skill-grader

skill-grader is a skill for Claude Code from curiositech/some_claude_skills. It costs 97 tokens per session (2,747 once invoked), scanned A, original, MIT.

A review framework for scoring Claude Agent Skills across ten quality areas and producing letter grades with improvement advice.

In plain words
What is it for?
Use it to assess individual skills, compare a skill library, prioritize fixes, and create quality-control reports.
Why use it?
It gives reviewers a consistent way to audit skills without relying only on personal judgment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Good fit Use it to assess individual skills, compare a skill library, prioritize fixes, and create quality-control reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curiositech/some_claude_skills/skill-grader
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.

Any agent
npx skills add curiositech/some_claude_skills --skill skill-grader
Clone the repo
git clone --depth 1 https://github.com/curiositech/some_claude_skills

Made for: Claude Code.

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 skill-grader

README.md
[![agentmods](https://agentmods.dev/badge/skills/curiositech/some_claude_skills/skill-grader/github.svg)](https://agentmods.dev/skills/curiositech/some_claude_skills/skill-grader)
Your own site
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/skill-grader"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/skill-grader/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 skill-grader

Your own site · 80×15
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/skill-grader"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/skill-grader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,747 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 180
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
  • medium Excessive Agency · line 284
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00097 $0.02747
Opus 5 $0.00048 $0.01373
Sonnet 5 $0.00019 $0.00549
Haiku 4.5 $0.00010 $0.00275

Measured 8d ago against content hash 33b421f2a0a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-grader 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 8d 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.

.claude/skills/skill-grader/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Grader

Structured evaluation rubric for Claude Agent Skills. Produces letter grades (A+ through F) on 10 axes plus an overall grade, with specific improvement recommendations for each axis.

Designed for sub-agents and non-expert reviewers who need a mechanical, repeatable process for assessing skill quality without deep domain expertise.


When to Use

Use for:

  • Auditing a single skill's quality
  • Comparing skills against each other
  • Prioritizing which skills to improve first
  • Quality control sweeps across a skill library
  • Generating improvement roadmaps

NOT for:

  • Creating new skills (use skill-architect)
  • Grading code quality or non-skill documents
  • Evaluating agent performance (different from skill quality)

Grading Process

flowchart TD
  A[Read SKILL.md + all files] --> B[Score each of 10 axes]
  B --> C[Assign letter grade per axis]
  C --> D[Compute overall grade]
  D --> E[Write improvement recommendations]
  E --> F[Produce grading report]

Step-by-Step

  1. Read the entire skill folder — SKILL.md, all references, scripts, CHANGELOG, README
  2. Score each axis — Use the rubric below (0-100 per axis)
  3. Convert to letter grade — See grade scale
  4. Compute overall grade — Weighted average (Description and Scope are 2x weight)
  5. Write 1-3 specific improvements per axis scoring below B+
  6. Produce the grading report in the output format below

The 10 Evaluation Axes

Axis 1: Description Quality (Weight: 2x)

Does the description follow [What] [When] [Keywords]. NOT for [Exclusions]?

Grade Criteria
A Specific verb+noun, domain keywords users would type, 2-5 explicit NOT exclusions, 25-50 words
B Has keywords and NOT clause, but slightly vague or missing synonym coverage
C Too generic, missing NOT clause, or >100 words of process detail
D Single vague sentence ("helps with X") or name/description mismatch
F Missing or empty description

Read the full file on GitHub · 294 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 294 lines · 97 tokens per session scan A 33b421f2a0a0

Subscribe to this mod's changes

skill-grader is a skill published in the GitHub repository curiositech/some_claude_skills (221 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 2,747 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens