Narraitor: Skill for Claude Code

.claude/skills/narraitor-validation-and-qa/SKILL.md

narraitor-validation-and-qa is a skill for Claude Code from jerseycheese/Narraitor. It costs 93 tokens per session (1,400 once invoked), scanned A, original, MIT.

A guide to choosing and interpreting tests for the Narraitor application. It explains what unit tests, Storybook, visual checks, end-to-end tests, and manual checks can each prove.

In plain words
What is it for?
Use it to choose tests for a change, interpret failures or suspiciously green results, plan quality checks, and identify gaps in release verification.
Why use it?
It prevents a passing test from being used as evidence for something that test cannot assess, such as browser rendering or the quality of generated text.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is jerseycheese/Narraitor's own configuration. It tells Claude Code how to work on Narraitor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Narraitor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jerseycheese/Narraitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jerseycheese/Narraitor/main/.claude/skills/narraitor-validation-and-qa/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jerseycheese/Narraitor

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 narraitor-validation-and-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-validation-and-qa/github.svg)](https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-validation-and-qa)
Your own site
<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-validation-and-qa"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-validation-and-qa/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 narraitor-validation-and-qa

Your own site · 80×15
<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-validation-and-qa"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-validation-and-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00093 $0.01400
Opus 5 $0.00046 $0.00700
Sonnet 5 $0.00019 $0.00280
Haiku 4.5 $0.00009 $0.00140

Measured 10d ago against content hash c408d4e4b709, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

narraitor-validation-and-qa scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Manual QA walkthrough | Human/agent plays the real app: onboarding → world + character creation → live story loop (real key) → consequences → endings → theming; smoke AI routes via curl | The product actually works, in
.claude/skills/narraitor-validation-and-qa/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validation & QA — what counts as evidence

1. Purpose

Map every verification tier to what it actually proves, so claims ride on the right tier and gaps are named instead of papered over.

2. When to use

Choosing tests for a change; interpreting failures; assessing a "tests pass" claim; planning release QA.

3. When not to use

  • Environment-level failures → narraitor-build-test-env.
  • AI output quality → narraitor-ai-quality-discipline (its matrix is the tier for generation behavior).

4. Inputs required

The change class (per change-control) and the diff.

5. Procedure — the tier table

Tier Command / surface Proves CANNOT prove
Unit/integration (Jest, jsdom) npm test — co-located src/**/__tests__, *.test.* Logic, parsing, template assembly, store actions Rendering in a real browser, hydration, visual truth, AI prose quality
Storybook npm run storybook + lint:ds-canon Design intent, isolated render states, a11y addon checks App integration, real data shapes, route/network behavior (S0/S1 on the parity ladder)
Visual regression / e2e critical (Playwright — NOTE: test:visual and test:e2e:critical are the SAME command, playwright test --project=chromium; two script names, one tier) npm run test:visual (dev server running; macOS baselines *-chromium-darwin.png, threshold 0.2 / maxDiffPixels 10k; post-hasHydrated store seeding) Pixel stability of the SEEDED states + wired flows the specs exercise Anything the seeds don't cover; correctness of behavior; live AI generation (gated off via isPlaywrightEnv()); cross-world generality
Manual QA walkthrough Human/agent plays the real app: onboarding → world + character creation → live story loop (real key) → consequences → endings → theming; smoke AI routes via curl The product actually works, including the AI loop Regression protection over time (it's a point-in-time gate)

Rules of evidence:

  1. A claim may only cite tiers that cover it. "Tests pass" (unit) says nothing about a layout bug; "visual suite green" says nothing about a prompt change (AI is gated off there).
  2. Green-but-irrelevant is a coverage gap, not evidence — check what state a baseline actually seeds before citing it.
  3. The AI play loop has NO automated tier by design. Claims about it require the manual walkthrough or the ai-quality-discipline matrix. This is the project's largest standing gap — say so rather than implying coverage.

Read the full file on GitHub · 68 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. 10d ago First seen · 68 lines · 93 tokens per session scan A c408d4e4b709

Subscribe to this mod's changes

narraitor-validation-and-qa is a skill published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 1,400 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

axiom-testing

Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest. Covers unit tests, UI tests, async testing, test architecture.

CharlesWiltgen/Axiom · 38 tokens

designing-tests

Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.

CloudAI-X/claude-workflow-v2 · 48 tokens

test-automation

Execute Vitest and Playwright test suites with result collection and failure analysis.

a5c-ai/babysitter · 0 tokens

testing-blocks

Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.

adobe/skills · 61 tokens

prd-auto-test-loop

A testing workflow driven by a product requirements document (PRD), which describes what a software version should do. It turns acceptance criteria into unit, integration, and end-to-end tests, then records the plan and results.

yunshu0909/yunshu_skillshub · 79 tokens

test-automation-expert

Comprehensive test automation specialist covering unit, integration, and E2E testing strategies. Expert in Jest, Vitest, Playwright, Cypress, pytest, and modern testing frameworks. Guides test pyramid design, coverage optimization, flaky test detection, and CI/CD integration. Activate on 'test strategy', 'unit tests'…

curiositech/some_claude_skills · 133 tokens