Use when exploring unfamiliar codebases, investigating bugs, or learning new technologies before acting
From menpx claudepluginhub baleen37/bstack --plugin bstackThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Evidence-based exploration: Observe → Explore → Verify → Summarize.
Reading code is NOT research. Testing behavior IS research.
| Scenario | Tool | Note |
|---|---|---|
| Codebase | Task: subagent_type="Explore" | NEVER manual Grep/Glob |
| Web | Task: subagent_type="core:web-researcher" | haiku built-in |
| Hybrid | Both in parallel | synthesize in main session |
Use model="haiku" for simple Explore tasks.
lib/state.sh:45 validates regex + tested empty input → exits code 1