wondel-skills-mcp
Read-only MCP server over 50 book-based agent skills: routes a task to the right framework.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~2,249Token（工具定義）
~4.3 KB典型回應大小
中等的注意力影響（128k 上下文的 1.76%）
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"wondel-skills-mcp": {
"url": "https://skills.wondel.ai/mcp"
}
}
}遠端端點
https://skills.wondel.ai/mcpstreamable-http它能做什麼
工具清單
工具（5）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search_skills(query, kind, category, limit, context)
Search 51 book-based agent skills and 14 guided journeys by keyword or phrase. Each skill is matched against its own trigger text, so plain task language works ("my UI looks amateur", "pricing", "dark mode"). Returns compact hits, each quoting the line that matched. Use recommend_skills instead when you have a task rather than a keyword.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 2,
"description": "Keyword, phrase, slug or plain description of the problem"
},
"kind": {
"description": "Restrict to single skills or guided journeys",
"type": "string",
"enum": [
"skill",
"journey",
"all"
]
},
"category": {
"description": "Restrict to one domain",
"type": "string",
"enum": [
"design",
"marketing",
"sales",
"product",
"strategy",
"team",
"code",
"architecture"
]
},
"limit": {
"description": "Maximum hits (default 8)",
"type": "integer",
"minimum": 1,
"maximum": 20
},
"context": {
"type": "string",
"description": "Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name."
}
},
"required": [
"query",
"context"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"total": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"kind": {
"type": "string",
"enum": [
"skill",
"journey"
]
},
"name": {
"type": "string"
},
"oneLiner": {
"type": "string"
},
"category": {
"type": "string"
},
"whyMatch": {
"type": "string"
},
"updated": {
"type": "string"
},
"canonical": {
"type": "string"
},
"install": {
"type": "string"
}
},
"required": [
"slug",
"kind",
"name",
"oneLiner",
"category",
"whyMatch",
"updated",
"canonical",
"install"
],
"additionalProperties": false
}
},
"next": {
"type": "string"
}
},
"required": [
"query",
"total",
"results",
"next"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢recommend_skills(task, stack, phase, max, context)
Route a task to the right skills. Describe the job in your own words and this returns which skills to load first, which to skip whenever a skill's own "not for" line rules it out for this task — quoted verbatim — and a guided journey when the task spans a whole project rather than one step. This is the tool to reach for first.
輸入結構描述
{
"type": "object",
"properties": {
"task": {
"type": "string",
"minLength": 4,
"description": "The job to be done, in your own words — a full sentence beats a keyword"
},
"stack": {
"description": "Language, framework or platform, if it narrows the answer",
"type": "string"
},
"phase": {
"description": "Where in the work you are",
"type": "string",
"enum": [
"audit",
"build",
"launch"
]
},
"max": {
"description": "How many skills to return (default 3)",
"type": "integer",
"minimum": 1,
"maximum": 6
},
"context": {
"type": "string",
"description": "Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name."
}
},
"required": [
"task",
"context"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"task": {
"type": "string"
},
"loadFirst": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"why": {
"type": "string"
}
},
"required": [
"slug",
"name",
"why"
],
"additionalProperties": false
}
},
"then": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"why": {
"type": "string"
}
},
"required": [
"slug",
"name",
"why"
],
"additionalProperties": false
}
},
"avoid": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"reason": {
"type": "string"
}
},
"required": [
"slug",
"name",
"reason"
],
"additionalProperties": false
}
},
"journey": {
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"why": {
"type": "string"
},
"phases": {
"type": "number"
}
},
"required": [
"slug",
"name",
"why",
"phases"
],
"additionalProperties": false
},
"next": {
"type": "string"
}
},
"required": [
"task",
"loadFirst",
"then",
"avoid",
"next"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_skill(slug, sections, context)
Metadata for one skill or journey: its definition, when to use it, when not to, and related slugs. Deliberately cheap (~300 tokens) so you can check a candidate before committing context to it. Pass sections to widen, or sections:["all"] for the whole page. This does not return the skill instructions — load_skill does.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Skill or journey slug, e.g. \"refactoring-ui\" or \"create-business\""
},
"sections": {
"description": "Which parts to return. Default: definition, use_when, not_for, related. \"all\" returns the full page.",
"type": "array",
"items": {
"type": "string",
"enum": [
"definition",
"use_when",
"not_for",
"key_concepts",
"prompts",
"faqs",
"book",
"related",
"phases",
"all"
]
}
},
"context": {
"type": "string",
"description": "Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name."
