Skill Hunter

Use when: You need to discover existing skills from GitHub repositories that use AI agent frameworks (pi, cursor, opencode, etc.) - searches across multiple agent directories to find reusable skill patterns, implementations, and best practices.

适用场景： 当你需要从使用AI agent框架（pi、cursor、opencode等）的GitHub仓库中发现现有Skill时使用——可跨多个agent目录搜索，找到可复用的Skill模式、实现方案及最佳实践。

Core Capability

核心能力

Search GitHub for skills in AI agent repositories using path-based search to discover:

Skill implementations from other projects
Common patterns and approaches
Reusable skill definitions
Best practices from the community

通过基于路径的搜索在GitHub的AI agent仓库中查找Skill，可发现：

其他项目中的Skill实现
通用模式与方法
可复用的Skill定义
社区总结的最佳实践

Prerequisites

前置条件

```
gh
```
CLI installed and authenticated
```
jq
```
for JSON processing
```
$DOTFILES_REPO_ROOT
```
environment variable set (or will auto-detect)
Skills stored in
```
$DOTFILES_REPO_ROOT/ai/files/skills/
```

已安装并认证
```
gh
```
CLI
已安装
```
jq
```
用于JSON处理
已设置
```
$DOTFILES_REPO_ROOT
```
环境变量（或会自动检测）
Skill存储在
```
$DOTFILES_REPO_ROOT/ai/files/skills/
```
目录下

GitHub Search Syntax

GitHub搜索语法

The core search pattern targets skill directories in AI agent repos:

bash

path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)\/skills?\/.*\.md$/

This pattern finds files in paths like:

```
.pi/skills/
```
```
.ai/skills/
```
```
.opencode/skill/
```
```
pi/skills/
```
```
agents/skills/
```
```
cursor/skills/
```
```
factory/skill/
```

核心搜索模式针对AI agent仓库中的Skill目录：

bash

path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)\/skills?\/.*\.md$/

该模式可匹配如下路径中的文件：

```
.pi/skills/
```
```
.ai/skills/
```
```
.opencode/skill/
```
```
pi/skills/
```
```
agents/skills/
```
```
cursor/skills/
```
```
factory/skill/
```

Implementation Pattern

实现模式

1. Basic Skill Search

1. 基础Skill搜索

Search for all skills matching a keyword:

bash

undefined

搜索所有匹配关键词的Skill：

bash

undefined

Search for skills related to "testing"

Search for zellij skills

undefined

undefined

2. Find Skills by File Type

2. 按文件类型查找Skill

Search for specific file types (e.g., all SKILL.md files):

bash

undefined

搜索特定文件类型（例如所有SKILL.md文件）：

bash

undefined

Find SKILL.md files

Find skill implementations in TypeScript

Find shell script skills

undefined

undefined

3. Language-Specific Skills

3. 特定语言的Skill

bash

undefined

bash

undefined

Find Python skills

Find JavaScript/TypeScript skills

Find Rust skills

undefined

undefined

4. Find Skills by Domain

4. 按领域查找Skill

bash

undefined

bash

undefined

Database skills

DevOps skills

Web development skills

Testing skills

undefined

undefined

5. Discover Popular Repositories

5. 发现热门仓库

Find repos with the most skills:

bash

undefined

查找包含最多Skill的仓库：

bash

undefined

Search and group by repository

undefined

undefined

6. Download and Inspect Skills

6. 下载并查看Skill

Once you find an interesting skill:

bash

undefined

找到感兴趣的Skill后：

bash

undefined

View a specific file directly

gh browse <owner>/<repo> --branch main <path-to-skill-file>

Clone the entire repository

gh repo clone <owner>/<repo>

Download a specific file

gh api repos/<owner>/<repo>/contents/<path-to-skill-file>
--jq '.content' | base64 -d > downloaded-skill.md

undefined

gh api repos/<owner>/<repo>/contents/<path-to-skill-file>
--jq '.content' | base64 -d > downloaded-skill.md

undefined

Complete Workflow Example

完整工作流示例

Scenario: Finding and Adapting a Zellij Skill

场景：查找并适配Zellij Skill

bash

undefined

bash

undefined

1. Search for zellij skills

2. Search more broadly for terminal multiplexer skills

3. Examine a promising result

REPO="username/repo-name" SKILL_PATH=".pi/skills/terminal-management/SKILL.md"

gh api "repos/${REPO}/contents/${SKILL_PATH}"
--jq '.content' | base64 -d | less

REPO="username/repo-name" SKILL_PATH=".pi/skills/terminal-management/SKILL.md"

