How do I install the Clawhub Publish Doctor skill?

Run npx skillmds@latest add modbender/clawhub-publish-doctor in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Clawhub Publish Doctor safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Clawhub Publish Doctor?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Clawhub Publish Doctor free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Clawhub Publish Doctor?

modbender (@modbender) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Clawhub Publish Doctor by modbender

Name: Clawhub Publish Doctor
Rating: 4.666666666666667 (3 reviews)
Author: modbender

Clawhub Publish Doctor

Diagnose and mitigate ClawHub/ClawDHUB publish failures (auth, browser-login, missing dependencies, pending security-scan visibility errors, and wrong profile/skill URLs). Use when publishing skills to ClawHub fails, inspect reports temporary errors, or you need a safer publish+verify workflow with retries.

modbender Updated Sep 9, 2026 12 repo stars

File contents

ClawHub Publish Doctor

Stabilize ClawHub publishing with preflight checks, safer publish commands, and post-publish verification that tolerates temporary registry states.

Quick workflow

Run preflight checks:
- scripts/clawhub_preflight.sh
If login/browser issues appear, follow references/error-map.md.
Publish with retry-aware verification:
- scripts/clawhub_publish_safe.sh <skill_path> <slug> <name> <version> [changelog]
If inspect still fails, classify the error with references/error-map.md before escalating.

Standard commands

Preflight

bash scripts/clawhub_preflight.sh

Login (token-based, headless-safe)

clawhub login --token <clh_token>
clawhub whoami

Safe publish

bash scripts/clawhub_publish_safe.sh ./my-skill my-skill "My Skill" 1.0.0 "Initial release"

Manual inspect

clawhub inspect my-skill --json

Rules

Prefer token login in server/headless environments.
Treat inspect errors right after publish as potentially transient for a few minutes.
Verify with both CLI (clawhub inspect) and web URL (/skills/<slug>).
Use canonical URLs:
- Skill: https://clawhub.ai/skills/<slug>
- Owner/slug: https://clawhub.ai/<handle>/<slug>
- User profile (if available): https://clawhub.ai/users/<handle>

Resources

references/error-map.md: quick diagnosis for common failure signatures.
scripts/clawhub_preflight.sh: dependency + environment checks.
scripts/clawhub_publish_safe.sh: publish + retry verification wrapper.

---name: clawhub-publish-doctordescription: Diagnose and mitigate ClawHub/ClawDHUB publish failures (auth, browser-login, missing dependencies, pending security-scan visibility errors, and wrong profile/skill URLs). Use when publishing skills to ClawHub fails, inspect reports temporary errors, or you need a safer publish+verify workflow with retries.--- # ClawHub Publish Doctor Stabilize ClawHub publishing with preflight checks, safer publish commands, and post-publish verification that tolerates temporary registry states. ## Quick workflow 1. Run preflight checks: - `scripts/clawhub_preflight.sh` 2. If login/browser issues appear, follow `references/error-map.md`. 3. Publish with retry-aware verification: - `scripts/clawhub_publish_safe.sh <skill_path> <slug> <name> <version> [changelog]` 4. If inspect still fails, classify the error with `references/error-map.md` before escalating. ## Standard commands ### Preflight ```bash bash scripts/clawhub_preflight.sh ``` ### Login (token-based, headless-safe) ```bash clawhub login --token <clh_token> clawhub whoami ``` ### Safe publish ```bash bash scripts/clawhub_publish_safe.sh ./my-skill my-skill "My Skill" 1.0.0 "Initial release" ``` ### Manual inspect ```bash clawhub inspect my-skill --json ``` ## Rules - Prefer token login in server/headless environments. - Treat `inspect` errors right after publish as potentially transient for a few minutes. - Verify with both CLI (`clawhub inspect`) and web URL (`/skills/<slug>`). - Use canonical URLs: - Skill: `https://clawhub.ai/skills/<slug>` - Owner/slug: `https://clawhub.ai/<handle>/<slug>` - User profile (if available): `https://clawhub.ai/users/<handle>` ## Resources - `references/error-map.md`: quick diagnosis for common failure signatures. - `scripts/clawhub_preflight.sh`: dependency + environment checks. - `scripts/clawhub_publish_safe.sh`: publish + retry verification wrapper.

Frequently asked questions