← Back to Skills Marketplace
110
Downloads
0
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install nm-abstract-skills-eval
Description
Evaluate and improve Claude skill quality through auditing
Usage Guidance
This is a documentation-first auditing skill (no code files included) that describes many scripts and command-line tools but does not bundle them. Before installing or running it: 1) verify you have the referenced claude-night-market repository or the Claude Code plugin that provides the scripts; 2) inspect any external scripts (scripts/, integration-tester, compliance-checker, etc.) before running — examples use subprocess execution which can run arbitrary binaries; 3) check the Night Market config paths (night-market.modular-skills, night-market.performance-optimization) to ensure they don't expose unrelated secrets; and 4) if you enable autonomous agent invocation, be cautious — an agent following these docs could execute local tools or run commands if those tools are present. If you need certainty, ask the maintainer for the associated scripts or a full package that includes the executable tooling before proceeding.
Capability Assessment
Purpose & Capability
Name/description (skills evaluation and improvement) align with the contents: the SKILL.md and modules are focused on auditing, scoring, and optimizing skills. The declared required config paths (night-market.modular-skills, night-market.performance-optimization) are consistent with a Night Market integration.
Instruction Scope
SKILL.md repeatedly instructs running CLI commands and Python scripts (make, skill_analyzer.py, token_estimator.py, scripts/*, integration-tester, etc.) and shows example code that reads skill files and runs subprocesses. However, this skill bundle contains only markdown modules (no scripts or executables). That mismatch means the runtime instructions expect tools/resources that are not delivered here; running such examples would execute subprocesses and could run arbitrary binaries if present on the host.
Install Mechanism
No install spec (instruction-only) which reduces installation risk. However the content references a scripts/ directory and CLI tools that are not present in the provided manifest — users should confirm those scripts exist in the upstream repo before executing any commands.
Credentials
The skill declares no environment variables, no credentials, and does not request system-wide secrets. The only external requirements are specific configuration paths for Night Market; ensure those config keys do not contain unrelated secrets before granting the skill access to them.
Persistence & Privilege
always:false and default invocation behavior. The skill does not request permanent/privileged presence and does not appear to modify other skills' configurations in its docs. If you allow autonomous invocation, standard platform cautions apply but there is no additional privilege requested here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install nm-abstract-skills-eval - After installation, invoke the skill by name or use
/nm-abstract-skills-eval - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.8.3
Release v1.8.3
v1.8.2
Release v1.8.2
vv1.8.2
Release v1.8.2
Metadata
Frequently Asked Questions
What is Nm Abstract Skills Eval?
Evaluate and improve Claude skill quality through auditing. It is an AI Agent Skill for Claude Code / OpenClaw, with 110 downloads so far.
How do I install Nm Abstract Skills Eval?
Run "/install nm-abstract-skills-eval" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Nm Abstract Skills Eval free?
Yes, Nm Abstract Skills Eval is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Nm Abstract Skills Eval support?
Nm Abstract Skills Eval is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Nm Abstract Skills Eval?
It is built and maintained by athola (@athola); the current version is v1.8.3.
More Skills