gh api "repos/${REPO}/contents/${SKILL_PATH}"
--jq '.content' | base64 -d | less

4. Download for adaptation

gh api "repos/${REPO}/contents/${SKILL_PATH}"
--jq '.content' | base64 -d > /tmp/reference-skill.md

echo "Downloaded to /tmp/reference-skill.md for review"

undefined

gh api "repos/${REPO}/contents/${SKILL_PATH}"
--jq '.content' | base64 -d > /tmp/reference-skill.md

echo "Downloaded to /tmp/reference-skill.md for review"

undefined

Advanced Search Patterns

高级搜索模式

Find Recently Updated Skills

查找最近更新的Skill

bash

undefined

bash

undefined

Skills updated in the last month

undefined

undefined

Find Skills by Star Count

按星标数量查找Skill

bash

undefined

bash

undefined

Skills from popular repositories (>100 stars)

undefined

undefined

Find Skills with Specific Patterns

查找包含特定模式的Skill

bash

undefined

bash

undefined

Skills that use subagents

Skills that use MCP (Model Context Protocol)

Skills with tool implementations

undefined

undefined

Output Processing

输出处理

Extract and Format Results

提取并格式化结果

bash

undefined

bash

undefined

Get a clean list of repositories with skills

Create a markdown report of found skills

undefined

undefined

Common Use Cases

常见使用场景

1. Before Writing a New Skill

1. 编写新Skill之前

bash

undefined

bash

undefined

Check if someone already solved this problem

SKILL_TOPIC="docker" gh search code "${SKILL_TOPIC} path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)/skills?/.*.md$/"
--limit 20
--json repository,path,url |
jq -r '.[] | "[(.repository.fullName)] (.path)\n (.url)\n"'

undefined

SKILL_TOPIC="docker" gh search code "${SKILL_TOPIC} path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)/skills?/.*.md$/"
--limit 20
--json repository,path,url |
jq -r '.[] | "[(.repository.fullName)] (.path)\n (.url)\n"'

undefined

2. Finding Best Practices

2. 查找最佳实践

bash

undefined

bash

undefined

Find skills with comprehensive documentation

undefined

undefined

3. Discovering Skill Patterns

3. 发现Skill模式

bash

undefined

bash

undefined

Find skills that use specific frameworks

undefined

undefined

Integration with Dotfiles

与Dotfiles集成

Save Discovered Skills for Reference

保存发现的Skill用于参考

Skills should be stored in your Dotfiles repo under

ai/files/skills/

. When discovering skills, save them to a research directory first:

bash

undefined

Skill应存储在你的Dotfiles仓库的

ai/files/skills/

目录下。发现Skill时，先将其保存到研究目录：

bash

undefined

Use dotfiles environment variable (fallback to detection if not set)

DOTFILES_ROOT="${DOTFILES_REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || echo "${HOME}/Projects/dotfiles")}" SKILLS_ROOT="${DOTFILES_ROOT}/ai/files/skills" RESEARCH_DIR="${DOTFILES_ROOT}/ai/files/skills-research"

Create a skills research directory

mkdir -p "${RESEARCH_DIR}"

Download and categorize interesting skills

CATEGORY="terminal-management" mkdir -p "${RESEARCH_DIR}/${CATEGORY}"

Save search results

gh search code "tmux OR zellij OR screen path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)/skills?/.*.md$/"
--limit 30
--json repository,path,url > "${RESEARCH_DIR}/${CATEGORY}/search-results.json"

Extract and download top results

jq -r '.[] | "(.repository.fullName)|(.path)|(.url)"'
"${RESEARCH_DIR}/${CATEGORY}/search-results.json" |
head -5 |
while IFS='|' read repo path url; do echo "Downloading: ${repo} - ${path}" gh api "repos/${repo}/contents/${path}" --jq '.content' | base64 -d >
"${RESEARCH_DIR}/${CATEGORY}/$(echo ${repo} | tr '/' '-')-$(basename ${path})" done

undefined

jq -r '.[] | "(.repository.fullName)|(.path)|(.url)"'
"${RESEARCH_DIR}/${CATEGORY}/search-results.json" |
head -5 |
while IFS='|' read repo path url; do echo "Downloading: ${repo} - ${path}" gh api "repos/${repo}/contents/${path}" --jq '.content' | base64 -d >
"${RESEARCH_DIR}/${CATEGORY}/$(echo ${repo} | tr '/' '-')-$(basename ${path})" done

undefined

Suggest Storage Location

建议存储位置

After downloading and reviewing a skill, suggest appropriate locations within

ai/files/skills/

:

bash

undefined

下载并查看Skill后，建议将其存储在

ai/files/skills/

下的合适位置：

bash

undefined

Function to suggest skill locations

suggest_skill_location() { local skill_name="$1" local skill_content="$2"

echo "📂 Where should '${skill_name}' be stored in ai/files/skills/?" echo ""

