skill-finder

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill Finder

技能查找器

Find and evaluate Claude skills for your specific needs with intelligent semantic search, quality assessment, and fitness scoring.

通过智能语义搜索、质量评估和适配度评分，为你的特定需求查找并评估Claude技能。

What This Skill Does

本技能的功能

Skill-finder is a query-driven evaluation engine that:

Searches GitHub for skills matching your specific use case
Fetches and reads actual SKILL.md content
Evaluates skills against Anthropic's best practices
Scores fitness to your exact request
Provides actionable quality assessments and recommendations

This is NOT a "show me popular skills" tool - it's a semantic matcher that finds the RIGHT skill for YOUR specific need.

Skill-finder是一个基于查询的评估引擎，它可以：

在GitHub上搜索匹配你特定使用场景的技能
获取并读取实际的SKILL.md内容
根据Anthropic的最佳实践评估技能
针对你的具体请求进行适配度评分
提供可操作的质量评估和推荐建议

这不是一个“展示热门技能”的工具——它是一个语义匹配器，为你的特定需求找到最合适的技能。

When to Use

使用场景

User asks to find skills for a specific purpose: "find me a skill for creating pitch decks"
User needs help choosing between similar skills
User wants quality-assessed recommendations, not just popularity rankings
User asks "what's the best skill for [specific task]"

用户要求为特定用途查找技能：“帮我找一个用于制作演示文稿的技能”
用户需要在相似技能中做选择
用户需要经过质量评估的推荐，而不仅仅是按热度排名
用户询问“[特定任务]的最佳技能是什么”

Quick Start Examples

快速入门示例

bash

undefined

bash

undefined

Find skills for specific use case

为特定使用场景查找技能

"Find me a skill for creating pitch decks" "What's the best skill for automated data analysis" "Find skills that help with git commit messages"

NOT: "Show me popular skills" (too generic)

不适用：“Show me popular skills”（过于通用）

NOT: "List all skills" (use skill list command instead)

不适用：“List all skills”（请使用skill list命令）

undefined

undefined

Core Workflow

核心工作流程

Phase 1: Query Understanding

阶段1：查询理解

Extract semantic terms from user query:

User: "Find me a skill for creating pitch decks"

Extract terms:

Primary: "pitch deck", "presentation"
Secondary: "slides", "powerpoint", "keynote"
Related: "business", "template"

从用户查询中提取语义术语：

用户：“帮我找一个用于制作演示文稿的技能”

提取的术语：

核心：“演示文稿”、“展示”
次要：“幻灯片”、“PowerPoint”、“Keynote”
相关：“商务”、“模板”

Phase 2: Multi-Source Search

阶段2：多源搜索

Search Strategy:

bash

undefined

搜索策略：

bash

undefined

1. Repository search with semantic terms

1. 使用语义术语搜索仓库

gh search repos "claude skills pitch deck OR presentation OR slides"
--sort stars --limit 20 --json name,stargazersCount,description,url,pushedAt,owner

2. Code search for SKILL.md with keywords

2. 针对SKILL.md文件进行关键词代码搜索

gh search code "pitch deck OR presentation" "filename:SKILL.md"
--limit 20 --json repository,path,url

3. Search awesome-lists separately

3. 单独搜索精选列表

gh search repos "awesome-claude-skills" --sort stars --limit 5
--json name,url,owner


**Deduplication:**
Collect all unique repositories from search results.

gh search repos "awesome-claude-skills" --sort stars --limit 5
--json name,url,owner


**去重：**
收集搜索结果中所有唯一的仓库。

Phase 3: Content Fetching

阶段3：内容获取

For each candidate skill:

bash

undefined

针对每个候选技能：

bash

undefined

1. Find SKILL.md location

1. 查找SKILL.md的位置

gh api repos/OWNER/REPO/git/trees/main?recursive=1 |
jq -r '.tree[] | select(.path | contains("SKILL.md")) | .path'

2. Fetch full SKILL.md content

2. 获取完整的SKILL.md内容

gh api repos/OWNER/REPO/contents/PATH/TO/SKILL.md |
jq -r '.content' | base64 -d > temp_skill.md

3. Fetch repository metadata

3. 获取仓库元数据

gh api repos/OWNER/REPO --jq '{ stars: .stargazers_count, updated: .pushed_at, description: .description }'


**IMPORTANT:** Actually READ the SKILL.md content. Don't just use metadata.

gh api repos/OWNER/REPO --jq '{ stars: .stargazers_count, updated: .pushed_at, description: .description }'


**重要提示：** 务必实际读取SKILL.md的内容，不要仅使用元数据。

Phase 4: Quality Evaluation

阶段4：质量评估

Use best-practices-checklist.md to evaluate:

For each skill, assess:

Description Quality (2.0 points)
- Specific vs vague?
- Includes what + when to use?
- Third person?
Name Convention (0.5 points)
- Follows naming rules?
- Descriptive?
Conciseness (1.5 points)
- Under 500 lines?
- No fluff?
Progressive Disclosure (1.0 points)
- Uses reference files?
- Good organization?
Examples and Workflows (1.0 points)
- Has concrete examples?
- Clear workflows?
Appropriate Degree of Freedom (0.5 points)
- Matches task complexity?
Dependencies (0.5 points)
- Documented?
- Verified available?
Structure (1.0 points)
- Well organized?
- Clear sections?
Error Handling (0.5 points)
- Scripts handle errors?
- Validation loops?
Avoids Anti-Patterns (1.0 points)
- No time-sensitive info?
- Consistent terminology?
- Unix paths?
Testing (0.5 points)
- Evidence of testing?

Calculate quality_score (0-10): See best-practices-checklist.md for detailed scoring.

使用best-practices-checklist.md进行评估：

针对每个技能，评估以下维度：

描述质量（2.0分）
- 具体还是模糊？
- 是否包含功能和使用场景？
- 是否使用第三人称？
命名规范（0.5分）
- 是否遵循命名规则？
- 是否具有描述性？
简洁性（1.5分）
- 内容是否少于500行？
- 有无冗余内容？
渐进式披露（1.0分）
- 是否使用参考文件？
- 组织结构是否良好？
示例与工作流程（1.0分）
- 是否有具体示例？
- 工作流程是否清晰？
自由度适配（0.5分）
- 是否匹配任务复杂度？
依赖项（0.5分）
- 是否有文档说明？
- 是否已验证可用？
结构（1.0分）
- 组织是否有序？
- 章节是否清晰？
错误处理（0.5分）
- 脚本是否处理错误？
- 是否有验证循环？
避免反模式（1.0分）
- 有无时间敏感信息？
- 术语是否一致？
- 是否使用Unix路径？
测试（0.5分）
- 是否有测试证据？

计算质量分数（0-10分）： 详细评分规则请参考best-practices-checklist.md。

Phase 5: Fitness Scoring

阶段5：适配度评分

Semantic match calculation:

python

undefined

语义匹配计算：

python

undefined

Pseudo-code for semantic matching

语义匹配伪代码

user_query_terms = ["pitch", "deck", "presentation"] skill_content = read_skill_md(skill_path)

Check occurrences of user terms in skill

检查用户术语在技能内容中的出现情况

matches = [] for term in user_query_terms: if term.lower() in skill_content.lower(): matches.append(term)

semantic_match_score = len(matches) / len(user_query_terms) * 10


**Fitness formula:**

fitness_score = ( semantic_match * 0.4 + # How well does it solve the problem? quality_score * 0.3 + # Follows best practices? (stars/100) * 0.2 + # Community validation freshness_multiplier * 0.1 # Recent updates )

Where:

semantic_match: 0-10 (keyword matching in SKILL.md content)
quality_score: 0-10 (from evaluation checklist)
stars: repository star count
freshness_multiplier: 0-10 based on days since update


**Freshness multiplier:**
```bash
days_old=$(( ($(date +%s) - $(date -j -f "%Y-%m-%dT%H:%M:%SZ" "$pushed_at" +%s)) / 86400 ))

if [ $days_old -lt 30 ]; then
  freshness_score=10
  freshness_badge="🔥"
elif [ $days_old -lt 90 ]; then
  freshness_score=7
  freshness_badge="📅"
elif [ $days_old -lt 180 ]; then
  freshness_score=5
  freshness_badge="📆"
else
  freshness_score=2
  freshness_badge="⏰"
fi

matches = [] for term in user_query_terms: if term.lower() in skill_content.lower(): matches.append(term)

semantic_match_score = len(matches) / len(user_query_terms) * 10


**适配度计算公式：**

fitness_score = ( semantic_match * 0.4 + # 问题解决匹配度？ quality_score * 0.3 + # 是否遵循最佳实践？ (stars/100) * 0.2 + # 社区认可度 freshness_multiplier * 0.1 # 最近更新情况 )

其中：

semantic_match: 0-10（SKILL.md内容中的关键词匹配度）
quality_score: 0-10（来自评估清单）
stars: 仓库星标数量
freshness_multiplier: 0-10（基于更新天数）


**新鲜度系数：**
```bash
days_old=$(( ($(date +%s) - $(date -j -f "%Y-%m-%dT%H:%M:%SZ" "$pushed_at" +%s)) / 86400 ))

if [ $days_old -lt 30 ]; then
  freshness_score=10
  freshness_badge="🔥"
elif [ $days_old -lt 90 ]; then
  freshness_score=7
  freshness_badge="📅"
elif [ $days_old -lt 180 ]; then
  freshness_score=5
  freshness_badge="📆"
else
  freshness_score=2
  freshness_badge="⏰"
fi

Phase 6: Awesome-List Processing

阶段6：精选列表处理

Extract skills from awesome-lists:

bash

undefined

从精选列表中提取技能：

bash

undefined

For each awesome-list found

针对每个找到的精选列表

for repo in awesome_lists; do

Fetch README or main content

gh api repos/$repo/readme | jq -r '.content' | base64 -d > readme.md

Extract GitHub links to potential skills

grep -oE 'https://github.com/[^/]+/[^/)]+' readme.md | sort -u

For each linked repo, check if it contains SKILL.md

If yes, evaluate same as other skills

done


**Display awesome-list skills separately** in results for comparison.

for repo in awesome_lists; do

获取README或主要内容

gh api repos/$repo/readme | jq -r '.content' | base64 -d > readme.md

提取指向潜在技能的GitHub链接

grep -oE 'https://github.com/[^/]+/[^/)]+' readme.md | sort -u

针对每个链接的仓库，检查是否包含SKILL.md

如果包含，按照其他技能的标准进行评估

done


**在结果中单独显示精选列表中的技能**以便对比。

Phase 7: Result Ranking and Display

阶段7：结果排序与展示

Sort by fitness_score (descending)

Output format:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 Skills for: "[USER QUERY]"
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🏆 #1 skill-name ⭐ STARS FRESHNESS | FITNESS: X.X/10

   Quality Assessment:
   ✅ Description: Excellent (2.0/2.0)
   ✅ Structure: Well organized (0.9/1.0)
   ⚠️  Length: 520 lines (over recommended 500)
   ✅ Examples: Clear workflows included

   Overall Quality: 8.5/10 (Excellent)

   Why it fits your request:
   • Specifically designed for [relevant aspect]
   • Mentions [user's key terms] 3 times
   • Has [relevant feature]
   • Includes [useful capability]

   Why it's high quality:
   • Follows Anthropic best practices
   • Has comprehensive examples
   • Clear workflows and validation
   • Well-tested and maintained

   📎 https://github.com/OWNER/REPO/blob/main/PATH/SKILL.md

   [Preview Full Analysis] [Install]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🏆 #2 another-skill ⭐ STARS FRESHNESS | FITNESS: Y.Y/10

   Quality Assessment:
   ✅ Good description and examples
   ⚠️  Some best practices not followed
   ❌ No progressive disclosure

   Overall Quality: 6.2/10 (Good)

   Why it fits your request:
   • Partially addresses [need]
   • Has [some relevant feature]

   Why it's not ideal:
   • Not specifically focused on [user's goal]
   • Quality could be better
   • Missing [important feature]

   📎 https://github.com/OWNER/REPO/blob/main/SKILL.md

   [Preview] [Install]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📚 From Awesome Lists:

Found in awesome-claude-skills (BehiSecc):
  • related-skill-1 (FITNESS: 7.5/10) - Good match
  • related-skill-2 (FITNESS: 5.2/10) - Partial match

Found in awesome-claude-skills (travisvn):
  • another-option (FITNESS: 6.8/10) - Consider this

[Evaluate All] [Show Details]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

💡 Recommendation: skill-name (FITNESS: 8.7/10)

   Best match for your needs. High quality, well-maintained,
   and specifically designed for [user's goal].

   Next best: another-skill (FITNESS: 7.2/10) if you need [alternative approach]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

按适配度分数降序排序

输出格式：

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 适配技能："[用户查询]"
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🏆 #1 skill-name ⭐ 星标数量 新鲜度标识 | 适配度：X.X/10

   质量评估：
   ✅ 描述：优秀（2.0/2.0）
   ✅ 结构：组织有序（0.9/1.0）
   ⚠️ 长度：520行（超过推荐的500行）
   ✅ 示例：包含清晰的工作流程

   整体质量：8.5/10（优秀）

   适配原因：
   • 专为[相关场景]设计
   • 提及[用户关键词]3次
   • 具备[相关功能]
   • 包含[实用能力]

   高质量原因：
   • 遵循Anthropic最佳实践
   • 示例全面
   • 工作流程清晰且有验证机制
   • 经过良好测试且维护及时

   📎 https://github.com/OWNER/REPO/blob/main/PATH/SKILL.md

   [查看完整分析] [安装]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🏆 #2 another-skill ⭐ 星标数量 新鲜度标识 | 适配度：Y.Y/10

   质量评估：
   ✅ 描述和示例良好
   ⚠️ 未完全遵循部分最佳实践
   ❌ 无渐进式披露

   整体质量：6.2/10（良好）

   适配原因：
   • 部分满足[需求]
   • 具备[部分相关功能]

   不足原因：
   • 未专注于[用户目标]
   • 质量有待提升
   • 缺少[重要功能]

   📎 https://github.com/OWNER/REPO/blob/main/SKILL.md

   [预览] [安装]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📚 来自精选列表：

在awesome-claude-skills（BehiSecc）中找到：
  • related-skill-1（适配度：7.5/10）- 匹配度良好
  • related-skill-2（适配度：5.2/10）- 部分匹配

在awesome-claude-skills（travisvn）中找到：
  • another-option（适配度：6.8/10）- 可考虑

[评估全部] [查看详情]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

💡 推荐：skill-name（适配度：8.7/10）

   最匹配你的需求，质量高、维护良好，且专为[用户目标]设计。

   次优选择：another-skill（适配度：7.2/10），如果你需要[替代方案]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Key Differences from Generic Search

与通用搜索的核心差异

Generic/Bad approach:

"Show me top 10 popular skills"
Ranks only by stars
No evaluation of actual content
No fitness to user's specific need

Query-Driven/Good approach:

"Find skills for [specific use case]"
Reads actual SKILL.md content
Evaluates against best practices
Scores fitness to user's query
Explains WHY it's a good match

通用/不佳的方式：

“展示前10个热门技能”
仅按星标数量排名
不评估实际内容
不考虑用户特定需求的适配度

基于查询/优质的方式：

“为[特定场景]查找技能”
读取实际SKILL.md内容
基于最佳实践评估
针对用户查询进行适配度评分
解释为何匹配

Evaluation Workflow

评估工作流程

Quick Evaluation (per skill ~3-4 min)

快速评估（每个技能约3-4分钟）

Fetch SKILL.md (30 sec)
Read frontmatter (30 sec)
- Check description quality
- Check name convention
Scan body (1-2 min)
- Check length
- Look for examples
- Check for references
- Note anti-patterns
Check structure (30 sec)
- Reference files?
- Scripts/utilities?
Calculate scores (30 sec)
- Quality score
- Semantic match
- Fitness score

获取SKILL.md（30秒）
阅读前置内容（30秒）
- 检查描述质量
- 检查命名规范
扫描正文（1-2分钟）
- 检查长度
- 查找示例
- 检查参考文件
- 标记反模式
检查结构（30秒）
- 是否有参考文件？
- 是否有脚本/工具？
计算分数（30秒）
- 质量分数
- 语义匹配度
- 适配度分数

Full Evaluation (for top candidates)

全面评估（针对排名靠前的候选技能）

For the top 3-5 candidates by fitness score, provide detailed analysis:

Full Analysis for: [skill-name]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 Quality Breakdown
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Description Quality:      2.0/2.0 ✅
  • Specific and clear
  • Includes what and when to use
  • Written in third person

Name Convention:          0.5/0.5 ✅
  • Follows naming rules
  • Descriptive gerund form

Conciseness:              1.3/1.5 ⚠️
  • 520 lines (over 500 recommended)
  • Could be more concise

Progressive Disclosure:   1.0/1.0 ✅
  • Excellent use of reference files
  • Well-organized structure

Examples & Workflows:     1.0/1.0 ✅
  • Clear concrete examples
  • Step-by-step workflows

Degree of Freedom:        0.5/0.5 ✅
  • Appropriate for task type

Dependencies:             0.5/0.5 ✅
  • All documented
  • Verified available

Structure:                0.9/1.0 ✅
  • Well organized
  • Minor heading inconsistencies

Error Handling:           0.4/0.5 ⚠️
  • Good scripts
  • Could improve validation

Anti-Patterns:            0.9/1.0 ✅
  • Mostly clean
  • One instance of inconsistent terminology

Testing:                  0.5/0.5 ✅
  • Clear testing approach

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Total Quality Score: 8.5/10 (Excellent)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎯 Semantic Match Analysis

User Query: "pitch deck creation"
Skill Content Analysis:
  ✅ "pitch deck" mentioned 5 times
  ✅ "presentation" mentioned 12 times
  ✅ "slides" mentioned 8 times
  ✅ Has templates section
  ✅ Has business presentation examples

Semantic Match Score: 9.2/10

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Final FITNESS Score: 8.8/10
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Recommendation: Highly Recommended ⭐⭐⭐⭐⭐

针对适配度分数排名前3-5的候选技能，提供详细分析：

技能详细分析：[skill-name]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 质量细分
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

描述质量：      2.0/2.0 ✅
  • 具体清晰
  • 包含功能和使用场景
  • 使用第三人称

命名规范：          0.5/0.5 ✅
  • 遵循命名规则
  • 采用描述性动名词形式

简洁性：              1.3/1.5 ⚠️
  • 520行（超过推荐的500行）
  • 可进一步精简

渐进式披露：   1.0/1.0 ✅
  • 优秀使用参考文件
  • 组织结构良好

示例与工作流程：     1.0/1.0 ✅
  • 示例具体清晰
  • 工作流程分步明确

自由度适配：        0.5/0.5 ✅
  • 与任务类型适配

依赖项：             0.5/0.5 ✅
  • 全部有文档说明
  • 已验证可用

结构：                0.9/1.0 ✅
  • 组织有序
  • 标题存在少量不一致

错误处理：           0.4/0.5 ⚠️
  • 脚本质量良好
  • 可提升验证机制

反模式：            0.9/1.0 ✅
  • 整体规范
  • 存在1处术语不一致

测试：                  0.5/0.5 ✅
  • 测试方法清晰

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
总质量分数：8.5/10（优秀）
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎯 语义匹配分析

用户查询：“演示文稿制作”
技能内容分析：
  ✅ “pitch deck”提及5次
  ✅ “presentation”提及12次
  ✅ “slides”提及8次
  ✅ 包含模板章节
  ✅ 包含商务演示示例

语义匹配分数：9.2/10

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
最终适配度分数：8.8/10
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

推荐等级：强烈推荐 ⭐⭐⭐⭐⭐

Reference Files

参考文件

best-practices-checklist.md - Anthropic's best practices evaluation criteria
search-strategies.md - Advanced search patterns
ranking-algorithm.md - Detailed scoring algorithms
installation-workflow.md - Installation process

best-practices-checklist.md - Anthropic最佳实践评估标准
search-strategies.md - 高级搜索模式
ranking-algorithm.md - 详细评分算法
installation-workflow.md - 安装流程

Example Usage

示例用法

See examples/sample-output.md for complete output examples.

完整输出示例请参考examples/sample-output.md。

Error Handling

错误处理

No results found:

No skills found for: "[user query]"

Suggestions:
• Try broader search terms
• Check if query is too specific
• Search awesome-lists directly
• Consider creating a custom skill

Low fitness scores (all < 5.0):

⚠️  Found skills but none are a strong match.

