CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fix-design-notes

Design notes on a PR, "Design review (advisory)" in the evidence check, "worth fixing", layout.split-row, OW-LIST, a reviewer says the UI looks off. Use to read what the design review found on a PR's screenshots, fix it in code, and prove the note is gone.

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

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary instruction-only skill body: lean, executable, and precisely sequenced, with a validated fix-and-verify loop, concrete commands and grep hooks for every step, and a documented exception path. Detail is appropriately deferred to DESIGN.md and the design-review rubric.

DimensionReasoningScore

Conciseness

The body is lean throughout: it assumes familiarity with gh, CI, and grep, and every element — the check-reading snippet, the field table, the five-step fix loop, the rules — carries operational information with no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

Guidance is fully executable: the copy-paste-ready gh api snippet for reading notes, the complete reproduce command (`pnpm evals:e2e <slug> --local && pnpm --dir evals design:review -- --test-run latest --json`), a concrete grep mapping (`[data-library-row="…"]` → `data-library-row`), and a sample PR-body line cover the common cases.

5 / 5

Workflow Clarity

The 'Reproduce, fix, verify' section gives a clearly sequenced five-step workflow with an explicit validation checkpoint ("The note must be gone and no new Worth fixing note may appear") and a fix→re-run feedback loop, plus a human-check step ("Look at the screenshot yourself").

5 / 5

Progressive Disclosure

The body is a well-organized overview that defers detail one level deep with clear signaling — "Read DESIGN.md and the rule in evals/design-review/rubric.md before changing anything" — and the JSON note format for scripts is pointed to rather than restated; nothing that belongs in a separate file is inlined.

5 / 5

Total

20

/

20

Passed

Description

86%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.

A strong, distinctive description: concrete actions, an unusually rich set of natural trigger terms (quoted check strings, rule IDs, a realistic complaint scenario), and a tightly scoped niche. The only weakness is that the trigger list is not linked with an explicit 'Use when...' clause and the action list omits the keep/documented-exception path.

Suggestions

Make the activation conditions explicit with a 'Use when...' clause (e.g., "Use when a PR's evidence check shows design review notes or a reviewer says the UI looks off") so the leading trigger list reads unambiguously as 'when' guidance rather than a topic fragment.

Close the coverage gap by mentioning the exception path — documenting in the PR body when a screen is intentionally kept despite a note — alongside the read/fix/prove actions.

DimensionReasoningScore

Specificity

"Use to read what the design review found on a PR's screenshots, fix it in code, and prove the note is gone" lists three concrete actions covering the core workflow, but omits the exception path (documenting in the PR body why a screen is intentionally kept) and the push/CI verification step — minor coverage gaps matching anchor 4 rather than comprehensive anchor 5.

4 / 5

Completeness

The 'what' is explicit ("read what the design review found... fix it in code, and prove the note is gone") and concrete trigger phrases are present, but the 'when' linkage relies on an implicit leading trigger list with no explicit 'Use when...' connector, fitting anchor 4 ('when' could be more explicit) rather than 5.

4 / 5

Trigger Term Quality

The trigger list is unusually rich and natural: quoted phrases a user would echo ("worth fixing", "Design review (advisory)"), concrete rule identifiers (layout.split-row, OW-LIST), and the scenario phrase "a reviewer says the UI looks off" — comprehensive coverage including variations of how the need surfaces.

5 / 5

Distinctiveness Conflict Risk

A clear niche — advisory design review notes riding the Evidence preview check on PRs — with distinct triggers (OW-* rules, layout.* measurements, the check name) that no generic design or PR skill would share, so conflict risk is minimal.

5 / 5

Total

18

/

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

different-ai/openwork

Path

.opencode/skills/fix-design-notes/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.