CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-preview

Hub 内嵌浏览器预览 localhost 应用。 Use when: 写前端代码、跑 dev server、需要看页面效果、调 UI、operator说"看看效果"。 Not for: 后端纯 API 开发、不涉及页面的工作。 Output: 前端页面在 Hub browser panel 中实时预览。

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 content is highly actionable with an explicit, validated workflow and copy-paste commands, and it mostly avoids explaining things Claude already knows. Its main weakness is progressive disclosure: it is a monolithic single-file skill with no organized reference bundle, and its one shared-refs pointer is not clearly signaled.

Suggestions

Pull the long '技术要点' and '常见错误' tables into a references/ file (e.g. references/technical-notes.md) and link to it from a short overview section, so SKILL.md stays a lean entry point.

Replace the bare relative path '../.cat-cafe-shared-refs/evidence-output-contract.md' with a clearly labeled, one-level-deep reference (e.g. 'Evidence output contract: See [evidence-output-contract.md](../.cat-cafe-shared-refs/evidence-output-contract.md)') so the pointer is discoverable.

Trim the repeated '猫猫/operator' framing and consolidate the durable≠immortal / running≠durable caveats into one place to reduce token cost without losing the safety guidance.

DimensionReasoningScore

Conciseness

The body is dense and mostly earns its tokens — tables, exact commands, and delivery-status contracts rather than concept explanation — though the repeated '猫猫/operator' framing and some restated caveats (e.g. durable≠immortal appears in multiple forms) could be trimmed slightly.

4 / 5

Actionability

Copy-paste-ready commands (`pnpm preview:process start/status --port PORT --cwd ... -- COMMAND`, `curl -s -o /dev/null -w "%{http_code}" http://localhost:PORT`) and a concrete MCP call (`cat_cafe_preview_open({port, path, worktreeId, threadId})`) cover the common cases with exact flags and expected output codes.

5 / 5

Workflow Clarity

The 3-step open flow is explicitly sequenced (verify server → call MCP → read deliveryStatus) with validation checkpoints (status=running/origin=launchd, HTTP 200/301/304), error-recovery guidance in the common-errors table, and a feedback loop that ties each deliveryStatus value to a distinct reporting action.

5 / 5

Progressive Disclosure

No bundle files exist in references/scripts/assets, and the single external pointer (../.cat-cafe-shared-refs/evidence-output-contract.md) is a buried relative path rather than a clearly signaled one-level-deep reference; most detail is inlined into one long SKILL.md rather than split across files.

3 / 5

Total

17

/

20

Passed

Description

95%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.

The description is precise, well-scoped, and rich in natural trigger terms, cleanly separating what/when/not-for/output. It is a strong, low-conflict skill description.

DimensionReasoningScore

Specificity

Names the concrete action (预览 localhost 前端应用 in the Hub browser panel) and scopes it clearly with what/when/not-for/output, but it centers on one main capability rather than listing several distinct actions.

4 / 5

Completeness

Explicitly answers both what (Hub 内嵌浏览器预览 localhost 应用) and when (Use when... / Not for...) with concrete trigger phrases and a stated output, matching the anchor for a fully specified description.

5 / 5

Trigger Term Quality

Covers a comprehensive set of natural trigger phrases including synonyms and shorthand — '看效果', '看看页面', 'preview', '浏览器预览', '打开浏览器', 'pnpm dev', 'dev server', 'localhost', '前端效果', '看看 UI', 'HMR', '热更新'.

5 / 5

Distinctiveness Conflict Risk

The niche is sharply defined (Hub-embedded localhost frontend preview) and the 'Not for' clause (后端纯 API 开发、不涉及页面的工作) sharply limits overlap with other skills, giving minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
zts212653/clowder-ai
Reviewed

Table of Contents

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.