recipe-front-design

Execute from codebase analysis to frontend design document creation

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content delivers highly actionable, well-sequenced orchestrator instructions with strong validation checkpoints and explicit stopping points. Its weaknesses are token efficiency (repeated contract details) and progressive disclosure (no bundle files; long inline subagent prompts).

Suggestions

Move the repeated `requirement_analysis` JSON field definitions and verbose subagent prompt templates into a `references/` file, keeping SKILL.md a lean overview.

De-duplicate the four-field `requirement_analysis` specification (restated in Steps 2 and 5) by referencing a single shared definition.

Tighten the Execution Protocol prose, which restates points already covered in Scope Boundaries and the workflow diagram.

Dimension	Reasoning	Score
Conciseness	The body is dense with orchestrator contracts and JSON field listings (e.g. the four `requirement_analysis` fields restated twice) that assume little of Claude and could be tightened, but it avoids explaining basic concepts and stays task-focused.	2 / 3
Actionability	Each step gives concrete, copy-paste-ready Agent invocations with exact `subagent_type`, `description`, and `prompt` contents, plus concrete examples (e.g. the ui-spec-designer prompt with PRD/no-PRD variants) — fully executable guidance.	3 / 3
Workflow Clarity	A clearly sequenced 8-step flow with explicit `[STOP]` approval checkpoints, branching for ADR vs Design Doc, a feedback loop (code-verifier → document-reviewer), and a Completion Criteria checklist for verification.	3 / 3
Progressive Disclosure	No references/scripts/assets bundle exists, yet the body is a ~170-line monolith embedding subagent prompts inline rather than factoring detailed subagent contracts out into referenced files; structure is present but content that could be separate is inline.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 identifies the frontend design phase and its output but is framed as an internal process step rather than a user-facing trigger. It lacks a "Use when" clause and natural trigger keywords, leaving Claude without clear guidance on when to invoke it.

Suggestions

Rewrite in third-person action voice with concrete capabilities, e.g. "Creates frontend design documents (UI Specs, ADRs, Design Docs) from codebase analysis and requirements."

Add an explicit trigger clause: "Use when designing a frontend feature that needs a UI Spec, ADR, or Design Doc."

Include natural user keywords such as "frontend design", "UI spec", "design doc", and "ADR" so the description surfaces for relevant requests.

Dimension	Reasoning	Score
Specificity	Quotes "Execute from codebase analysis to frontend design document creation" — it names a domain (frontend design) and a concrete action (document creation) but uses abstract framing rather than listing multiple concrete actions like analysis, spec drafting, and review.	2 / 3
Completeness	It states what the skill does ("Execute from codebase analysis to frontend design document creation") but lacks any "Use when..." trigger clause, so the "when" half is missing — per the guidelines this caps completeness at 2.	2 / 3
Trigger Term Quality	The description offers no natural user-facing keywords (e.g. "frontend design", "UI spec", "design doc", "ADR"); the phrasing "from codebase analysis to frontend design document creation" is process jargon a user would not naturally say.	1 / 3
Distinctiveness Conflict Risk	"frontend design document" gives a recognizable niche that limits broad conflicts, but the generic "codebase analysis" lead-in could overlap with general code-analysis or design skills, so it is only somewhat distinct.	2 / 3
	Total	7 / 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: shinpr/claude-code-workflows
Commit: 66e3b29

Reviewed: 1 day 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.