flows-design-review

Semi-automated design quality review for Flows apps. Runs concrete repo probes (grep, lint, build) to propose a draft 1–5 score for each of the official 10 quality-guidelines questions from docs.cognite.com/cdf/flows/guides/quality-guidelines, then asks the user to confirm or override each score. Still requires the user to walk their tasks end-to-end in the running app (Step 2) since navigation and clickability feel cannot be measured statically. Writes reviews/design-review/feedback-round-<N>/design-review-report.md with an overall average and prioritized fix lists. Use when the user asks to run a Flows design review, run the design quality assessment, or run flows-design-review. Must be run AFTER flows-code-review reaches 0 Must Fix and BEFORE flows-external-app-submit.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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.

A thorough, highly actionable review procedure with clear sequencing and validation checkpoints. Its main weaknesses are token redundancy from restating the core loop and a monolithic structure that inlines the 10-question detail rather than offloading it to a reference file.

Suggestions

Move the per-question probe lists and 1–5 rubric anchors (Q1–Q10) into a references/ file (e.g. questions.md) and link to it from Step 3, keeping only the shared probe→propose→confirm loop and heuristics table inline in SKILL.md.

State the "automate first, ask second" / AskQuestion three-option pattern once in Operating rules and reference it from Step 0 and Step 3 instead of restating it in each section.

Collapse the per-question "Translate to draft score" lines into the shared heuristics table, referencing the table from each question to remove the overlapping scoring guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly purposeful domain-specific rubric content rather than concepts Claude already knows, but the automate-first/ask-second loop is restated across "Operating rules", Step 0, and Step 3, and per-question "Translate to draft score" lines overlap the shared heuristics table, so it could be tightened.	3 / 5
Actionability	Copy-paste-ready probes (e.g. `grep -rlE '#[0-9a-fA-F]{3,8}' --include='*.css'...`, `npx eslint . --ext .ts,.tsx --rule '...'`, `npm run build 2>&1 \| tail -20`) plus a complete report template with an exact machine-readable `Average score:` line cover the common cases fully.	5 / 5
Workflow Clarity	Steps 0–6 are clearly sequenced with explicit validation ("Do NOT proceed to scoring until the user confirms they walked every task") and a feedback loop (re-run in a new feedback round); the operations are read-only probes plus report writing, so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	The body is well-sectioned with clear headers, but it is a single ~360-line monolith: the per-question probe lists and 1–5 rubric anchors are inlined in SKILL.md with no skill-bundle reference files (references/, scripts/, assets/ are absent), where a reference file would be appropriate.	3 / 5
	Total	16 / 20 Passed

Description

92%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, specific description that clearly states capabilities, trigger conditions, and sequencing relative to sibling skills. The only soft spot is trigger term breadth, which centers on a few near-synonyms of "design review".

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Runs concrete repo probes (grep, lint, build) to propose a draft 1–5 score", "asks the user to confirm or override each score", and "Writes reviews/design-review/feedback-round-<N>/design-review-report.md with an overall average and prioritized fix lists" — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (probes → propose → confirm → report) and when ("Use when the user asks to run a Flows design review…") with concrete trigger phrases and an ordering constraint, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural triggers — "run a Flows design review, run the design quality assessment, or run flows-design-review" — with synonyms, but the surface is narrow (all variations of "design review") and lacks broader phrasings a user might naturally say.	4 / 5
Distinctiveness Conflict Risk	Clear niche ("Semi-automated design quality review for Flows apps") with explicit ordering — "Must be run AFTER flows-code-review reaches 0 Must Fix and BEFORE flows-external-app-submit" — minimizing conflict with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: cognitedata/builder-skills
Path: skills/flows-design-review/SKILL.md
Commit: c87160a

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.