Analyze content to suggest locations

if grep -qi "github|gh cli|pull request|pr|issue" "${skill_content}"; then echo "1. ai/files/skills/github/${skill_name}/" echo " ✓ GitHub-related functionality" fi

if grep -qi "test|playwright|selenium|cypress" "${skill_content}"; then echo "2. ai/files/skills/devtools/${skill_name}/" echo " ✓ Development and testing tools" fi

if grep -qi "project|task|planning|tracking" "${skill_content}"; then echo "3. ai/files/skills/projectmanagement/${skill_name}/" echo " ✓ Project management and workflow" fi

if grep -qi "design|ui|ux|figma" "${skill_content}"; then echo "4. ai/files/skills/design/${skill_name}/" echo " ✓ Design-related skills" fi

if grep -qi "research|search|discover" "${skill_content}"; then echo "5. ai/files/skills/research/${skill_name}/" echo " ✓ Research and discovery" fi

echo "" echo "Choose a number (1-5), or provide your own path:" echo "Example: ai/files/skills/custom-category/${skill_name}/" }

suggest_skill_location() { local skill_name="$1" local skill_content="$2"

echo "📂 Where should '${skill_name}' be stored in ai/files/skills/?" echo ""

Analyze content to suggest locations

if grep -qi "github|gh cli|pull request|pr|issue" "${skill_content}"; then echo "1. ai/files/skills/github/${skill_name}/" echo " ✓ GitHub-related functionality" fi

if grep -qi "test|playwright|selenium|cypress" "${skill_content}"; then echo "2. ai/files/skills/devtools/${skill_name}/" echo " ✓ Development and testing tools" fi

if grep -qi "project|task|planning|tracking" "${skill_content}"; then echo "3. ai/files/skills/projectmanagement/${skill_name}/" echo " ✓ Project management and workflow" fi

if grep -qi "design|ui|ux|figma" "${skill_content}"; then echo "4. ai/files/skills/design/${skill_name}/" echo " ✓ Design-related skills" fi

if grep -qi "research|search|discover" "${skill_content}"; then echo "5. ai/files/skills/research/${skill_name}/" echo " ✓ Research and discovery" fi

echo "" echo "Choose a number (1-5), or provide your own path:" echo "Example: ai/files/skills/custom-category/${skill_name}/" }

Usage example

SKILL_FILE="${RESEARCH_DIR}/terminal-management/example-skill.md" SKILL_NAME="zellij-manager"

suggest_skill_location "${SKILL_NAME}" "${SKILL_FILE}" read -r location_choice

case $location_choice in

TARGET_DIR="${SKILLS_ROOT}/github/${SKILL_NAME}" ;;
TARGET_DIR="${SKILLS_ROOT}/devtools/${SKILL_NAME}" ;;
TARGET_DIR="${SKILLS_ROOT}/projectmanagement/${SKILL_NAME}" ;;
TARGET_DIR="${SKILLS_ROOT}/design/${SKILL_NAME}" ;;
TARGET_DIR="${SKILLS_ROOT}/research/${SKILL_NAME}" ;; *) # User provided custom path if [[ "$location_choice" =~ ^ai/files/skills/ ]]; then TARGET_DIR="${DOTFILES_ROOT}/${location_choice}" else TARGET_DIR="${SKILLS_ROOT}/${location_choice}" fi ;; esac

SKILL_FILE="${RESEARCH_DIR}/terminal-management/example-skill.md" SKILL_NAME="zellij-manager"

suggest_skill_location "${SKILL_NAME}" "${SKILL_FILE}" read -r location_choice

case $location_choice in

TARGET_DIR="${SKILLS_ROOT}/github/${SKILL_NAME}" ;;
TARGET_DIR="${SKILLS_ROOT}/devtools/${SKILL_NAME}" ;;
TARGET_DIR="${SKILLS_ROOT}/projectmanagement/${SKILL_NAME}" ;;
TARGET_DIR="${SKILLS_ROOT}/design/${SKILL_NAME}" ;;
TARGET_DIR="${SKILLS_ROOT}/research/${SKILL_NAME}" ;; *) # User provided custom path if [[ "$location_choice" =~ ^ai/files/skills/ ]]; then TARGET_DIR="${DOTFILES_ROOT}/${location_choice}" else TARGET_DIR="${SKILLS_ROOT}/${location_choice}" fi ;; esac

Create target directory and move skill

mkdir -p "${TARGET_DIR}" cp "${SKILL_FILE}" "${TARGET_DIR}/SKILL.md" echo "✅ Skill moved to: ${TARGET_DIR}"

undefined

mkdir -p "${TARGET_DIR}" cp "${SKILL_FILE}" "${TARGET_DIR}/SKILL.md" echo "✅ Skill moved to: ${TARGET_DIR}"

undefined

Tips and Tricks

技巧与窍门

1. Fuzzy Matching with Wildcards

1. 通配符模糊匹配

The regex in the path already handles variations like

skill

vs

skills

with the

quantifier.

路径中的正则表达式已通过

量词处理了

skill

与

skills

这类变体。

2. Combine with Other Search Terms

2. 组合其他搜索词

bash

undefined

bash

undefined

Find skills that mention specific tools

undefined

undefined

3. Language-Specific Searches

3. 特定语言搜索

bash

undefined

bash

undefined

Find skills written in specific languages with content search

undefined

undefined

4. Exclude Certain Repos

4. 排除特定仓库

bash

undefined

bash

undefined

Search but exclude your own repos

undefined

undefined

Error Handling

错误处理

bash

undefined

bash

undefined

Check if gh CLI is installed and authenticated

if ! command -v gh &> /dev/null; then echo "Error: GitHub CLI (gh) is not installed" echo "Install with: brew install gh (macOS) or apt install gh (Linux)" exit 1 fi

if ! gh auth status &> /dev/null; then echo "Error: Not authenticated with GitHub" echo "Run: gh auth login" exit 1 fi

if ! command -v gh &> /dev/null; then echo "Error: GitHub CLI (gh) is not installed" echo "Install with: brew install gh (macOS) or apt install gh (Linux)" exit 1 fi

if ! gh auth status &> /dev/null; then echo "Error: Not authenticated with GitHub" echo "Run: gh auth login" exit 1 fi

Handle rate limiting

gh search code "path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)/skills?/.*.md$/"
--limit 30 || { echo "Error: GitHub API rate limit exceeded" echo "Check status: gh api rate_limit" exit 1 }

undefined

gh search code "path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)/skills?/.*.md$/"
--limit 30 || { echo "Error: GitHub API rate limit exceeded" echo "Check status: gh api rate_limit" exit 1 }

undefined

Best Practices

最佳实践

Start Broad, Then Narrow: Begin with general searches, then refine based on results
Check Multiple Frameworks: Skills from cursor might work in pi and vice versa
Look for Patterns: Similar problems often have similar solutions across repos
Respect Licenses: Check repository licenses before adapting code
Credit Sources: When adapting skills, note the original source
Update Your Own Skills: Share back improved versions to help others

由广到窄：先从通用搜索开始，再根据结果逐步细化
多框架检查：cursor中的Skill也可能在pi中适用，反之亦然
寻找模式：相似问题通常在不同仓库中有相似的解决方案
尊重许可证：在适配代码前检查仓库许可证
注明来源：适配Skill时，记录原始来源
更新自有Skill：分享改进后的版本，帮助他人

Example: Complete Skill Discovery Session

示例：完整的Skill发现会话

bash

#!/bin/bash

bash

#!/bin/bash

skill-discovery.sh - Discover and analyze skills for a specific topic

TOPIC="${1:-testing}"

Use dotfiles environment variable

DOTFILES_ROOT="${DOTFILES_REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || echo "${HOME}/Projects/dotfiles")}" SKILLS_ROOT="${DOTFILES_ROOT}/ai/files/skills" RESEARCH_DIR="${DOTFILES_ROOT}/ai/files/skills-research" OUTPUT_DIR="${RESEARCH_DIR}/${TOPIC}"

mkdir -p "${OUTPUT_DIR}"

echo "🔍 Discovering skills related to: ${TOPIC}" echo "📍 Dotfiles: ${DOTFILES_ROOT}" echo "📂 Research output: ${OUTPUT_DIR}" echo ""

DOTFILES_ROOT="${DOTFILES_REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || echo "${HOME}/Projects/dotfiles")}" SKILLS_ROOT="${DOTFILES_ROOT}/ai/files/skills" RESEARCH_DIR="${DOTFILES_ROOT}/ai/files/skills-research" OUTPUT_DIR="${RESEARCH_DIR}/${TOPIC}"

mkdir -p "${OUTPUT_DIR}"

echo "🔍 Discovering skills related to: ${TOPIC}" echo "📍 Dotfiles: ${DOTFILES_ROOT}" echo "📂 Research output: ${OUTPUT_DIR}" echo ""

1. Initial search

echo "Step 1: Searching GitHub..." gh search code "${TOPIC} path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)/skills?/.*.md$/"
--limit 50
--json repository,path,url \

"${OUTPUT_DIR}/search-results.json"

RESULT_COUNT=$(jq length "${OUTPUT_DIR}/search-results.json") echo "Found ${RESULT_COUNT} results"

echo "Step 1: Searching GitHub..." gh search code "${TOPIC} path:/^./.?(opencode|ai|llm|claude|codex|agents|pi|cursor|factory)/skills?/.*.md$/"
--limit 50
--json repository,path,url \

"${OUTPUT_DIR}/search-results.json"

RESULT_COUNT=$(jq length "${OUTPUT_DIR}/search-results.json") echo "Found ${RESULT_COUNT} results"

2. Analyze repositories

echo "Step 2: Analyzing repositories..." jq -r '.[].repository.fullName' "${OUTPUT_DIR}/search-results.json" |
sort | uniq -c | sort -rn |
head -10 > "${OUTPUT_DIR}/top-repos.txt"

echo "Top repositories with ${TOPIC} skills:" cat "${OUTPUT_DIR}/top-repos.txt"

echo "Step 2: Analyzing repositories..." jq -r '.[].repository.fullName' "${OUTPUT_DIR}/search-results.json" |
sort | uniq -c | sort -rn |
head -10 > "${OUTPUT_DIR}/top-repos.txt"

echo "Top repositories with ${TOPIC} skills:" cat "${OUTPUT_DIR}/top-repos.txt"

3. Download top 3 skill files

echo "Step 3: Downloading sample skills..." jq -r '.[0:3] | .[] | "(.repository.fullName)|(.path)"'
"${OUTPUT_DIR}/search-results.json" |
while IFS='|' read repo path; do filename=$(echo "${repo}-${path}" | tr '/' '-') echo " Downloading: ${repo}/${path}" gh api "repos/${repo}/contents/${path}"
--jq '.content' | base64 -d
> "${OUTPUT_DIR}/${filename}" 2>/dev/null ||
echo " Failed to download" done

4. Create summary report

echo "Step 4: Creating summary report..." cat > "${OUTPUT_DIR}/DISCOVERY-REPORT.md" << EOF

Skill Discovery Report: ${TOPIC}

Date: $(date) Total Results: ${RESULT_COUNT} Dotfiles Root: ${DOTFILES_ROOT}

Top Repositories

``` $(cat "${OUTPUT_DIR}/top-repos.txt") ```

All Results

$(jq -r '.[] | "- (.repository.fullName)) - (.path))"'
"${OUTPUT_DIR}/search-results.json")

Storage Locations

Review downloaded skills and determine appropriate location in:

``` ${SKILLS_ROOT}/ ├── github/ # GitHub-related functionality ├── devtools/ # Development and testing tools ├── projectmanagement/ # Project and task management ├── design/ # Design and UI/UX tools ├── research/ # Research and discovery ├── superpowers/ # Advanced meta-skills ├── experts/ # Domain expert personas └── [custom]/ # Your custom categories ```

Review downloaded skills and determine appropriate location in:

``` ${SKILLS_ROOT}/ ├── github/ # GitHub-related functionality ├── devtools/ # Development and testing tools ├── projectmanagement/ # Project and task management ├── design/ # Design and UI/UX tools ├── research/ # Research and discovery ├── superpowers/ # Advanced meta-skills ├── experts/ # Domain expert personas └── [custom]/ # Your custom categories ```

Next Steps

Review downloaded skill files in: ${OUTPUT_DIR}
Identify common patterns and best practices
Choose appropriate location in ai/files/skills/
Adapt for your use case
Consider contributing improvements back

Review downloaded skill files in: ${OUTPUT_DIR}
Identify common patterns and best practices
Choose appropriate location in ai/files/skills/
Adapt for your use case
Consider contributing improvements back

Move to Skills Directory

```bash

Example: Move adapted skill to appropriate location

SKILL_NAME="my-new-skill"

Option 1: GitHub-related

mkdir -p "${SKILLS_ROOT}/github/${SKILL_NAME}" cp adapted-skill.md "${SKILLS_ROOT}/github/${SKILL_NAME}/SKILL.md"

