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

87%

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

86%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 tight, well-structured instruction skill: lean imperatives, concrete CLI commands, an explicit phase contract, and clear sequencing with coverage validation and phase-transition rules. Its only weaknesses are a few process-level steps that lack executable specifics and no explicit recovery path when validation fails.

Dimension	Reasoning	Score
Conciseness	Lean imperative instructions with concrete commands ('Run `npx ai-devkit@latest lint` before phase work') and domain-specific checklists ('shallow modules, pass-through layers, temporal decomposition'); it assumes Claude's competence and explains nothing the model already knows.	5 / 5
Actionability	Provides executable commands and exact path resolution ('`npx ai-devkit@latest lint --feature <name>`', 'resolve `.ai-devkit.json` `paths.docs`, falling back to `docs/ai`'), but several steps remain process directives ('Brainstorm alternatives', 'Resolve every gap') rather than fully executable specifics.	4 / 5
Workflow Clarity	A clear 13-step numbered sequence with a lint pre-check, coverage cross-check ('Flag uncovered requirements'), and branch-back error handling ('If requirements gaps are found, return to `dev-requirements`'), but lacks an explicit recovery loop for validation failures (e.g., what to do when lint fails).	4 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained with no bundle files, and cleanly organized into well-labeled sections ('## Phase Contract', '## Review Design'), which satisfies the rubric's simple-skill criterion for a top score.	5 / 5
	Total	18 / 20 Passed

Description

83%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 description that names its domain, lists multiple concrete actions, and includes an explicit 'Use when' clause with natural trigger phrases. It is well-scoped to the AI DevKit lifecycle, with only minor gaps in synonym coverage and capability enumeration.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('validate architecture', 'review design docs', 'resolve design trade-offs') in a named domain, but omits other capabilities the skill body covers (updating design docs, storing decisions, coverage summaries), leaving minor gaps in coverage.	4 / 5
Completeness	Clearly states what the skill does ('Design phase guidance for reviewing feature design against requirements') and explicitly answers when to use it with concrete trigger phrases ('Use when the user wants to validate architecture, review design docs, resolve design trade-offs, or run dev-lifecycle phase 3'), matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('validate architecture', 'review design docs', 'design trade-offs') with explicit 'Use when' triggers, but misses common synonyms such as 'design review' or 'architecture review'.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche via 'AI DevKit' and 'dev-lifecycle phase 3' qualifiers, but the bare trigger phrases ('review design docs', 'validate architecture') could overlap with generic design-review skills.	4 / 5
	Total	17 / 20 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: 7ef0cd5

Reviewed: 8 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.