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...

Security Scan

The skill's declared purpose (rewriting SKILL.md and producing an audit) matches its instructions and has no extra install, binaries, or credential requests — it is internally coherent.

Purpose & Capability

Name/description claim to polish SKILL.md; the SKILL.md instructions describe reading the existing SKILL.md, rewriting, moving non-storefront content to references/, and producing an audit and outputs. There are no unrelated env vars, binaries, or installs required — the requested capabilities align with the stated purpose.

Instruction Scope

Instructions operate only on repository docs (SKILL.md and references/). They explicitly require preserving or moving security and credential instructions and produce an audit. This is appropriate, but moving credential/setup/security content to references/ can obscure important operational details if implemented poorly; the skill's audit rules mitigate this by flagging removals, but users should review the generated reference files and the audit before accepting changes.

Install Mechanism

No install spec and no code files — instruction-only. This is the lowest-risk install model and matches the skill's editing/formatting role.

Credentials

The skill declares no required environment variables, credentials, or special config paths. Nothing in the SKILL.md attempts to access secrets or unrelated system resources.

Persistence & Privilege

always is false, and autonomous invocation is allowed by default (normal). The skill edits repo files but does not request elevated system presence or modify other skills. It requires user approval before overwriting the original SKILL.md, which limits accidental persistence.

Assessment

This skill is coherent and low-risk as described, but review outputs before accepting them. Before running: (1) run it on a copy/branch, not master; (2) inspect the audit report and each new references/ file to ensure credential/setup/security notes were preserved and not hidden; (3) verify trigger phrases and exact LLM execution commands remain intact; (4) confirm the author/source is acceptable for your project since the package has no homepage and an unknown owner. If anything flagged in the audit looks unclear, reject the overwrite and request explicit changes.

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 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 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.