skill-package-doctorAudit Claude, Codex, OpenClaw, and ClawHub skill packages before publishing; produce concrete fix lists, trust scores, and shareable proof cards.
Install via ClawdBot CLI:
clawdbot install zack-dev-cm/skill-package-doctorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.getgeofix.xyz/Audited May 24, 2026 · audit v1.0
Generated Jul 29, 2026
A developer has built a skill package for Claude or OpenClaw and wants to publish it on ClawHub. The Skill Package Doctor audits the package, checks SKILL.md for completeness, runs validation scripts, and outputs a trust score and fix list, ensuring the package meets marketplace standards before submission.
A skill author auto-generated a SKILL.md but suspects it may be generic or unsafe. The doctor reviews the content for vague instructions, missing frontmatter, or security risks like secret exposure, and provides specific edits to make it publish-ready.
An agent marketplace wants to display a trust score for each skill package. The doctor produces a score out of 100 and generates a proof card (SVG) that shows validation results, helping buyers gauge reliability.
A team inherited a skill with bloated scripts and unclear instructions. The doctor identifies unnecessary complexity, suggests small edits to preserve intent, and recommends bundling only essential files, improving maintainability.
An open-source contributor wants to submit a skill package to ClawHub. The doctor enforces rules like requiring frontmatter, avoiding dangerous commands, and validating test commands, ensuring the contribution meets community standards.
Offer a free basic audit (score and errors) and a paid premium version that includes automated fix patches and priority support. Revenue comes from subscription tiers for individual developers and teams.
Integrate with ClawHub, Codex, or other agent skill marketplaces as a mandatory pre-publish step. Charge a small fee per audit or take a percentage of the publishing fee, reducing risk for the marketplace.
Provide a cloud-based API that development teams integrate into their CI/CD pipelines. Automated audits run on every pull request, ensuring skill quality before deployment. Revenue from usage-based pricing or monthly plans.
💬 Integration Tip
Integrate the doctor as a pre-commit hook or CI step using the included Python script to automate auditing. For marketplaces, call the doctor via API before finalizing a listing to ensure only validated packages are published.
Scored Jul 29, 2026
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in o...
Transcribe YouTube videos to text by extracting captions and subtitles directly from the video URL using yt-dlp without audio processing.
Manage a self-hosted Trello-like board via `wekancli`. Create, move and archive cards, lists and boards on a WeKan server. Use when user asks about task boar...
Proactive security monitoring, threat scanning, and auto-remediation for OpenClaw deployments