Option 2: DevTools

mkdir -p "${SKILLS_ROOT}/devtools/${SKILL_NAME}" cp adapted-skill.md "${SKILLS_ROOT}/devtools/${SKILL_NAME}/SKILL.md"

Option 3: Custom location

mkdir -p "${SKILLS_ROOT}/custom-category/${SKILL_NAME}" cp adapted-skill.md "${SKILLS_ROOT}/custom-category/${SKILL_NAME}/SKILL.md" ```

EOF

echo "✅ Discovery complete! Report saved to: ${OUTPUT_DIR}/DISCOVERY-REPORT.md" echo "" echo "Next: Review skills and move to ${SKILLS_ROOT}/"

undefined

mkdir -p "${SKILLS_ROOT}/custom-category/${SKILL_NAME}" cp adapted-skill.md "${SKILLS_ROOT}/custom-category/${SKILL_NAME}/SKILL.md" ```

EOF

echo "✅ Discovery complete! Report saved to: ${OUTPUT_DIR}/DISCOVERY-REPORT.md" echo "" echo "Next: Review skills and move to ${SKILLS_ROOT}/"

undefined

Skill Storage Workflow

Skill存储工作流

After discovering and adapting a skill, follow this workflow:

发现并适配Skill后，遵循以下工作流：

1. Analyze Skill Content

1. 分析Skill内容

Review the skill to determine its primary purpose:

bash

SKILL_FILE="downloaded-skill.md"

echo "Analyzing skill content..."
echo ""
echo "Contains GitHub functionality:" $(grep -qi "github\|gh cli" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")
echo "Contains testing tools:" $(grep -qi "test\|playwright\|selenium" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")
echo "Contains project management:" $(grep -qi "project\|task\|planning" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")
echo "Contains design tools:" $(grep -qi "design\|ui\|figma" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")
echo "Contains research tools:" $(grep -qi "research\|search\|discover" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")

查看Skill以确定其主要用途：

bash

SKILL_FILE="downloaded-skill.md"

echo "Analyzing skill content..."
echo ""
echo "Contains GitHub functionality:" $(grep -qi "github\|gh cli" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")
echo "Contains testing tools:" $(grep -qi "test\|playwright\|selenium" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")
echo "Contains project management:" $(grep -qi "project\|task\|planning" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")
echo "Contains design tools:" $(grep -qi "design\|ui\|figma" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")
echo "Contains research tools:" $(grep -qi "research\|search\|discover" "$SKILL_FILE" && echo "✓ Yes" || echo "✗ No")

2. Present Storage Options

2. 展示存储选项

Present 1-3 suggested locations based on content analysis:

📂 Where should this skill be stored in ai/files/skills/?

Suggested locations:

1. ai/files/skills/github/skill-name/
   ✓ Contains GitHub API usage
   ✓ Uses gh CLI extensively

2. ai/files/skills/research/skill-name/
   ✓ Primary purpose is discovery/research
   ✓ Searches external sources

3. ai/files/skills/devtools/skill-name/
   ✓ Developer tooling functionality
   ✓ Enhances development workflow

Choose a number (1-3), or provide your own path:
Example: ai/files/skills/custom-category/skill-name/

根据内容分析展示1-3个建议存储位置：

📂 Where should this skill be stored in ai/files/skills/?

Suggested locations:

1. ai/files/skills/github/skill-name/
   ✓ Contains GitHub API usage
   ✓ Uses gh CLI extensively

2. ai/files/skills/research/skill-name/
   ✓ Primary purpose is discovery/research
   ✓ Searches external sources

3. ai/files/skills/devtools/skill-name/
   ✓ Developer tooling functionality
   ✓ Enhances development workflow

Choose a number (1-3), or provide your own path:
Example: ai/files/skills/custom-category/skill-name/

3. Interactive Selection Script

3. 交互式选择脚本

bash

#!/bin/bash

bash

#!/bin/bash

store-skill.sh - Interactive skill storage helper

SKILL_FILE="$1" SKILL_NAME="$2"

if [[ -z "$SKILL_FILE" || -z "$SKILL_NAME" ]]; then echo "Usage: $0 <skill-file> <skill-name>" exit 1 fi

SKILL_FILE="$1" SKILL_NAME="$2"

if [[ -z "$SKILL_FILE" || -z "$SKILL_NAME" ]]; then echo "Usage: $0 <skill-file> <skill-name>" exit 1 fi

Use dotfiles environment variable

DOTFILES_ROOT="${DOTFILES_REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || echo "${HOME}/Projects/dotfiles")}" SKILLS_ROOT="${DOTFILES_ROOT}/ai/files/skills"

