CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

design-editor-repro

Reproduce and verify Design editor issues against the application itself.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/design-editor-repro/SKILL.md
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 an exemplary lean, operational workflow: concrete commands, explicit setup-investigate-verify sequencing with feedback loops and cleanup discipline, and no token waste. The single weakness is progressive disclosure — the bundle ships only scripts/clip.mjs and scripts/copy-design.mjs, so most of the files the body cites for details cannot be found in the bundle as provided.

Suggestions

Ship the referenced files (harness-recipes.md, reference/input-and-osmouse.md, reference/fixing.md, reference/tests-and-blast-radius.md, reference/performance.md) in the bundle, or correct the paths so the closing "For details, see ..." pointers resolve.

State what doctor.mjs readiness looks like and what to do if it never reports ready, so the setup feedback loop has an explicit error-recovery exit.

DimensionReasoningScore

Conciseness

The body is lean, imperative, and free of concept explanations Claude already knows — every line is operational ("Run node ... doctor.mjs until the local app and editor session are ready", "Do not commit screenshots, copied user designs, session data, credentials, or temporary exports"). Matches the 5 anchor; anchor 4 would require over-explanation that is simply absent.

5 / 5

Actionability

Commands are copy-paste ready with concrete paths and placeholders ("node .agents/skills/design-editor-repro/scripts/copy-design.mjs <design-id>", "harness/start-dev.sh", "harness/shot.mjs"), named env vars (DESIGN_TEST_EMAIL, DESIGN_TEST_PASSWORD), a designated temp dir, and named helpers (harness/dlib.mjs). Fully executable guidance matching the 5 anchor.

5 / 5

Workflow Clarity

Setup (numbered 1-4), Investigation, and Verification are explicitly sequenced with validation checkpoints and feedback loops: run doctor until ready, "Reproduce the reported steps before changing application code", re-run the original steps on the changed build, run the narrowest relevant tests, inspect the rendered application, and clean up the production copy. This matches the 5 anchor (clear sequence, explicit validation, error-recovery loop); not 4, since no checkpoint is left implicit.

5 / 5

Progressive Disclosure

Sections are well organized and the closing pointer ("For details, see harness-recipes.md, reference/input-and-osmouse.md, reference/fixing.md, reference/tests-and-blast-radius.md, and reference/performance.md") is clearly signaled and one level deep. However, scored against the actual bundle, only scripts/copy-design.mjs exists — the reference/, harness/, and harness-recipes.md paths do not resolve anywhere in the bundle, so the promised navigation is incomplete. Better than 2 (structure is not minimal, references are not buried), short of 4 (referenced paths are missing from the bundle).

3 / 5

Total

18

/

20

Passed

Description

53%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 states a clear, domain-specific capability in third person with two concrete verbs, but it is minimal. The missing "Use when..." trigger clause caps completeness, and the terse phrasing omits natural synonyms (bug, defect, regression) that would improve trigger matching.

Suggestions

Add an explicit trigger clause, e.g. "Use when reproducing reported bugs or defects in the Design editor, or when a fix needs verification against the real application."

Include natural trigger synonyms users would actually say — "bug", "defect", "regression", "editor report" — alongside "issues".

Enumerate one or two more concrete capabilities (launch the dev harness, copy a design, drive the editor and capture screenshots) to raise specificity beyond two verbs.

DimensionReasoningScore

Specificity

"Reproduce and verify" names two concrete actions on the "Design editor issues" domain, but the description lists nothing further about what the skill actually does (harness setup, copying designs, driving the editor, screenshots). This matches the 3 anchor ("Names domain and 1-2 concrete actions, but not comprehensive"); it is not 4 because no additional specific actions are enumerated.

3 / 5

Completeness

The "what" is clear ("Reproduce and verify Design editor issues against the application itself"), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps this dimension at 3 per the judging guidelines. Not 2, because the "what" half is concrete and unambiguous.

3 / 5

Trigger Term Quality

"Reproduce", "Design editor", and "issues" are natural terms a user would say, but common variations such as "bug", "defect", "regression", or "report" are missing. Fits the 3 anchor ("Some relevant keywords but missing common variations or synonyms") better than 4, since keyword coverage is thin rather than merely missing a few terms.

3 / 5

Distinctiveness Conflict Risk

"Design editor" pins a specific application's editor, giving a clear niche with minor overlap risk against generic debugging/repro skills. Not 5, because without any trigger guidance the bare action language ("reproduce and verify issues") could pull in general bug-reproduction requests.

4 / 5

Total

13

/

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

BuilderIO/agent-native

Path

.agents/skills/design-editor-repro/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.