skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize...

This package largely does what it says — it helps author and evaluate skills — but it omits a few important operational details. Before installing or running anything: 1) Review the code yourself (especially scripts that write files or call subprocesses). 2) Expect to need Python dependencies (anthropic, pyyaml, etc.) and a local 'claude' CLI; don't run arbitrary pip installs without checking package sources. 3) Do not supply API keys (Anthropic or others) to this skill unless you trust the code and intend it to call remote models; the code will call external model APIs which will transmit prompt/eval data. 4) Run in an isolated environment (container/VM) or a project workspace where writing to .claude/commands and creating zip files is safe. 5) If you want to proceed, add explicit metadata: required binaries and env vars (e.g., ANTHROPIC_API_KEY, presence of 'claude' CLI) and/or modify scripts to surface prompts before network calls. These steps will reduce unexpected behavior and data exposure.

Type: OpenClaw Skill Name: skill-creator-latest Version: 2.0.0 The bundle is a comprehensive developer toolset designed to facilitate the creation, testing, and optimization of other OpenClaw skills. It contains scripts for running evaluations via the Claude CLI (run_eval.py), aggregating performance metrics (aggregate_benchmark.py), and generating local HTML reports (generate_report.py). A local HTTP server is implemented in generate_review.py to allow users to review test results and provide feedback. While the bundle performs high-privilege actions such as executing subprocesses and managing local files/ports, these behaviors are strictly aligned with its stated purpose as a meta-development tool. No evidence of data exfiltration, malicious prompt injection, or unauthorized persistence was found.