team-shinchan:deepsearch
npx machina-cli add skill seokan-jeong/team-shinchan/deepsearch --openclawEXECUTE IMMEDIATELY
Step 1: Validate Input
If args is empty or only whitespace:
Ask user: "What would you like to search for?"
STOP and wait for user response
If args length > 2000 characters:
Truncate to 2000 characters
Warn user: "Request was truncated to 2000 characters"
Step 2: Execute Tasks
Do not read further. Execute these Tasks NOW:
// Step 1: Fast Search (Shiro)
Task(
subagent_type="team-shinchan:shiro",
model="haiku",
prompt=`/team-shinchan:deepsearch has been invoked.
## Codebase Exploration Request
Perform fast search:
- File name pattern matching
- Keyword search
- Directory structure analysis
Search target: ${args || '(What to search)'}
`
)
// Step 2: Deep Search if needed (Masumi)
// Call additionally if Shiro results are insufficient
Task(
subagent_type="team-shinchan:masumi",
model="sonnet",
prompt=`Perform deep analysis based on Shiro search results:
- Code content analysis
- Related documentation search
- Dependency tracking
Search target: ${args || '(What to search)'}
`
)
STOP HERE. The above Tasks handle everything.
Source
git clone https://github.com/seokan-jeong/team-shinchan/blob/main/skills/deepsearch/SKILL.mdView on GitHub Overview
team-shinchan:deepsearch orchestrates deep codebase discovery by leveraging Shiro (Explorer) for fast, pattern-based hunts and Masumi (Librarian) for thorough code-content analysis. It supports find, where is, and search requests by first scanning filenames and structure, then diving into code, docs, and dependencies.
How This Skill Works
The skill validates the input, ensuring it is non empty and truncating any query longer than 2000 characters. It then runs two tasks: a fast search via Shiro to match file names, keywords, and directory structure; and, if results are insufficient, a follow up deep search via Masumi to analyze code content, related documentation, and dependencies.
When to Use It
- Locate a function or symbol across the repository
- Find where a file or module is located
- Search for a concept or keyword across code and docs
- Map dependencies for a module or feature
- Understand related documentation for a feature
Quick Start
- Step 1: Provide your search query as args
- Step 2: Shiro performs fast file name, pattern, and keyword search
- Step 3: If results are insufficient, Masumi does a deep analysis of code, docs, and dependencies
Best Practices
- Provide precise keywords or file patterns to narrow results
- Keep the query under the 2000 character limit
- Start with a file name or function name to get faster hits
- Review Shiro results before requesting a deeper Masumi analysis
- Use Masumi for deep dives into code content, docs, and dependencies when needed
Example Use Cases
- Find where a function is implemented across the codebase
- Determine where a specific configuration file is located
- Locate all usages of an external library across modules
- Map dependencies for a new feature to assess impact
- Pull up related documentation for a feature in docs or READMEs
