console-dev

Console 前端交付范式：4 道门禁驱动的前端开发流程。Use when: 新增前端能力、settings section 迁移、新增页面、重构布局、或 F190/Console 级前端流程需要 Product/Design/Implementation/Verification gate。 Not for: 小样式点改、纯后端 API、纯计算逻辑、独立 Design System token 定义。 Output: 通过 Product / Design-System / Implementation / Verification gate 的前端代码与证据。

Quality

88%

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

90%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 concise, highly actionable gated workflow with concrete thresholds, checklists, and a mistake/fix table. The main gaps are an implicit (not explicit) verification-retry loop and two reference paths that do not resolve to real files in the bundle.

Suggestions

Add an explicit feedback loop to Gate 4: state what to do when evidence checks fail (e.g., 'if a check fails, fix in the relevant gate and re-run Gate 4 evidence before declaring done').

Verify or fix the 参考 paths — ../.cat-cafe-shared-refs/f190-frontend-lessons.md and docs/architecture/feature-placement.md are not present in the bundle; either restore the files or remove/inline the references so navigation is not broken.

Consider converting the 参考 entries into markdown links with the one-line description kept inline, so the reference target and its purpose are visible in a single scan.

Dimension	Reasoning	Score
Conciseness	Lean, table-driven body with no padding or explanation of concepts Claude already knows; every section earns its tokens (gate tables, state matrix axes, mistake/fix mapping).	5 / 5
Actionability	Highly concrete guidance: numeric split thresholds (200行/350行), explicit state-matrix axes (loading/empty/partial/full/error; owner/member/guest/unauthenticated; desktop/mobile), a named verification checklist, and a migration proof template (Source Behavior / Must Preserve Home Behavior / Decision / Proof).	5 / 5
Workflow Clarity	A clear 4-gate sequence with an explicit Gate 4 validation/evidence checkpoint and a Common Mistakes error→fix table; held below 5 because the validate→fix→retry feedback loop is not stated as an explicit retry path when verification fails.	4 / 5
Progressive Disclosure	Well-organized into clear sections with a 参考 list of clearly-signaled one-level-deep references; held below 5 because both referenced paths (../.cat-cafe-shared-refs/f190-frontend-lessons.md and docs/architecture/feature-placement.md) do not exist in the bundle, so the navigation is currently broken.	4 / 5
	Total	18 / 20 Passed

Description

87%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 well-structured, third-person description that clearly states what the skill does, when to use it, when not to use it, and what it outputs. It is specific to its niche and includes an explicit exclusion list, with only minor room for more natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain (Console frontend) and several concrete scenarios (settings section 迁移, 新增页面, 重构布局) plus a concrete output (前端代码与证据 through 4 named gates); not a full 5 because the 'what' is framed as a delivery paradigm rather than enumerated concrete actions like extract/fill/merge.	4 / 5
Completeness	Explicitly answers both what (4 道门禁驱动的前端开发流程, Output: 通过...gate 的前端代码与证据) and when (Use when: with concrete triggers), plus a Not for exclusion list — matching the anchor that requires concrete trigger phrases for both.	5 / 5
Trigger Term Quality	Multiple natural trigger phrases a user would say (新增前端能力, settings section 迁移, 新增页面, 重构布局); held below 5 because some terms are project-specific jargon (F190, Console gate) and no synonyms or file extensions are given.	4 / 5
Distinctiveness Conflict Risk	Clear Console-frontend niche with distinct 4-gate triggers and an explicit Not for list (小样式点改, 纯后端 API, 纯计算逻辑, 独立 Design System token) that minimizes overlap with adjacent skills.	5 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/console-dev/SKILL.md
Commit: 090626a

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.