← Back to Skills Marketplace
bluebirdback

Exec ClawHub Publish Doctor

by BlueBirdBack ✨ · GitHub ↗ · v1.0.1
cross-platform ✓ Security Clean
597
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install 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 secu...
README (SKILL.md)

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 \x3Cskill_path> \x3Cslug> \x3Cname> \x3Cversion> [changelog]
  4. For GitHub search failures like Unknown JSON field, use:
    • scripts/gh_search_repos_safe.sh "\x3Cquery>" [limit]
  5. If errors persist, classify with references/error-map.md before escalating.

Standard commands

Preflight

bash scripts/clawhub_preflight.sh

Login (token-based, headless-safe)

clawhub login --token \x3Cclh_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

Safe GitHub repo search (schema-aware)

bash scripts/gh_search_repos_safe.sh "safe-exec skill" 15

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/\x3Cslug>).
  • For gh search repos --json failures, prefer fullName over unsupported aliases like nameWithOwner, or run scripts/gh_search_repos_safe.sh.
  • Use canonical URLs:
    • Skill: https://clawhub.ai/skills/\x3Cslug>
    • Owner/slug: https://clawhub.ai/\x3Chandle>/\x3Cslug>
    • User profile (if available): https://clawhub.ai/users/\x3Chandle>

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.
  • scripts/gh_search_repos_safe.sh: resilient gh search repos wrapper with JSON-field mismatch fallback.
Usage Guidance
This skill is a convenience wrapper around your existing clawhub and GitHub CLI tooling. Before using: (1) inspect the three included scripts yourself (they are small shell scripts) and confirm you intend to run clawhub publish; (2) run in a safe environment (e.g., your development machine) — the scripts write transient files to /tmp and will call your installed clawhub/gh CLIs which in turn contact remote services; (3) do not paste tokens into an untrusted UI—use the recommended headless token login and ensure tokens have minimum necessary scopes; (4) ensure the clawhub and gh binaries you have installed are the official ones (npm/global installs can be tampered with on compromised hosts). Other than those operational cautions, the skill's behavior matches its stated purpose.
Capability Analysis
Type: OpenClaw Skill Name: exec-clawhub-publish-doctor Version: 1.0.1 The skill bundle provides diagnostic and utility scripts for OpenClaw publishing and GitHub CLI interactions. All scripts (`clawhub_preflight.sh`, `clawhub_publish_safe.sh`, `gh_search_repos_safe.sh`) align with the stated purpose, primarily interacting with `clawhub` and `gh` CLI tools. There is no evidence of data exfiltration, persistence mechanisms, obfuscation, or malicious prompt injection attempts in SKILL.md. The scripts properly quote arguments when calling sub-commands, mitigating shell injection risks within the scripts themselves. The use of `/tmp` for temporary files and network calls via `clawhub`/`gh` are expected for the skill's functionality.
Capability Assessment
✓ Purpose & Capability
Name/description match the included artifacts: the SKILL.md plus three shell scripts implement preflight checks, a publish wrapper with retries, and a resilient gh search wrapper. All required actions (calling clawhub and gh CLIs) are appropriate for the described purpose.
✓ Instruction Scope
Runtime instructions are limited to running the provided shell scripts and invoking clawhub/gh/inspect commands. The scripts only inspect environment/binaries, run CLI commands, parse outputs, and use /tmp for transient command output. They do not read arbitrary user files, send data to third-party endpoints other than those the CLIs contact, or include open-ended instructions like 'gather whatever context you need.'
✓ Install Mechanism
No install spec is provided (instruction-only with bundled scripts), so nothing is downloaded or written beyond the included files. This is low risk compared with downloading remote archives or running an installer.
✓ Credentials
The skill requires no declared environment variables or credentials. It instructs users to authenticate to clawhub/gh with their usual tokens (expected for this workflow). The only optional override is GH_FIELDS for gh_search_repos_safe.sh. There are no unrelated or excessive credential requests.
✓ Persistence & Privilege
Skill is not forced-always and does not request persistent privileges or modify other skills or system-wide agent settings. It runs only when invoked and relies on the user-installed clawhub/gh CLIs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install exec-clawhub-publish-doctor
  3. After installation, invoke the skill by name or use /exec-clawhub-publish-doctor
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Fix gh search JSON field mismatch (nameWithOwner) with safe fallback wrapper
v1.0.0
Initial public release
Metadata
Slug exec-clawhub-publish-doctor
Version 1.0.1
License —
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is Exec ClawHub Publish Doctor?

Diagnose and mitigate exec-related tooling failures around ClawHub publishing and GitHub CLI queries (auth, browser-login, missing dependencies, pending secu... It is an AI Agent Skill for Claude Code / OpenClaw, with 597 downloads so far.

How do I install Exec ClawHub Publish Doctor?

Run "/install exec-clawhub-publish-doctor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Exec ClawHub Publish Doctor free?

Yes, Exec ClawHub Publish Doctor is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Exec ClawHub Publish Doctor support?

Exec ClawHub Publish Doctor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Exec ClawHub Publish Doctor?

It is built and maintained by BlueBirdBack ✨ (@bluebirdback); the current version is v1.0.1.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463942 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259883 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200739 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191401 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190375 · by oswalpalash

💬 Comments