new-skill.eval

new-skill.eval is a command for Claude Code from davistroy/claude-marketplace. It costs 0 tokens per session (597 once invoked), scanned A, original, MIT.

A command that creates a new skill in the required folder structure, including a SKILL.md file with setup information called frontmatter. It also describes when the skill should be suggested and includes an example.

In plain words
What is it for?
Use it when adding a new skill to a plugin, such as a skill that summarises staged Git changes before a commit.
Why use it?
It prevents common setup mistakes, such as using the wrong filename, a flat folder, or missing required metadata. These mistakes can stop a skill from being discovered or used correctly.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it when adding a new skill to a plugin, such as a skill that summarises staged Git changes before a commit.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/davistroy/claude-marketplace/new-skill.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/davistroy/claude-marketplace

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 new-skill.eval

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/new-skill.eval/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/new-skill.eval)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/new-skill.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/new-skill.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 new-skill.eval

Your own site · 80×15
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/new-skill.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/new-skill.eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 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 $0.00000 $0.00597
Opus 5 $0.00000 $0.00298
Sonnet 5 $0.00000 $0.00119
Haiku 4.5 $0.00000 $0.00060

Measured 10d ago against content hash 9c2394cf0675, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

new-skill.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 10d 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.

evals/commands/new-skill.eval.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval: /new-skill

Purpose

Generates a new skill file with proper nested directory structure and required frontmatter. Good output: a skills/<name>/SKILL.md file with name and description in frontmatter, proactive trigger conditions, and the correct nested structure.

Fixtures

None — generates files in the plugin directory.

Test Scenarios

S1: Happy path — generate a new skill

Invocation: /new-skill (then provide name and description when prompted)

Interaction:

  • Name: diff-summary
  • Description: Summarize staged git changes before committing

Must:

  • Creates plugins/personal-plugin/skills/diff-summary/SKILL.md
  • SKILL.md has name: diff-summary in frontmatter
  • SKILL.md has description: in frontmatter
  • File is named exactly SKILL.md (uppercase)
  • Directory name matches the name field exactly

Should:

  • Includes "Proactive Triggers" section describing when Claude should suggest the skill
  • Includes allowed-tools frontmatter field
  • Includes at least one usage example

Must NOT:

  • Create skills/diff-summary.md (flat structure — skill would not be discovered)
  • Create skills/diff-summary/skill.md (wrong case — skill would not be discovered)
  • Omit name from frontmatter (skill would not be registered)

S2: Skill name provided as argument

Invocation: /new-skill audit-log

Must:

  • Creates plugins/personal-plugin/skills/audit-log/SKILL.md
  • name: audit-log in frontmatter

S3: Error — skill already exists

Invocation: /new-skill ship

Must:

  • Detects skills/ship/SKILL.md already exists
  • Prompts to confirm overwrite or aborts
  • Does not silently overwrite the existing ship skill

S4: Validate created skill

After running S1, run:

Invocation: /validate-plugin personal-plugin

Must:

  • The new diff-summary skill passes validation
  • No missing name or description errors reported

Read the full file on GitHub · 86 lines

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. 10d ago First seen · 86 lines · 0 tokens per session scan A 9c2394cf0675

Subscribe to this mod's changes

new-skill.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 597 tokens. 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 2026-08-31.