CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

export-persistence-local-first

Review Excalidraw export, persistence, and local-only feature changes for data loss, round-trip, escaping, quota, and boundary regressions. Use as one lens in a code review run.

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

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

The body is a lean, well-structured review lens that respects the reader's intelligence: dense directive prose, a clear trace-first method with explicit failure scenarios to probe, precise report/don't-report thresholds, and a defined reporting format. The only improvement space is adding a worked example of a finding to make the reporting expectations fully concrete.

DimensionReasoningScore

Conciseness

Every section is dense, directive content with no padding and no explanations of concepts Claude already knows — e.g. "Follow data from user input through serialization, storage or file APIs, reload/import, and UI messaging" packs the entire trace path into one line. This matches the anchor-5 "lean and efficient; every token earns its place"; there is no unnecessary explanation to trim.

5 / 5

Actionability

The guidance is concrete and executable for a review skill: a specific trace path, named failure scenarios ("the browser denies file access, storage is full or corrupt, or a scene includes binary references"), and explicit report/don't-report rules. It stops short of anchor 5 only because there is no worked example of an actual finding or bug pattern to calibrate against — a minor gap, so anchor 4 fits best.

4 / 5

Workflow Clarity

The Method gives a clear ordered sequence ("Start at the changed persistence or export boundary" → trace through serialization/storage/reload/UI → check failure scenarios) and the Threshold section serves as an explicit decision checkpoint, including false-positive suppression ("Do not report a browser file-picker denial as a product bug..."). This is a single-task, under-50-line read-only review skill with unambiguous steps, so the rubric's simple-skill exception applies and anchor 5 fits; the destructive/batch validation cap does not apply since reviewing is non-destructive.

5 / 5

Progressive Disclosure

The body is under 50 lines, needs no external references, and is organized into clear, well-labeled sections (Scope, Method, Threshold, Reporting) covering exactly what a review lens requires. No references/ or scripts/ bundle exists and none is needed, so per the rubric's simple-skill guidance this matches anchor 5.

5 / 5

Total

19

/

20

Passed

Description

78%Weight 40%Scale 1-5

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

The description is specific, honest, and well-targeted at a clear Excalidraw niche with minimal conflict risk. Its main weakness is the trigger guidance: "Use as one lens in a code review run" answers "when" only abstractly, and natural trigger synonyms (save, load, import, scene files) are missing from the description despite appearing in the body.

Suggestions

Replace the abstract when-clause with concrete trigger phrases, e.g. "Use when reviewing Excalidraw changes that save, load, export, or import scenes, or when the user mentions data loss or local-only features."

Add the natural synonyms already used in the body — save, load, import, scene files, storage — to the description so users' phrasing matches the trigger terms.

Consider naming one or two concrete actions beyond the single verb "Review" (e.g. "trace scene data through serialization and reload") to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

"Review Excalidraw export, persistence, and local-only feature changes for data loss, round-trip, escaping, quota, and boundary regressions" names the domain and enumerates five specific regression classes to check. It lists several specific actions rather than 1-2 (anchor 3), but all hang off a single verb rather than multiple distinct concrete actions, so it does not reach anchor 5.

4 / 5

Completeness

The "what" is clear (review export/persistence/local-only changes for the listed regression classes) and a "when" equivalent is explicitly present: "Use as one lens in a code review run." The when-clause exists, avoiding the anchor-3 cap, but it is abstract and lacks concrete trigger phrases like "when reviewing changes that save or export scenes", so it does not match anchor 5.

4 / 5

Trigger Term Quality

"Excalidraw", "export", "persistence", and "local-only" are natural terms a user working in this domain would say. Common variations and synonyms a user might actually utter — "save", "load", "import", "scene files" — appear in the body but not the description, so coverage is good but not comprehensive (anchor 4, not 5).

4 / 5

Distinctiveness Conflict Risk

"Excalidraw export, persistence, and local-only feature changes" carves out a clear niche with a named product and feature areas, so it is unlikely to trigger for the wrong skill. This matches the anchor-5 example of a clear niche with distinct triggers and minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

guypod/excalidraw-factory

Path

review-lenses/export-persistence-local-first/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.