ai-skill-creator-1-1-0AI公司 Skill 创作工作流（CTO MLOps + CISO 安全标准版）。当需要从头创建新 Skill（包括初始化目录结构、编写 SKILL.md、引用文件、脚本资源、安全审查、质量门禁）时使用。触发关键词：创建技能、新建 Skill、开发 Skill、创建 skill、新建技能包。整合 CTO MLOp...
Install via ClawdBot CLI:
clawdbot install johnsmithfan/ai-skill-creator-1-1-0Grade 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/Audited Apr 20, 2026 · audit v1.0
Generated May 12, 2026
A developer needs to create a new AI skill for processing PDFs. They use the ai-skill-creator to initialize the directory structure, write SKILL.md, and pass through the MLOps lifecycle stages with built-in security gates.
CISO-001 performs a mandatory security review on a skill flagged as critical risk. Using the security-review task, they scan for vulnerabilities, assess CVSS score, and either approve or reject the skill before it proceeds to quality gate.
Before publishing a skill to ClawHub, CQO-001 runs the quality-gate task to verify compliance with coding standards, documentation completeness, and test coverage. Failed checks must be resolved before packaging.
After passing all gates, a developer uses the package task to create a .skill artifact with checksum, then publishes it via the publish task to ClawHub with a changelog.
A team lead initiates a design-review task to evaluate the skill's design document stored in references/design.md. The review identifies issues such as missing security considerations or incomplete trigger definitions.
Enterprises subscribe to a catalog of pre-vetted skills that meet CISO security standards. Revenue comes from monthly or annual subscriptions.
Offer security review services for third-party skill developers. Each review incurs a fee based on risk level and scan depth.
Basic skill creation and publishing are free, but advanced features like custom security scans or priority support require payment.
💬 Integration Tip
Ensure your CI/CD pipeline invokes security-review and quality-gate tasks before any publish action to enforce compliance.
Scored Jun 25, 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.