}
},
"required": [
"slug",
"context"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"kind": {
"type": "string",
"enum": [
"skill",
"journey"
]
},
"name": {
"type": "string"
},
"category": {
"type": "string"
},
"oneLiner": {
"type": "string"
},
"updated": {
"type": "string"
},
"canonical": {
"type": "string"
},
"source": {
"type": "string"
},
"install": {
"type": "string"
},
"definition": {
"type": "string"
},
"useWhen": {
"type": "array",
"items": {
"type": "string"
}
},
"notFor": {
"type": "array",
"items": {
"type": "string"
}
},
"keyConcepts": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"description": {
"type": "string"
}
},
"required": [
"title",
"description"
],
"additionalProperties": false
}
},
"examplePrompts": {
"type": "array",
"items": {
"type": "string"
}
},
"faqs": {
"type": "array",
"items": {
"type": "object",
"properties": {
"question": {
"type": "string"
},
"answer": {
"type": "string"
}
},
"required": [
"question",
"answer"
],
"additionalProperties": false
}
},
"book": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"author": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"title",
"author"
],
"additionalProperties": false
},
"related": {
"type": "array",
"items": {
"type": "string"
}
},
"phases": {
"type": "array",
"items": {
"type": "object",
"properties": {
"n": {
"type": "number"
},
"skillSlug": {
"type": "string"
},
"question": {
"type": "string"
},
"artifact": {
"type": "string"
},
"gate": {
"type": "boolean"
}
},
"required": [
"n",
"skillSlug",
"question",
"artifact",
"gate"
],
"additionalProperties": false
}
},
"next": {
"type": "string"
}
},
"required": [
"slug",
"kind",
"name",
"category",
"oneLiner",
"updated",
"canonical",
"source",
"install",
"next"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢load_skill(slug, part, context)
The skill's actual instructions — the upstream SKILL.md, ready to follow in this session with nothing installed. The response also lists the skill's reference files with their token cost, so you can pull deeper material on demand by calling again with part set to a filename.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Skill or journey slug"
},
"part": {
"description": "\"core\" (default) for SKILL.md, or a reference filename from a previous response",
"type": "string"
},
"context": {
"type": "string",
"description": "Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name."
}
},
"required": [
"slug",
"context"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_journey(slug, goal, context)
One guided journey as a phase plan: the ordered skills, the decision question each phase answers, the docs/ file it writes, and which phases are go/no-go gates. Pass slug for a known journey, or goal to have one picked.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"description": "Journey slug, e.g. \"grow-website\"",
"type": "string"
},
"goal": {
"description": "What you are trying to achieve, if you do not know which journey fits",
"type": "string"
},
"context": {
"type": "string",
"description": "Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name."
}
},
"required": [
"context"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"tagline": {
"type": "string"
},
"definition": {
"type": "string"
},
"phases": {
"type": "array",
"items": {
"type": "object",
"properties": {
"n": {
"type": "number"
},
"skillSlug": {
"type": "string"
},
"skillName": {
"type": "string"
},
"question": {
"type": "string"
},
"artifact": {
"type": "string"
},
"gate": {
"type": "boolean"
}
},
"required": [
"n",
"skillSlug",
"skillName",
"question",
"artifact",
"gate"
],
"additionalProperties": false
}
},
"artifacts": {
"type": "array",
"items": {
"type": "string"
}
},
"useWhen": {
"type": "array",
"items": {
"type": "string"
}
},
"notFor": {
"type": "array",
"items": {
"type": "string"
}
},
"install": {
"type": "string"
},
"canonical": {
"type": "string"
},
"next": {
"type": "string"
}
},
"required": [
"slug",
"name",
"tagline",
"definition",
"phases",
"artifacts",
"useWhen",
"notFor",
"install",
"canonical",
"next"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}社群
證據
近期觀測
已驗證未記錄版本5 個工具
已驗證未記錄版本5 個工具
已驗證未記錄版本5 個工具