Exec ClawHub Publish Doctor
name: exec-clawhub-publish-doctor
by bluebirdback · published 2026-03-22
$ claw add gh:bluebirdback/bluebirdback-exec-clawhub-publish-doctor---
name: exec-clawhub-publish-doctor
description: "Diagnose and mitigate exec-related tooling failures around ClawHub publishing and GitHub CLI queries (auth, browser-login, missing dependencies, pending security-scan visibility errors, wrong profile/skill URLs, and gh JSON-field mismatch errors like Unknown JSON field). Use when publishing skills to ClawHub fails, inspect reports temporary errors, or GitHub CLI search commands fail due to field schema differences."
---
# Exec 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. For GitHub search failures like `Unknown JSON field`, use:
- `scripts/gh_search_repos_safe.sh "<query>" [limit]`
5. If errors persist, classify with `references/error-map.md` before escalating.
Standard commands
Preflight
bash scripts/clawhub_preflight.shLogin (token-based, headless-safe)
clawhub login --token <clh_token>
clawhub whoamiSafe publish
bash scripts/clawhub_publish_safe.sh ./my-skill my-skill "My Skill" 1.0.0 "Initial release"Manual inspect
clawhub inspect my-skill --jsonSafe GitHub repo search (schema-aware)
bash scripts/gh_search_repos_safe.sh "safe-exec skill" 15Rules
- Skill: `https://clawhub.ai/skills/<slug>`
- Owner/slug: `https://clawhub.ai/<handle>/<slug>`
- User profile (if available): `https://clawhub.ai/users/<handle>`
Resources
More tools from the same signal band
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
Sign plugins, rotate agent credentials without losing identity, and publicly attest to plugin behavior with verifiable claims and authenticated transfers.
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...