Coding

skill-publish

Publish SKILL.md files to ClawHub (clawhub.ai) and diagnose publish failures across the three skill repos (history, ai-custom-skills, ai-thoughts). Use when the user wants to publish skills to ClawHub, manually trigger a publish, check why a publish failed or was skipped, or understand the ClawHub skill sync pipeline.

What it does

The skill document

Publish Skills Safely

Transform any knowledge into a publishable skill. Sanitize personal data, format correctly, verify before publishing.

Key principle: Never modify user's original files. Create clean publish-ready version separately.

References:

sanitize.md — Security checklist and personal data removal
transform.md — Convert any format to proper skill structure
verify.md — Pre-publish verification process

When to Use

User wants to publish existing skill/instructions to ClawHub
User wants to share knowledge they've developed locally
User has content in any format that should become a public skill

The Process

Understand — What knowledge/skill exists? Where is it?
Transform — Convert to proper skill format (see transform.md)
Sanitize — Remove personal/dangerous content (see sanitize.md)
Verify — Confirm with user before publishing (see verify.md)
Publish — Only after explicit approval

Critical Rules

⚠️ Never modify original files — Create separate publish version ⚠️ Never publish without sanitization — Check sanitize.md ⚠️ Never publish without user approval — Always verify first ⚠️ When in doubt, include more — User can remove, harder to add later

Asking the User

Before transforming, clarify:

What should be PUBLIC vs kept private?
Any specific names/references to remove?
Target audience (beginners, experts, specific domain)?
Desired slug/name for ClawHub?

Always run sanitize.md checklist before any publish.

Related skills

clawsec-clawhub-checker

ClawHub reputation checker for clawsec-suite. Adds a standalone reputation gate before guarded skill installation.

34 installs

skill-kit

Claude Code skill management. Topics — writer (create), lint (validate + fix frontmatter), merge (combine related), dedup (find duplicates), convert (agent → skill), architecture (multi-topic structure), upgrade (enhance + add topics), route (topic placement), trigger (declare + auto-register hooks), find (discover via npx skills CLI), graph (extract depends-on + topic body Skill calls into Edge Table + Mermaid + dispatched d3 force-directed render), language (per-skill language consistency enforcement), portability (public skill cross-ref + vendor isolation), publish-scope (published skill scope review before extending), invoke-discipline (slash command → Skill tool call, multi-topic Read, post-decision auto-invoke, interactive script, vendor dispatch). Use when: "skill writer", "skill lint", "skill merge", "skill dedup", "create skill", "frontmatter fix", "multi-topic skill", "convert agent", "skill upgrade", "add topic", "topic route", "trigger compile", "hook auto register", "find

24 installs

skill-trust-auditor

Audit a named ClawHub skill or skill URL before installation by combining OpenClaw verification with bounded static analysis. Use when the user explicitly asks whether a skill is safe or requests a pre-install review; report evidence and uncertainty instead of treating a score as proof.

39 installs