skill-creator-mingCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize a...
Install via ClawdBot CLI:
clawdbot install wm-zqbx/skill-creator-mingGrade 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
http://www.apache.org/licenses/Uses known external API (expected, informational)
googleapis.comAI Analysis
The skill definition describes legitimate skill creation workflows and shows no evidence of credential harvesting, data exfiltration, or hidden malicious instructions. The external API usage (googleapis.com) appears consistent with development tasks, and the shell command reference is for internal evaluation scripts, not active exploitation.
Audited Apr 18, 2026 · audit v1.0
Generated Oct 9, 2026
A support operations manager wants Claude to automatically classify, prioritize, and route incoming tickets using their custom taxonomy. They use the skill creator to draft the classification rules, generate labelled test tickets, and iterate on the prompts until routing accuracy stabilizes.
A legal ops lead needs Claude to pull indemnification, termination, and renewal clauses from vendor agreements in a consistent structured format. The skill creator helps define the output schema, build a test set from redacted contracts, and measure extraction recall across iterations.
An agency content director wants every brief to include target audience, tone, SEO keywords, and channel variants. They capture the workflow in a skill and use qualitative eval reviews to tune the instructions until junior writers consistently produce usable drafts.
A data platform team wants Claude to review pull-request SQL for anti-patterns, missing indexes, and dialect mismatches before human review. They benchmark with a suite of past queries and use variance analysis to confirm the skill isn't flagging good queries as errors.
A direct-to-consumer brand wants Claude to rewrite marketplace listings for clarity, keyword coverage, and compliance with each platform's rules. The skill creator helps them test on historical listings and improve the description so the skill triggers whenever listing, catalog, or product copy work comes up.
Companies deploy the skill creator to package repeated internal workflows into reusable Claude skills, reducing onboarding time and ensuring consistent output across teams. Value is measured in hours saved per employee and reduced rework.
Consultancies and freelance AI engineers use the skill creator to deliver custom skills to clients, including eval suites and performance benchmarks. They charge for discovery, build, and iteration cycles as a billable engagement.
Creators package high-performing skills, evaluation suites, and tuning recipes as paid downloads or subscription libraries. Buyers get tested, benchmarked skills without building from scratch, and sellers earn recurring or one-time revenue.
💬 Integration Tip
Start by capturing the user's existing workflow and intent before writing any skill files, and keep the description field pushy enough to counter Claude's undertriggering tendency. Add a small eval set early so iterations are grounded in measurable results rather than subjective feel.
Scored Oct 9, 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.
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.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.