skills-eval

skills-eval is a command for Claude Code from athola/claude-night-market. It costs 24 tokens per session (371 once invoked), scanned A, original, MIT.

A command that reviews Claude Skills for quality, required metadata, efficient use of text, and reliable activation. It can inspect all discovered skills or one named skill.

In plain words
What is it for?
Use it to audit a skill collection, examine one skill in detail, check compliance, and produce improvement recommendations.
Why use it?
It identifies standards violations and improvement opportunities before skills are relied on by developers or agents.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the abstract plugin — 16 skills, 17 commands, 5 agents, 4 hooks shipped together

Good fit Use it to audit a skill collection, examine one skill in detail, check compliance, and produce improvement recommendations.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/athola/claude-night-market/skills-eval
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market

Made for: Claude Code.

Or install abstract, the plugin that ships this one along with the rest of its 16 skills, 17 commands, 5 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skills-eval

README.md
[![agentmods](https://agentmods.dev/badge/commands/athola/claude-night-market/skills-eval/github.svg)](https://agentmods.dev/commands/athola/claude-night-market/skills-eval)
Your own site
<a href="https://agentmods.dev/commands/athola/claude-night-market/skills-eval"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/skills-eval/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skills-eval

Your own site · 80×15
<a href="https://agentmods.dev/commands/athola/claude-night-market/skills-eval"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/skills-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00371
Opus 5 $0.00012 $0.00186
Sonnet 5 $0.00005 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 12d ago against content hash 3c7bbbb93efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skills-eval scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/abstract/commands/skills-eval.md · 62 lines

What it actually says

Skills Evaluation Command

Invoke Skill(abstract:skills-eval), which carries the evaluation criteria, the workflow and the output format across its modules.

When To Use

Use this command when you need to:

  • Auditing skill ecosystem quality
  • Discovering implementation patterns
  • Planning skill improvements
  • Checking compliance with standards
  • Generating improvement recommendations

When NOT To Use

Avoid this command if:

  • Evaluating hooks - use /hooks-eval instead
  • Validating plugin structure - use /validate-plugin instead
  • Creating new skills - use /create-skill instead

Usage

Evaluates all Claude Skills in your ~/.claude/ ecosystem for quality, compliance, and potential improvements.

Basic Usage

/prompt:skills-eval

Evaluates all discovered skills and generates improvement recommendations.

Specific Skill Evaluation

/prompt:skills-eval <skill-name>

Evaluates a specific skill (e.g., /prompt:skills-eval modular-skills).

Examples

/prompt:skills-eval
# Evaluates all 50+ skills, identifies 5 critical issues and 20+ improvements

/prompt:skills-eval modular-skills
# Deep dive on specific skill with detailed improvement plan

Integration with Tools

This command uses the skills-eval skill's specialized tools:

  • skills-auditor: Quality analysis
  • improvement-suggester: Actionable recommendation generation
  • compliance-checker: Standards and security validation

This evaluation validates an efficient skills ecosystem that follows Claude Skills best practices.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 62 lines · 24 tokens per session scan A 3c7bbbb93efe

Subscribe to this mod's changes

skills-eval is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 371 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.