A validator for SKILL.md files, the instruction files used by coding-agent skills. It can check file structure, test behavior against example prompts, or audit the entire skill library for missing and outdated references.

Use it to lint one skill, test a skill against fixtures, or review all skills for reference and coverage problems. It writes a Markdown report for the results.

It catches structural problems, incorrect behavior, and library-wide drift before skill changes are published or merged. Different modes let you choose a quick check or a broader review.

skill-test — Skill for Claude Code by cenconq25

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 cenconq25/claude-code-app-studio --skill skill-test

Clone the repo

git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/skill-test/github.svg)](https://agentmods.dev/skills/cenconq25/claude-code-app-studio/skill-test)

Your own site

<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/skill-test"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/skill-test/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/skill-test"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/skill-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,160 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.02160
Opus 5	$0.00020	$0.01080
Sonnet 5	$0.00008	$0.00432
Haiku 4.5	$0.00004	$0.00216

Measured 6d ago against content hash 85652b549b89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skill-test 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 6d 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-test/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Test

The canonical validator for the project's skill library. Owned by the template, used by /skill-improve (which calls --mode static), by CI sanity hooks, and by maintainers auditing drift after a refactor.

Three modes, escalating cost:

static — pure structural lint. Fast, deterministic. The default.
spec — runs the skill against a fixture prompt set in tests/skills/<skill-id>/ and checks the response shape.
audit — library-wide coverage report: which agents are referenced by which skills, dead refs, ghost entries, tier drift.

Output is always a markdown report appended to production/skill-test-report.md.

Purpose / When to Run

Run before:

Publishing a new skill (--mode static).
Merging a PR that touches .claude/skills/ (--mode static --all).
A release-readiness gate (--mode audit).
Investigating "why does this skill misbehave" (--mode spec).

Skip when:

Editing only prose inside a skill that already passes static (the lint is unchanged).
The change is a one-line typo fix.

Inputs

A skill id (resolves to .claude/skills/<id>/SKILL.md), or
--all to iterate every skill, or
--mode <static|spec|audit> to pick the mode (defaults to static).

For spec mode, fixtures live at tests/skills/<skill-id>/cases/<case-name>.md with two sections: ## Input and ## Expected.

For audit mode, the agent roster lives under .claude/agents/.

Outputs

A printed verdict per skill: PASS, WARN, FAIL.
A structured report block appended to production/skill-test-report.md with timestamp.
For --mode audit, a coverage table mapping skills → agents and agents → skills, with ghost / dead entries flagged.

Mode A: Static Lint

The canonical structural rule set. This is what every skill MUST pass.

Frontmatter rules

YAML frontmatter delimited by --- at file start.
name: value matches the parent directory name exactly.
description: is one sentence, ≤ 240 characters, begins with the action and ends with when to use.
argument-hint: present using [arg | --flag value] shape.
user-invocable: is literal true or false.
allowed-tools: lists every tool referenced in the body. No Write if the body never writes; no missing tool either.
model: matches the tier policy in coordination-rules.md:
- Read-only/format-only → haiku.
- Multi-doc synthesis with high-stakes verdicts → opus (only the handful listed in coordination-rules.md).
- Otherwise → sonnet or absent.
agent: if present matches a real file under .claude/agents/.

Read the full file on GitHub · 272 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.

6d ago First seen · 272 lines · 40 tokens per session scan A 85652b549b89

Subscribe to this mod's changes

skill-test is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 2,160 once invoked, about $0.0002 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.

Building agents Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

skill-test