CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/extension-storage-test-author

Build-an-X workflow that emits a `chrome.storage` test suite. Picks the right area (`storage.local` 10 MB / `storage.sync` 100 KB total + 8 KB per item + 512 items + 1,800 writes/hour / `storage.session` 10 MB in-memory MV3-only / `storage.managed` read-only enterprise-policy) per access pattern, then generates tests for quota-exceeded behavior (`runtime.lastError` callback path + rejected promise async path), `storage.sync` per-item + total quotas, `storage.onChanged` event payload shape, multi-area write isolation, and Firefox-Chrome divergences (Firefox `storage.sync` quotas align with Chrome per MDN; Firefox `storage.managed` available; Firefox `storage.session` MV3-only). Output: a per-extension storage test file + matrix asserting the right area was chosen. Use when an extension persists state across sessions or devices and no test proves the chosen storage area survives its quota limits.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill with a clear multi-step workflow, validation/coverage checkpoints, and a genuine one-level-deep reference file that exists and holds the promised templates. The main weakness is conciseness: quota constants and version floors are restated across multiple sections rather than referenced once.

Suggestions

State each quota constant (QUOTA_BYTES, per-item, MAX_ITEMS, version floors) exactly once in Step 2 and reference it by name elsewhere, instead of restating values in the Overview, Anti-patterns, and Limitations sections.

Consider moving the Firefox-Chrome divergence bullet list out of the Limitations section into the reference file's divergence table, keeping the body to a single pointer.

The Overview's quoted MDN/Chrome caveat sentences could be trimmed to a one-line summary with the link, since the reference file already records the detailed caveats.

DimensionReasoningScore

Conciseness

Mostly efficient and free of generic concept explanations, but the body is dense with repeated quota constants and version-floor details restated across Overview, Step 2, Anti-patterns, Limitations and the reference file, which could be tightened by stating them once.

2 / 3

Actionability

Provides executable, copy-paste-ready TypeScript specs (Step 3 core template, Step 1 grep command, decision-matrix test) plus a worked example and concrete anti-pattern fixes; templates in the reference file are complete and runnable.

3 / 3

Workflow Clarity

Five clearly sequenced steps (inventory -> decision matrix -> quota template -> author cells -> emit suite) with a CI gate checkpoint ('CI gates on every cell having at least one passing test') and an explicit coverage-manifest feedback loop.

3 / 3

Progressive Disclosure

Body is a lean overview that repeatedly signals one-level-deep references to the real references/storage-test-templates.md (verified to exist and contain the deeper templates, divergence table, and version floors), with composes-with skills clearly named.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, third-person description that pairs concrete capabilities with an explicit 'Use when' trigger clause and named sibling-skill boundaries. It is dense and technical but every clause earns its place; the only minor cost is that the density borders on over-packing for a one-line description.

DimensionReasoningScore

Specificity

Lists many concrete actions: 'Picks the right area...', 'generates tests for quota-exceeded behavior', 'storage.sync per-item + total quotas', 'storage.onChanged event payload shape', 'multi-area write isolation', and 'Firefox-Chrome divergences'.

3 / 3

Completeness

Clearly answers 'what' (emits a storage test suite + area-selection matrix) and 'when' via the explicit clause 'Use when an extension persists state across sessions or devices and no test proves the chosen storage area survives its quota limits.'

3 / 3

Trigger Term Quality

Covers natural terms users would say ('extension persists state across sessions or devices', 'storage.local/sync/session', 'quota-exceeded', 'chrome.storage') plus explicit 'Use when' guidance tied to user-facing scenarios.

3 / 3

Distinctiveness Conflict Risk

Niche is sharply scoped (chrome.storage area-selection test authoring with named sibling skills), with triggers tied to quota/persistence failures unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents