ai-skill-creatorAI公司 Skill 创作工作流（CTO MLOps + CISO securitystandard版）。当需要从头create新 Skill（包括初始化目录结构、编写 SKILL.md、引用文件、脚本资源、securityreview、quality gate）时使用。trigger关键词：createSkil...
Install via ClawdBot CLI:
clawdbot install johnsmithfan/ai-skill-creatorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://semver.org/lang/zh-CN/AI Analysis
The skill defines a structured workflow for creating other skills with integrated security reviews, which aligns with its stated purpose. The identified signals are related to internal tool definitions and a reference to a public, reputable website (semver.org) for documentation, not data exfiltration. There is no evidence of credential harvesting, hidden malicious instructions, or unauthorized data transmission.
Audited Apr 16, 2026 · audit v1.0
Generated May 20, 2026
A CTO at a tech corporation needs to quickly create a new AI skill for processing PDF documents. The AI Skill Creator automates the entire workflow from directory setup to security review, ensuring compliance with MLops and CISO standards. This enables the enterprise to deploy internal AI tools within hours instead of days.
A healthcare company wants to build an AI skill to analyze medical records. Using this skill creator, they adhere to strict security gates (STRIDE, CVSS) and skip no compliance steps, producing a .skill package that passes audit and can be shared with partners.
Multiple AI agents (CTO, CISO, CQO) collaborate to create, review, and publish a skill. The skill creator orchestrates tasks like create, security-review, quality-gate, and publish, ensuring each phase is approved before moving forward. This streamlines the handoff between teams.
A fintech startup needs to build a skill that handles sensitive financial data. The skill creator enforces zero-trust architecture and path traversal protection, and requires CISO-001 authorization for high-risk skills. This minimizes the risk of data breaches.
A developer wants to contribute a new skill to the ClawHub community. Using the skill creator, they follow a six-phase lifecycle including quality gates and security review. The packaged .skill artifact includes checksum and passes VirusTotal checks, ensuring community trust.
Provide the basic skill creator for free, allowing users to create simple skills. Charge a subscription for advanced features like automated security reviews, custom quality gates, and priority publishing to ClawHub.
Offer the skill creator with integrated CISO compliance as a managed service. Enterprises pay per skill created or per audit, with guaranteed adherence to security standards like STRIDE and CVSS. This appeals to regulated industries.
Host a marketplace where developers publish skills created with the tool. Take a commission on each sale or transaction. The built-in quality and security checks increase buyer confidence, attracting more users to the platform.
💬 Integration Tip
Integrate with existing agent orchestration frameworks by invoking the skill creator via sessions_send with isolated sessions. Ensure your agents have the necessary permissions (L3 for workspace, CISO-001 for security tasks) to avoid authorization errors.
Scored Jul 12, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.