← Back to Skills Marketplace
yang1002378395-cmyk

Skill Creator

by yang1002378395-cmyk · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
129
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install skill-creator-cn
Description
Create 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...
Usage Guidance
This skill is coherent for building and evaluating skills and includes useful scripts to run local evals and generate a self-contained review page. Before running anything or pointing the tool at a workspace: 1) inspect the workspace directory — the viewer will read and embed any file it finds (so remove or move sensitive files first); 2) be aware generate_review.py tries to free a port by finding and SIGTERM-ing processes (avoid running it on machines hosting important services); 3) run the scripts in an isolated environment or VM if you are unsure about the workspace contents; 4) on Windows or systems without lsof the port-kill code may behave differently — review/modify the script if needed; 5) if you plan to allow the agent to run the skill autonomously, limit access to workspaces that don't contain credentials or private data. If you want, I can point out the exact lines in the scripts that perform port-killing, file embedding, and HTTP serving so you can review or modify them before execution.
Capability Analysis
Type: OpenClaw Skill Name: skill-creator-cn Version: 1.0.0 The skill-creator-cn bundle is a comprehensive developer toolset designed to automate the creation, evaluation, and optimization of OpenClaw skills. It includes Python scripts for running parallel test cases via the Claude CLI (run_eval.py), aggregating performance metrics (aggregate_benchmark.py), and serving a local HTML-based review interface (generate_review.py). The bundle follows a well-documented iterative workflow and includes safety instructions in SKILL.md explicitly forbidding the creation of malicious or misleading skills. No evidence of data exfiltration, unauthorized persistence, or malicious code execution was found; all behaviors, including local port management and temporary file creation in .claude/commands/, are consistent with its stated purpose as a development utility.
Capability Assessment
Purpose & Capability
The name/description (create/modify/evaluate skills) align with the included artifacts: SKILL.md, evaluator agents (analyzer/comparator/grader), and multiple scripts (run_eval, run_loop, generate_review, package_skill, etc.). There are no unrelated environment variables, external credentials, or surprising binaries required.
Instruction Scope
The SKILL.md instructs the agent to run the bundled evaluation scripts (e.g., eval-viewer/generate_review.py) and to read skill files, transcripts, and workspace outputs to produce analyses and HTML review pages. This is expected for an eval/skill-authoring tool, but those scripts will read arbitrary files in the provided workspace and embed them into a served HTML page — so confidential files in the workspace could be exposed if you run the viewer without checking contents.
Install Mechanism
No install spec; the skill is instruction-first and ships Python scripts. No network downloads or archives are fetched during install. The code uses only standard-library Python modules and bundled files.
Credentials
The package declares no required environment variables, credentials, or config paths. The scripts access the local workspace and rely on standard tools (e.g., lsof if present) but do not request unrelated secrets or cloud credentials.
Persistence & Privilege
always:false and no persistent system-wide changes are requested. However, generate_review.py contains logic to locate and SIGTERM processes listening on a port (via lsof + os.kill) to free the port for its local HTTP server — this can terminate other local services and is somewhat intrusive. The script also serves workspace files over HTTP and auto-saves feedback.json in the workspace.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install skill-creator-cn
  3. After installation, invoke the skill by name or use /skill-creator-cn
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Skill Creator 1.0.0 – Initial Release - Introduces a comprehensive workflow for creating, improving, and evaluating skills from scratch or by editing existing ones. - Supports intent capture, user interviews, iterative drafting, evaluation with quantitative and qualitative benchmarks, and description optimization. - Provides detailed guidance on SKILL.md structure, best practices, and output formatting. - Offers adaptable communication strategies for users of varying technical backgrounds. - Emphasizes safety, clarity, and progressive skill-building techniques.
Metadata
Slug skill-creator-cn
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Skill Creator?

Create 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... It is an AI Agent Skill for Claude Code / OpenClaw, with 129 downloads so far.

How do I install Skill Creator?

Run "/install skill-creator-cn" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Skill Creator free?

Yes, Skill Creator is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Skill Creator support?

Skill Creator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Skill Creator?

It is built and maintained by yang1002378395-cmyk (@yang1002378395-cmyk); the current version is v1.0.0.

💬 Comments