xiangguangyu-mcp-skills
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SSE_PORT | No | SSE server port | 3100 |
| MCP_TRANSPORT | No | Transport mode: stdio or sse | stdio |
| SKILL_API_BASE | No | Skill API base URL | http://124.222.26.218:3000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| discover_skillsA | List all 252 available AI skills with name, description, price, and featured status. Use this to browse the full catalog. |
| skill_ad-copywriterC | [Ad Copywriter] 广告文案生成器 (¥0.10/call) |
| skill_contract-guardianA | [Contract Guardian] 合同卫士 — AI合同审查助手，识别风险条款、提取关键信息、追踪到期日 (¥0.10/call) |
| skill_zhuojianB | [Zhuojian] 灼见｜ZHUOJIAN——穿透事物本质的深度分析工具，拒绝表面叙事，用证据链给出最接近真相的判断 (¥0.50/call) |
| skill_taobao-listingD | [Taobao Listing] 淘宝商品文案 (¥0.10/call) |
| skill_bianzhenD | [Bianzhen] 多模型对抗验证助手（跨平台版） (¥0.50/call) |
| skill_weekly-reportD | [Weekly Report] 周报快写器 (¥0.10/call) |
| skill_mbti-deep-analysisB | [mbti-deep-analysis] 通过28题引导式问卷判定MBTI四维度类型，生成包含16型人格解读、认知功能栈、职业倾向与成长建议的深度分析报告 (¥0.10/call) |
| skill_cuiluB | [Cuilu] 淬炉——Skill锻造与双重质检引擎。边锻造边质检，每个Skill出厂前必须通过辩真事实核查与灼见深度穿透双重门禁。 (¥0.50/call) |
| skill_shijinB | [Shijin] 试金石｜SHIJIN——Skill质量试金石，一键检测Skill是否达到上架标准 (¥0.50/call) |
| skill_game-audioC | [Game Audio] 游戏音频设计——音效/配乐/环境音方案与资源制作 (¥0.10/call) |
| get_skill_detailA | Get full details/SKILL.md of any of the 252 skills by slug. Use discover_skills first to find slugs. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| browse-skills | Browse available AI skills |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| skill-catalog |
TDQS
Scored across 12 tools
Each tool has a clearly distinct purpose: discover_skills lists all skills, get_skill_detail retrieves details by slug, and the 10 skill_ tools each target a specific, unique skill (e.g., ad copywriting, contract review, MBTI analysis). No two tools appear to overlap in functionality.
The two discovery tools follow a verb_noun pattern (discover_skills, get_skill_detail), while the 10 individual skills are consistently prefixed with 'skill_'. This minor inconsistency is manageable as the prefixes signal different roles, but it could be unified.
12 tools is a well-scoped number for a skills server. It offers discovery (2 tools) plus a curated set of 10 specific skills, avoiding bloat while providing enough variety. The count fits within the ideal 3–15 range.
The tool surface covers browsing (discover_skills, get_skill_detail) and using a subset of skills (10 individual tools), but it lacks search/filter for the full 252-skill catalog and does not allow executing skills outside the 10 pre-selected ones. This gap may limit agents that need a skill not in the list.