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

68%

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

87%

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 lean, highly actionable CLI reference: complete parameter tables and five copy-paste-ready command examples covering streamable, SSE, and auth scenarios, plus a clear output-structure tree. Its main gap is the absence of validation/verification and error-recovery guidance for what is fundamentally a networked, authenticated conversion operation.

Suggestions

Add a short verification step after the examples, e.g. 'After running, confirm {output}/{skillName}/SKILL.md and scripts/mcp_client.py exist; re-run with a larger timeout if the connection failed.'

Include brief error-recovery guidance for the network/auth failure modes the parameters imply (connection timeout, authType mismatch, missing apiKeyValue).

Clarify the success/exit criteria of the conversion so Claude knows when the task is complete.

DimensionReasoningScore

Conciseness

The body is lean — a Parameters table, an apiAuth properties table, five copy-paste bash examples, and an output-structure tree — with no explanations of concepts Claude already knows (no 'what is MCP/Skill' padding), matching 'Lean and efficient; every token earns its place'; it is not the score-2 case because there is no unnecessary explanation to tighten.

3 / 3

Actionability

Examples like 'mcp2skill name=天气查询 streamableUrl=http://192.168.0.21:8081/mcp/server/streamable?key=xxx description="查询天气" output=./skills' and the api_key_query/header auth commands are fully executable, specific, and copy-paste ready, fitting the score-3 anchor; it is not score 2 because the commands are complete real invocations rather than pseudocode.

3 / 3

Workflow Clarity

The single mcp2skill invocation is unambiguous and illustrated across scenarios, but for an operation involving network connection (timeout param) and authentication there is no validation/verification step or error-recovery guidance (what to check if the connection fails or output is not generated), matching 'Steps listed but validation gaps'; it falls short of 3 which requires explicit validation checkpoints and feedback loops.

2 / 3

Progressive Disclosure

The content is self-contained with no bundle files present and is organized into clear sections (Parameters, apiAuth Properties, Example, 输出结构) with no nested references, matching the rubric note that skills with no need for external references can score 3 via well-organized sections; it is not score 2 because nothing is inline that should be split out.

3 / 3

Total

11

/

12

Passed

Description

50%

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 specific about a single conversion action within a clear niche, but it stops short of listing multiple concrete actions and entirely omits 'Use when...' trigger guidance. Adding explicit usage triggers and a couple more concrete actions would lift all four dimensions.

Suggestions

Append a 'Use when...' clause stating when Claude should invoke this skill, e.g. 'Use when the user wants to turn an MCP Server's tools into a Claude Skill or asks to convert/generate a SKILL.md from an MCP endpoint.'

List multiple concrete actions to raise specificity, e.g. 'Convert MCP Server tool lists into Skill-format Markdown, generate a SKILL.md overview and per-tool detail documents, and produce an MCP Python client.'

Add natural trigger-term variations users would actually say ('MCP to Skill', 'generate SKILL.md from MCP', 'convert MCP tools') to improve trigger_term_quality and distinctiveness.

DimensionReasoningScore

Specificity

Quotes '将 MCP Server 的工具列表转换为 Skill 格式的结构化 Markdown 文档' — it names the domain (MCP Server tools) and one concrete action (convert to structured Markdown), matching the score-2 anchor 'Names domain and some actions, but not comprehensive'; it does not list multiple distinct actions required for a 3, yet is far more concrete than 'Helps with documents'.

2 / 3

Completeness

It clearly states what the skill does (convert MCP tool lists to Skill-format Markdown) but provides no explicit 'when to use it' trigger guidance, so per the rubric guideline a missing 'Use when...' clause caps completeness at 2.

2 / 3

Trigger Term Quality

The terms 'MCP Server' and 'Skill' are keywords a user working in this niche would say, but the description omits common variations and any 'Use when...' phrasing, fitting 'Some relevant keywords but missing common variations' rather than the broad natural-term coverage of a 3.

2 / 3

Distinctiveness Conflict Risk

The MCP-Server-to-Skill conversion niche is fairly specific and unlikely to conflict broadly, but the description lacks distinct explicit triggers, matching 'Somewhat specific but could still overlap' rather than the 'distinct triggers' required for a 3.

2 / 3

Total

8

/

12

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.

Validation16 / 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.