `---` block with `name` and `description` only
2. **Extra frontmatter fields** — Remove any fields other than `name` and `description`
3. **Weak description** — Rewrite to include: what the skill does + trigger conditions ("Use when...")
4. **Extraneous files** — Delete README.md, INSTALLATION_GUIDE.md, CHANGELOG.md, etc.
5. **Wrong location** — If a skill is outside `skills/`, move it to `~/.openclaw/workspace/skills/<skill-name>/`
6. **Naming violations** — Rename directory to lowercase-hyphen-case

For warnings (advisory):
- Long SKILL.md (>500 lines): extract detailed content into `references/` files and link from SKILL.md
- Unlinked references: add links in SKILL.md body
- Weak description: improve trigger language

### Step 5 — Validate fixes

Re-run `audit_skill.py` on each fixed skill to confirm `"compliant": true`.

Optionally package with:
```bash
python3 /opt/homebrew/lib/node_modules/openclaw/skills/skill-creator/scripts/package_skill.py <skill-dir>
```

## Compliance Checklist

A compliant skill must have:
- [ ] `SKILL.md` at the root of a named directory
- [ ] YAML frontmatter with exactly `name` and `description` (no other fields)
- [ ] `description` includes what the skill does AND when to trigger it
- [ ] Directory name: lowercase letters, digits, hyphens only; ≤64 chars
- [ ] No extraneous files (README.md, CHANGELOG.md, etc.)
- [ ] Resources only in `scripts/`, `references/`, or `assets/`
- [ ] All `references/` files linked from SKILL.md body
- [ ] SKILL.md body ≤500 lines (split into references/ if longer)

Related Skills

sop-refiner

3891

from openclaw/skills

优化已有 SOP，删冗余、补异常路径、补回滚、补质量门槛。；use for sop, process, improvement workflows；do not use for 改变制度权限边界, 跳过安全检查.

---

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