Best partial matches:
1. [skill-name] (FITNESS: 4.2/10) - Missing [key feature]
2. [skill-name] (FITNESS: 3.8/10) - Different focus

Consider:
• Combine multiple skills
• Request skill from awesome-list curators
• Create custom skill for your specific need

GitHub API rate limit:

⚠️  GitHub API rate limit reached.

Current: 0/60 requests remaining (unauthenticated)
Resets: in 42 minutes

Solution:
export GH_TOKEN="your_github_token"

This increases limit to 5000/hour.

未找到结果：

未找到适配“[用户查询]”的技能

建议：
• 尝试更宽泛的搜索词
• 检查查询是否过于具体
• 直接搜索精选列表
• 考虑创建自定义技能

适配度分数较低（全部<5.0）：

⚠️ 找到技能但无强匹配项

最佳部分匹配项：
1. [skill-name]（适配度：4.2/10）- 缺少[关键功能]
2. [skill-name]（适配度：3.8/10）- 关注点不同

建议：
• 组合多个技能
• 向精选列表维护者请求技能
• 为你的特定需求创建自定义技能

GitHub API速率限制：

⚠️ 达到GitHub API速率限制

当前：0/60次剩余请求（未认证）
重置时间：42分钟后

解决方案：
export GH_TOKEN="your_github_token"

这会将限制提升至5000次/小时。

Performance Optimization

性能优化

Parallel execution:

bash

undefined

并行执行：

bash

undefined

Run searches in parallel

并行运行搜索

{ gh search repos "claude skills $QUERY" > repos.json & gh search code "$QUERY" "filename:SKILL.md" > code.json & gh search repos "awesome-claude-skills" > awesome.json & wait }


**Caching:**
```bash

{ gh search repos "claude skills $QUERY" > repos.json & gh search code "$QUERY" "filename:SKILL.md" > code.json & gh search repos "awesome-claude-skills" > awesome.json & wait }


**缓存：**
```bash

Cache skill evaluations for 1 hour

缓存技能评估结果1小时

cache_file=".skill-eval-cache/$repo_owner-$repo_name.json" if [ -f "$cache_file" ] && [ $(($(date +%s) - $(stat -f %m "$cache_file"))) -lt 3600 ]; then cat "$cache_file" else evaluate_skill | tee "$cache_file" fi

undefined

undefined

Quality Tiers

质量等级

Based on fitness score:

9.0-10.0: Perfect match - Highly Recommended ⭐⭐⭐⭐⭐
7.0-8.9: Excellent match - Recommended ⭐⭐⭐⭐
5.0-6.9: Good match - Consider ⭐⭐⭐
3.0-4.9: Partial match - Review carefully ⭐⭐
0.0-2.9: Poor match - Not recommended ⭐

基于适配度分数：

9.0-10.0： 完美匹配 - 强烈推荐 ⭐⭐⭐⭐⭐
7.0-8.9： 优秀匹配 - 推荐 ⭐⭐⭐⭐
5.0-6.9： 良好匹配 - 可考虑 ⭐⭐⭐
3.0-4.9： 部分匹配 - 仔细评估 ⭐⭐
0.0-2.9： 匹配度差 - 不推荐 ⭐

Important Notes

重要说明

This is NOT:

本工具不是：

A "show popular skills" tool
A generic ranking by stars
A list of all skills

“展示热门技能”工具
仅按星标数量排名的通用榜单
所有技能的列表

This IS:

本工具是：

A query-driven semantic matcher
A quality evaluator against Anthropic best practices
A fitness scorer for your specific need
A recommendation engine

基于查询的语义匹配器
基于Anthropic最佳实践的质量评估器
针对特定需求的适配度评分器
推荐引擎

Always:

请始终：

Read actual SKILL.md content (don't just use metadata)
Evaluate against best practices checklist
Score fitness to user's specific query
Explain WHY a skill fits or doesn't fit
Show quality assessment, not just stars

Remember: The goal is to find the RIGHT skill for the user's SPECIFIC need, not just show what's popular.

读取实际SKILL.md内容（不要仅依赖元数据）
基于最佳实践清单评估
针对用户特定查询评分适配度
解释技能适配或不适配的原因
展示质量评估结果，而不仅仅是星标数量

记住： 目标是为用户的特定需求找到最合适的技能，而不仅仅是展示热门技能。