CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp2skill

将 MCP Server 的工具列表转换为 Skill 格式的结构化 Markdown 文档

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/wanwu/mcp2skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 strong, execution-ready command reference: complete parameter tables, five runnable examples covering the main transport and auth variants, and a documented output structure that doubles as a success check. The only real gaps are minor token redundancy across the auth examples and slightly long parameter tables that could live in a reference file.

Suggestions

Trim the repeated 'name=天气查询 streamableUrl=... description="查询天气"' arguments in the three auth examples — show the full command once and then only the differing apiAuth/headers argument.

Consider moving the apiAuth sub-property table into a short reference file (e.g. references/auth.md) with a clearly signaled link, keeping the top-level parameter table as the overview.

State what happens on failure (e.g. connection timeout behavior, where errors are reported) so the expected-output check in the 输出结构 section has a counterpart for the unhappy path.

DimensionReasoningScore

Conciseness

The body is efficient — compact parameter tables and bare command examples with no explanations of concepts Claude already knows — but examples 3-5 each repeat the identical 'name=天气查询 streamableUrl=... description="查询天气"' prefix that could be trimmed, matching the 'efficient; minor instances that could be trimmed' anchor rather than 5.

4 / 5

Actionability

Five copy-paste-ready mcp2skill commands cover the common cases (streamable URL, SSE URL, query-param API key, bearer-token header auth, custom headers), backed by complete parameter and apiAuth property tables and a concrete output tree — fully executable guidance matching the top anchor.

5 / 5

Workflow Clarity

This is a simple single-command skill whose single action is unambiguous (exact syntax, defaults, and five examples), and the expected result is documented ("转换成功后,在输出目录下生成...") so success can be verified against the output tree; the simple-skill exception applies since it is not a destructive or batch operation.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well organized into clearly signaled sections (Parameters, apiAuth Properties, Example, 输出结构) with content that appropriately lives inline for a single-command reference; at ~74 lines with everything in one file it sits at 'good structure; minor organization gaps' rather than the ideal split of a 5.

4 / 5

Total

18

/

20

Passed

Description

53%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 states a clear, single concrete capability in a distinct niche, but it reads like a bare function signature: it lists no 'when to use' trigger guidance and few natural search terms. Adding a 'Use when...' clause with the phrases users would actually say would lift completeness and trigger-term quality substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to turn an MCP server's tools into a Skill, or mentions converting/generating Skill documentation from MCP tool lists."

Include natural keyword variations users would say — "MCP tools", "tool list", "generate skill", "MCP documentation" — rather than only the technical terms "MCP Server" and "Skill 格式".

Optionally enumerate 1-2 more concrete actions (e.g. generates a SKILL.md overview plus per-tool reference docs and a Python client) to raise specificity from 3 to 4.

DimensionReasoningScore

Specificity

"将 MCP Server 的工具列表转换为 Skill 格式的结构化 Markdown 文档" names the domain (MCP Server tools) and one concrete action (convert to structured Skill-format Markdown), matching the 'names domain and 1-2 concrete actions' anchor; it does not list several specific actions, so it is not a 4.

3 / 5

Completeness

The description has a clear 'what' (convert MCP tool lists to Skill-format Markdown) but contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

The only keywords are technical terms like "MCP Server", "工具列表", "Skill 格式", "Markdown" — relevant but missing natural variations or synonyms a user would say (e.g. "MCP tools", "convert MCP to skill", "generate skill docs"), matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

The MCP-to-Skill conversion niche is quite specific with minimal conflict risk against other skills, but the thin trigger phrasing leaves minor overlap with generic documentation-generation skills, placing it between anchors 4 and 5, closer to 4.

4 / 5

Total

13

/

20

Passed

Validation

100%

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
UnicomAI/wanwu
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.