Analyze content

echo "🔍 Analyzing skill content..." echo ""

SUGGESTIONS=() COUNT=1

if grep -qi "github|gh cli|pull request|issue" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:github:GitHub-related functionality") echo "${COUNT}. ai/files/skills/github/${SKILL_NAME}/" echo " ✓ GitHub-related functionality" echo "" ((COUNT++)) fi

if grep -qi "test|playwright|selenium|cypress|jest" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:devtools:Testing and development tools") echo "${COUNT}. ai/files/skills/devtools/${SKILL_NAME}/" echo " ✓ Testing and development tools" echo "" ((COUNT++)) fi

if grep -qi "project|task|planning|tracking|workflow" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:projectmanagement:Project management") echo "${COUNT}. ai/files/skills/projectmanagement/${SKILL_NAME}/" echo " ✓ Project management and workflow" echo "" ((COUNT++)) fi

if grep -qi "design|ui|ux|figma|sketch" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:design:Design tools") echo "${COUNT}. ai/files/skills/design/${SKILL_NAME}/" echo " ✓ Design and UI/UX tools" echo "" ((COUNT++)) fi

if grep -qi "research|search|discover|analyze" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:research:Research and discovery") echo "${COUNT}. ai/files/skills/research/${SKILL_NAME}/" echo " ✓ Research and discovery" echo "" ((COUNT++)) fi

echo "🔍 Analyzing skill content..." echo ""

SUGGESTIONS=() COUNT=1

if grep -qi "github|gh cli|pull request|issue" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:github:GitHub-related functionality") echo "${COUNT}. ai/files/skills/github/${SKILL_NAME}/" echo " ✓ GitHub-related functionality" echo "" ((COUNT++)) fi

if grep -qi "test|playwright|selenium|cypress|jest" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:devtools:Testing and development tools") echo "${COUNT}. ai/files/skills/devtools/${SKILL_NAME}/" echo " ✓ Testing and development tools" echo "" ((COUNT++)) fi

if grep -qi "project|task|planning|tracking|workflow" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:projectmanagement:Project management") echo "${COUNT}. ai/files/skills/projectmanagement/${SKILL_NAME}/" echo " ✓ Project management and workflow" echo "" ((COUNT++)) fi

if grep -qi "design|ui|ux|figma|sketch" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:design:Design tools") echo "${COUNT}. ai/files/skills/design/${SKILL_NAME}/" echo " ✓ Design and UI/UX tools" echo "" ((COUNT++)) fi

if grep -qi "research|search|discover|analyze" "$SKILL_FILE"; then SUGGESTIONS+=("${COUNT}:research:Research and discovery") echo "${COUNT}. ai/files/skills/research/${SKILL_NAME}/" echo " ✓ Research and discovery" echo "" ((COUNT++)) fi

If no suggestions, show common categories

if [[ ${#SUGGESTIONS[@]} -eq 0 ]]; then echo "No specific category detected. Common options:" echo "" echo "1. ai/files/skills/devtools/${SKILL_NAME}/" echo "2. ai/files/skills/superpowers/${SKILL_NAME}/" echo "3. ai/files/skills/experts/${SKILL_NAME}/" echo "" fi

echo "Choose a number, or provide your own path:" echo "Example: ai/files/skills/my-category/${SKILL_NAME}/" echo "" read -r -p "Selection: " choice

if [[ ${#SUGGESTIONS[@]} -eq 0 ]]; then echo "No specific category detected. Common options:" echo "" echo "1. ai/files/skills/devtools/${SKILL_NAME}/" echo "2. ai/files/skills/superpowers/${SKILL_NAME}/" echo "3. ai/files/skills/experts/${SKILL_NAME}/" echo "" fi

echo "Choose a number, or provide your own path:" echo "Example: ai/files/skills/my-category/${SKILL_NAME}/" echo "" read -r -p "Selection: " choice

Process choice

TARGET_DIR="" if [[ "$choice" =~ ^[0-9]+$ ]] && [[ "$choice" -le "${#SUGGESTIONS[@]}" ]]; then

Numbered choice

CATEGORY=$(echo "${SUGGESTIONS[$((choice-1))]}" | cut -d: -f2) TARGET_DIR="${SKILLS_ROOT}/${CATEGORY}/${SKILL_NAME}" elif [[ "$choice" =~ ^ai/files/skills/ ]]; then

Full path provided

TARGET_DIR="${DOTFILES_ROOT}/${choice}" else

Relative path assumed

TARGET_DIR="${SKILLS_ROOT}/${choice}" fi

TARGET_DIR="" if [[ "$choice" =~ ^[0-9]+$ ]] && [[ "$choice" -le "${#SUGGESTIONS[@]}" ]]; then

