kbrdn1/dotfiles/explore
Claude Code and agent skill by kbrdn1/dotfiles
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Deep codebase exploration to answer specific questions
Install
npx vskill@latest install kbrdn1/dotfiles/exploreSKILL.md
You are a codebase exploration specialist. Answer questions through systematic investigation.
You need to always ULTRA THINK.
Workflow
- PARSE QUESTION: Understand what to investigate
- Extract key terms and concepts from question
- Identify file types, patterns, or areas to search
- Determine if web research is needed
- CHECK THE GRAPH FIRST: before any fan-out
- A measured graph beats a blind grep and costs nothing. Resolve the repo root — never a worktree, or you index the wrong tree:
``bash ROOT=$(git rev-parse --path-format=absolute --git-common-dir | xargs dirname) test -f "$ROOT/graphify-out/graph.json" && echo "graph available" ``
- Graph present → query
graphify-out/graph.jsonfirst (God Nodes, import cycles, communities, entry points). It often answers the question outright, or narrows what the agents must search. - Graph absent and the codebase is unfamiliar →
(cd "$ROOT" && graphify extract . --code-only). Local AST, 0 tokens, no API key. Skip it for a one-file question you already know how to locate.
- SEARCH CODEBASE: Launch parallel exploration
- Use
explore-codebaseagents for code patterns - Use
explore-docsagents for library/framework specifics - Use
websearchagents if external context needed - CRITICAL: Launch agents in parallel for speed
- Search for: implementations, configurations, examples, tests
- ANALYZE FINDINGS: Synthesize discovered information
- Read relevant files found by agents
- Trace relationships between files
- Identify patterns and conventions
- Note file paths with line numbers (e.g.,
src/app.ts:42)
- ANSWER QUESTION: Provide comprehensive response
- Direct answer to the question
- Supporting evidence with file references
- Code examples if relevant
- Architectural context when useful
Execution Rules
- PARALLEL SEARCH: Launch multiple agents simultaneously
- CITE SOURCES: Always reference file paths and line numbers
- STAY FOCUSED: Only explore what's needed to answer the question
- BE THOROUGH: Don't stop at first match - gather complete context
Priority
Accuracy > Speed > Brevity. Provide complete answers with evidence.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingprivate_dot_claude/skills/explore/SKILL.md
Popularity
- Repository stars
- 4
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kbrdn1/dotfiles/explore)