← Back to list

parallel-exploration
by trash-panda-v91-beta
A modular and declarative dotfiles configuration using Nix Flakes, Home Manager, and nix-darwin.
⭐ 1🍴 0📅 Jan 22, 2026
SKILL.md
name: parallel-exploration description: Use when researching unfamiliar code, multiple modules involved, or external libraries referenced
Parallel Exploration
Fire search agents in parallel. Never wait sequentially when searches are independent.
Tool Selection
| Tool | Cost | When to Use |
|---|---|---|
grep, glob, lsp_*, ast_grep | FREE | Scope clear, single pattern, known location |
tracer agent | FREE | Multiple search angles, unfamiliar modules, cross-layer patterns |
rocket agent | CHEAP | External docs, GitHub examples, OSS reference |
oracle agent | EXPENSIVE | Architecture decisions, debugging after 2+ failures |
Tracer = Contextual Grep (Internal)
Use for searching YOUR codebase:
| Use Direct Tools | Use Tracer |
|---|---|
| Exact pattern known | Multiple search angles needed |
| Single keyword suffices | Unfamiliar module structure |
| Known file location | Cross-layer pattern discovery |
Rocket = Reference Grep (External)
Use for searching EXTERNAL resources:
- Official API documentation
- Library best practices
- OSS implementation examples
- GitHub examples
Trigger phrases (fire rocket immediately):
- "How do I use [library]?"
- "What's the best practice for [framework feature]?"
- Working with unfamiliar packages
Parallel Execution Pattern
// CORRECT: Fire and continue
background_task(agent="tracer", prompt="Find auth implementations...")
background_task(agent="tracer", prompt="Find error handling patterns...")
background_task(agent="rocket", prompt="Find JWT best practices...")
// Continue working immediately
// WRONG: Sequential blocking
result = task(...) // Never wait synchronously
Result Collection
- Launch parallel agents → receive task_ids
- Continue immediate work
- When results needed:
background_output(task_id="...") - BEFORE final answer:
background_cancel(all=true)
Stop Conditions
STOP searching when:
- Enough context to proceed confidently
- Same information appearing across multiple sources
- 2 iterations yielded no new useful data
- Direct answer found
DO NOT over-explore. Time is precious.
Score
Total Score
55/100
Based on repository quality metrics
✓SKILL.md
SKILL.mdファイルが含まれている
+20
○LICENSE
ライセンスが設定されている
0/10
○説明文
100文字以上の説明がある
0/10
○人気
GitHub Stars 100以上
0/15
✓最近の活動
1ヶ月以内に更新
+10
○フォーク
10回以上フォークされている
0/5
✓Issue管理
オープンIssueが50未満
+5
✓言語
プログラミング言語が設定されている
+5
✓タグ
1つ以上のタグが設定されている
+5
Reviews
💬
Reviews coming soon