Numbered choice

CATEGORY=$(echo "${SUGGESTIONS[$((choice-1))]}" | cut -d: -f2) TARGET_DIR="${SKILLS_ROOT}/${CATEGORY}/${SKILL_NAME}" elif [[ "$choice" =~ ^ai/files/skills/ ]]; then

Full path provided

TARGET_DIR="${DOTFILES_ROOT}/${choice}" else

Relative path assumed

TARGET_DIR="${SKILLS_ROOT}/${choice}" fi

Create and copy

mkdir -p "${TARGET_DIR}" cp "${SKILL_FILE}" "${TARGET_DIR}/SKILL.md"

echo "" echo "✅ Skill stored at: ${TARGET_DIR}/SKILL.md" echo "" echo "Next steps:" echo "1. Review and edit: ${TARGET_DIR}/SKILL.md" echo "2. Add frontmatter if needed (name, description)" echo "3. Commit to dotfiles repo"

undefined

mkdir -p "${TARGET_DIR}" cp "${SKILL_FILE}" "${TARGET_DIR}/SKILL.md"

echo "" echo "✅ Skill stored at: ${TARGET_DIR}/SKILL.md" echo "" echo "Next steps:" echo "1. Review and edit: ${TARGET_DIR}/SKILL.md" echo "2. Add frontmatter if needed (name, description)" echo "3. Commit to dotfiles repo"

undefined

4. Commit to Dotfiles

4. 提交到Dotfiles

After storing the skill:

bash

cd "${DOTFILES_ROOT}"
git add "ai/files/skills/${CATEGORY}/${SKILL_NAME}/"
git commit -m "feat(skills): add ${SKILL_NAME} skill

Discovered from GitHub search, adapted for local use.
Stored in ${CATEGORY} category."
git push

存储Skill后：

bash

cd "${DOTFILES_ROOT}"
git add "ai/files/skills/${CATEGORY}/${SKILL_NAME}/"
git commit -m "feat(skills): add ${SKILL_NAME} skill

Discovered from GitHub search, adapted for local use.
Stored in ${CATEGORY} category."
git push

另请参阅

github: Core GitHub CLI skill
writing-skills: Creating and editing skills
superpowers/brainstorming: Design before implementation

github: 核心GitHub CLI Skill
writing-skills: 创建与编辑Skill
superpowers/brainstorming: 实现前的设计环节

skill-hunter

Original

Translation

Skill Hunter

Skill Hunter

Core Capability

核心能力

Prerequisites

前置条件

GitHub Search Syntax

GitHub搜索语法

Implementation Pattern

实现模式

1. Basic Skill Search

1. 基础Skill搜索

Search for skills related to "testing"

Search for skills related to "testing"

Search for zellij skills

Search for zellij skills

2. Find Skills by File Type

2. 按文件类型查找Skill

Find SKILL.md files

Find SKILL.md files

Find skill implementations in TypeScript

Find skill implementations in TypeScript

Find shell script skills

Find shell script skills

3. Language-Specific Skills

3. 特定语言的Skill

Find Python skills

Find Python skills

Find JavaScript/TypeScript skills

Find JavaScript/TypeScript skills

Find Rust skills

Find Rust skills

4. Find Skills by Domain

4. 按领域查找Skill

Database skills

Database skills

DevOps skills

DevOps skills

Web development skills

Web development skills

Testing skills

Testing skills

5. Discover Popular Repositories

5. 发现热门仓库

Search and group by repository

Search and group by repository

6. Download and Inspect Skills

6. 下载并查看Skill

View a specific file directly

View a specific file directly

Clone the entire repository

Clone the entire repository

Download a specific file

Download a specific file

Complete Workflow Example

完整工作流示例

Scenario: Finding and Adapting a Zellij Skill

场景：查找并适配Zellij Skill

1. Search for zellij skills

1. Search for zellij skills

2. Search more broadly for terminal multiplexer skills

2. Search more broadly for terminal multiplexer skills

3. Examine a promising result

3. Examine a promising result

4. Download for adaptation

4. Download for adaptation

Advanced Search Patterns

高级搜索模式

Find Recently Updated Skills

查找最近更新的Skill

Skills updated in the last month

Skills updated in the last month

Find Skills by Star Count

按星标数量查找Skill

Skills from popular repositories (>100 stars)

Skills from popular repositories (>100 stars)

Find Skills with Specific Patterns