← Back to Skills Marketplace
119
Downloads
0
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install plugineval
Description
PluginEval Quality Evaluation with enhanced UI. Wraps plugineval-core with vetting and reporting features. Requires plugineval-core.
Usage Guidance
This skill is an instruction-only wrapper that delegates to external scripts and a separate plugineval-core. Before installing or running it: 1) Clarify the version mismatch (_meta.json v1.3.0 vs SKILL.md/registry v2.0.0). 2) Do not blindly run or copy scripts from the linked GitHub repo — inspect the vet.sh, clawdefender.sh, and other scripts for unexpected network calls, credential access, or privileged operations. 3) Prefer a pinned release or commit rather than cloning main; avoid running as root. 4) If you will allow automated agents to invoke this skill, understand they may execute the external scripts under ~/.openclaw and could change PATH. 5) Verify that plugineval-core (the required dependency) is present and from a trusted source, or request that the skill bundle its runtime or provide an explicit, auditable install specification. If you want to proceed confidently, ask the publisher to (a) fix the version metadata, (b) include or pin the evaluation scripts in the skill bundle, or (c) provide a vetted install script and signed release.
Capability Analysis
Type: OpenClaw Skill
Name: plugineval
Version: 2.0.0
The bundle consists of metadata and documentation for a skill designed to perform security and quality vetting of other skills. It acts as a wrapper for external scripts and the 'plugineval-core' dependency, emphasizing local execution via Ollama for privacy. No functional code is included in this specific bundle, and the instructions in SKILL.md and EXTERNAL.md are consistent with its stated purpose of auditing and reporting.
Capability Assessment
Purpose & Capability
The name/description (PluginEval wrapper around plugineval-core) match the instructions which call evaluation and vetting scripts. However the skill declares a required dependency (plugineval-core) but provides no bundled implementation — it delegates behavior to external scripts and a separate skill. Also _meta.json reports v1.3.0 while SKILL.md and registry metadata reference v2.0.0, an inconsistency that should be clarified.
Instruction Scope
The runtime instructions tell users/agents to run scripts located under ~/.openclaw (e.g., ~/.openclaw/skills/plugineval/scripts/vet.sh) or to clone and copy scripts from the GitHub repo into their PATH. Those instructions implicitly require writing and executing arbitrary shell scripts from an external repo and reading from the user's home workspace. That expands scope beyond an instruction-only wrapper and could lead to executing unreviewed code unless the scripts are inspected first.
Install Mechanism
There is no formal install spec. Instead the docs instruct cloning a GitHub repo and copying scripts to PATH or relying on a separate Nova workspace setup. Relying on an out-of-band repository to obtain executable scripts is higher risk than a self-contained, pinned install; executing those scripts without review could run arbitrary code.
Credentials
The skill does not request any environment variables, credentials, or config paths in the registry metadata. That is proportionate to a local evaluation utility. Note: instructions implicitly access files under ~/.openclaw and require presence of local tools (Python, Ollama) but do not ask for secrets.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent system-wide privileges in metadata. However its instructions encourage copying scripts into PATH (a persistent change) and depending on external workspace tooling, so installation may create persistent executables outside the skill bundle.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install plugineval - After installation, invoke the skill by name or use
/plugineval - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
Version 2.0.0: Now wraps plugineval-core. Adds combined security + quality vetting workflow. Gold badge quality.
v1.2.0
**v1.2.0 Summary:**
Adds explicit read-only default mode and new safeguards for file modification.
- Now defaults to read-only mode; file changes require `--allow-write` flag.
- Auto-fix commands only modify files when explicitly enabled, never by default.
- Only `SKILL.md` can be changed, and a backup is always created before edits (max 3 backups per skill).
- Documentation updated to reflect stricter security controls and usage safeguards.
v1.1.0
Auto-Fix feature added for common anti-patterns.
- Added Auto-Fix (Layer 3) for anti-patterns with `--auto-fix`
- Supports dry-run mode (`--dry-run`) and partitions safe vs. unsafe fixes (`--unsafe`)
- Automatic backup before any fix is applied
- Documentation updated to describe new options and workflows
v1.0.1
- Added a changelog section to SKILL.md.
- Removed the "Automatic Quality Check" automation details to improve general usability.
- Simplified and cleaned up documentation for clarity.
v1.0.0
Initial release of plugineval: a skill quality evaluation tool for AI agent skills.
- Measures skill quality across 6 weighted dimensions (frontmatter, orchestration, disclosure, completeness, efficiency, coherence)
- Detects common skill anti-patterns and applies penalties
- Assigns quality badges (Platinum/Gold/Silver/Bronze/Needs Improvement) based on score
- Provides quick-start commands for evaluation, anti-pattern detection, and combined workflows
- Designed for pre-install, post-install, and pre-publish quality checks
- Integrates with security vetting and automated weekly quality reports
Metadata
Frequently Asked Questions
What is PluginEval?
PluginEval Quality Evaluation with enhanced UI. Wraps plugineval-core with vetting and reporting features. Requires plugineval-core. It is an AI Agent Skill for Claude Code / OpenClaw, with 119 downloads so far.
How do I install PluginEval?
Run "/install plugineval" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is PluginEval free?
Yes, PluginEval is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does PluginEval support?
PluginEval is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created PluginEval?
It is built and maintained by Donmeusi (@donmeusi); the current version is v2.0.0.
More Skills