From deep-ass-research
Deep, multi-source, primary-sourced research into a backlinked Obsidian vault. Fans out scout/diver sub-agents that write atomic cited claim notes, adversarially verifies them, then synthesizes a Map-of-Content + report. Use when the user wants thorough, cited research on a topic, company, market, or literature, or says "deep research", "DAR", "Deep Ass Research", "research X properly", "build me a knowledge map of X", "look deeply into", "do a deep dive on".
How this skill is triggered — by the user, by Claude, or both
Slash command
/deep-ass-research:deep-ass-researchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This is the Claude Code entry point for the **portable DAR framework**. The methodology is host-agnostic and lives in `core/`; this file just binds DAR's capability verbs to Claude Code's tools and tells you how to spawn the roles.
core/PREREQUISITES.mdcore/capabilities.mdcore/methodology.mdcore/modes/academic.mdcore/modes/gtm.mdcore/modes/market.mdcore/modes/technical.mdcore/note-schemas.mdcore/orchestration.mdcore/provenance.mdcore/roles/arbiter.mdcore/roles/deep-diver.mdcore/roles/librarian.mdcore/roles/relevance-monitor.mdcore/roles/scout.mdcore/roles/skeptic.mdcore/roles/synthesizer.mdcore/vault-layout.mdThis is the Claude Code entry point for the portable DAR framework. The methodology is host-agnostic and lives in core/; this file just binds DAR's capability verbs to Claude Code's tools and tells you how to spawn the roles.
core/orchestration.md and follow it exactly. It is the runbook (preflight → charter → breadth → gate → depth → drift guard → verify → synthesize → deliver). Read its referenced files as needed: core/capabilities.md, core/methodology.md, core/vault-layout.md, core/note-schemas.md, core/provenance.md, and the chosen core/modes/<mode>.md.subagent_type: general-purpose). For each role, read core/roles/<role>.md and paste its full content as the sub-agent prompt, then append a ## Task block with the thread/claim context and the absolute vault path. (This mirrors the bug-hunt-review skill's dispatch pattern.) Run independent sub-agents in parallel by issuing multiple Task calls in one message._progress.md and _open-threads.md (source of truth). You MAY also mirror _progress.md into TodoWrite for visibility.| Verb | Binding |
|---|---|
WRITE_FILE | Write / Edit |
ASK_USER | AskUserQuestion |
SPAWN_SUBAGENT | Task / Agent tool (general-purpose), parallel via multiple calls |
SEARCH | Tavily / Exa MCP if present, else built-in WebSearch |
FETCH | Tavily extract / Exa fetch if present, else built-in WebFetch |
BROWSE | TinyFish MCP (run_web_automation) |
READ_DOCS | Context7 + Ref MCP, else WebSearch+WebFetch on official docs |
Record the actual bindings (and any degraded verbs) in _session.md during preflight.
For determinism, resumability, and budget control, the Depth → Drift → Verify → Synthesize stretch MAY run via adapters/claude-code/dar-pipeline.workflow.js (native Workflow tool). If you use it: first read the role files in core/roles/ and the chosen core/modes/<mode>.md, then invoke the Workflow passing them in args (the script sandbox can't read files): args = {vault, mode, brief, threads, roles:{...}, playbook}. Otherwise just follow steps 3–5 of core/orchestration.md directly. Running DAR implies opting into multi-agent orchestration — announce the approach before launching.
This directory works as a drop-in skill as-is. To distribute it as a plugin (registers the roles as real subagents, adds /dar, and auto-wires prerequisite MCP servers), see adapters/claude-code/plugin/.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub kaos599/deep-ass-research --plugin deep-ass-research