dev-design

AI DevKit · Design phase guidance for reviewing feature design against requirements. Use when the user wants to validate architecture, review design docs, resolve design trade-offs, or run dev-lifecycle phase 3.

Quality

86%

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

85%Weight 40%Scale 1-3

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 well-sequenced, actionable design-review workflow with real commands, validation, and feedback loops. Its main weaknesses are mild redundancy between the two sections and a few abstract directives that lack concrete completion criteria.

Suggestions

Deduplicate the lint, memory, and task-tracing guidance that appears in both Phase Contract and Review Design so each section earns its place.

Tighten abstract steps like "Brainstorm alternatives" and "Summarize requirements coverage" with concrete acceptance criteria or output formats.

Dimension	Reasoning	Score
Conciseness	The numbered lists are lean and assume competence, but the Phase Contract and Review Design sections repeat the same concerns (lint, memory, task tracing) and could be tightened.	2.5 / 3
Actionability	Concrete executable commands ("npx ai-devkit@latest lint --feature <name>", ".ai-devkit.json paths.docs") anchor the steps, but several items ("Brainstorm alternatives", "Summarize requirements coverage") remain abstract directives.	2.5 / 3
Workflow Clarity	A clearly sequenced 1–10 process with explicit validation (lint upfront), a decision gate ("Do not approve or transition past design while material open questions remain"), and feedback loops (return to dev-requirements if gaps are found).	3 / 3
Progressive Disclosure	A sub-50-line single-purpose skill with no need for external references, organized into well-labeled Phase Contract and Review Design sections; no bundle files exist to verify.	3 / 3
	Total	11 / 12 Passed

Description

88%Weight 40%Scale 1-3

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 description that answers both what and when with explicit triggers and concrete actions. It is slightly weakened by toolkit jargon in the trigger list and some overlap risk with adjacent review skills.

Suggestions

Add common natural variations to the trigger clause (e.g., "review the design", "architecture review", "design doc sign-off") alongside the existing phrases.

Soften or contextualize "run dev-lifecycle phase 3" so users unfamiliar with the phase numbering still recognize the trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as "validate architecture, review design docs, resolve design trade-offs" rather than vague language.	3 / 3
Completeness	Clearly states what it does ("reviewing feature design against requirements") and gives an explicit "Use when the user wants to…" trigger clause.	3 / 3
Trigger Term Quality	"validate architecture", "review design docs", and "resolve design trade-offs" are natural user phrases, but "run dev-lifecycle phase 3" is toolkit jargon and common variations are limited.	2.5 / 3
Distinctiveness Conflict Risk	The "AI DevKit" / "dev-lifecycle phase 3" framing carves a niche, but "review design docs" and "resolve design trade-offs" could overlap with sibling lifecycle review skills.	2.5 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: codeaholicguy/ai-devkit
Path: skills/dev-design/SKILL.md
Commit: 15b09d2

Reviewed: 12 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.