⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

publish-guard

@zack-dev-cm⭐ 0 stars

Review a repo, README, SKILL.md, release notes, and social copy before publishing. Catch leak risks, weak public-facing copy, broken first-run paths, and internal operator language before GitHub or ClawHub release.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 0 on GitHubGitHub ↗

New / niche

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

Publish Guard

Review a repo, README, SKILL.md, and release surface before you publish.

Publish Guard is a small public OpenClaw skill for pre-release audits. It catches obvious leak risks, public-audience mismatch, broken first-run copy, and launch-surface problems before a GitHub repo or ClawHub skill goes live.

Proof

# Publish Guard Audit

- Recommendation: **Publish**
- Launch copy score: **100/100** (publish-ready)
- Leak scan: **0** findings
- Public surface scan: **0** findings

Quick Start

python3 skill/publish-guard/scripts/scan_leaks.py \
  --root . \
  --out /tmp/publish-guard-leaks.json

python3 skill/publish-guard/scripts/scan_public_surface.py \
  --root . \
  --out /tmp/publish-guard-surface.json

python3 skill/publish-guard/scripts/score_launch_copy.py \
  --readme README.md \
  --out /tmp/publish-guard-copy.json

python3 skill/publish-guard/scripts/render_public_audit.py \
  --repo . \
  --leaks /tmp/publish-guard-leaks.json \
  --surface /tmp/publish-guard-surface.json \
  --copy /tmp/publish-guard-copy.json \
  --out /tmp/publish-guard-audit.md

What It Catches

  • absolute paths, localhost URLs, websocket endpoints, and token-shaped strings
  • operator-facing or internal language near the top of a public README
  • missing or buried quick starts
  • oversized public SKILL.md files
  • internal launch docs accidentally left in a public repo
  • public prompts and metadata that read like internal control text instead of a user-facing product

Included

  • skill/publish-guard/SKILL.md
  • skill/publish-guard/agents/openai.yaml
  • skill/publish-guard/scripts/scan_leaks.py
  • skill/publish-guard/scripts/scan_public_surface.py
  • skill/publish-guard/scripts/score_launch_copy.py
  • skill/publish-guard/scripts/render_public_audit.py

Use Cases

  • review a GitHub repo before making it public
  • review a ClawHub skill before publishing or bumping a version
  • compare two README directions and choose the cleaner public story
  • audit release notes and social copy for leaks and audience mismatch

License

MIT No Attribution (MIT-0)

// HOW IT'S BUILT

KEY FILES

skill/publish-guard/SKILL.mdREADME.md

// REPO STATS

0 stars

// SHARE

Share on XShare on LinkedIn