skills/deepsearch/SKILL.md
Thorough codebase search using structured search strategy via scout agent
npx skillsauth add sartoris-digital/pi-superpowers deepsearchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Perform a thorough search of the codebase for the specified query, pattern, or concept.
Dispatch a single scout agent at fast tier with the full search strategy:
subagent({
agent: "scout",
tier: "fast",
task: "DEEP SEARCH: {QUERY}\n\nPerform a thorough codebase search using this 3-phase strategy:\n\n## Phase 1: Broad Search\n- Search for exact matches of the query\n- Search for related terms, synonyms, and variations\n- Check common locations: components, utils, services, hooks, lib, helpers\n- Search file names, function names, class names, and comments\n\n## Phase 2: Deep Dive\n- Read files with matches to understand context\n- Check imports/exports to find connections\n- Follow the trail: what imports this? What does this import?\n- Look for related configuration, tests, and documentation\n\n## Phase 3: Synthesize\n- Map out where the concept is used across the codebase\n- Identify the main implementation vs secondary references\n- Note related functionality and patterns\n\n## Output Format\n\n### Primary Locations\n(Main implementations with file:line references)\n\n### Related Files\n(Dependencies, consumers, tests)\n\n### Usage Patterns\n(How it's used across the codebase)\n\n### Key Insights\n(Patterns, conventions, gotchas discovered)\n\nBe comprehensive but concise. Always cite file paths and line numbers."
})
| Placeholder | Source |
|-------------|--------|
| {QUERY} | The user's search query from arguments |
testing
Use when creating new skills, editing existing skills, or verifying skills work before deployment
development
Use when you have a spec or requirements for a multi-step task, before touching code
data-ai
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
tools
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions