Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No external API needed.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Deep Dive
Autonomous deep research using the same DAG-based planning pattern as Google's Deep Research — but running entirely on Claude Code with no external dependencies.
## How it works
1. **Plan** — decompose the question into a DAG of sub-questions with dependencies
2. **Fan out** — run independent sub-questions in parallel via Agent subagents
3. **Gap analysis** — each subagent returns findings + identified gaps
4. **Iterate** — gaps become new sub-questions, fed back into the DAG
5. **Synthesize** — once all nodes complete, produce a final report
## Steps
### 1. Decompose into a DAG
Given the research question, generate a DAG of sub-questions. Each node has:
- **id**: short identifier (e.g., `q1`, `q2a`)
- **question**: the specific sub-question to research
- **depends_on**: list of node IDs whose answers are needed first (empty = no dependencies)
**Rules for decomposition:**
- Start with foundational/context-setting questions that have no dependencies
- Build toward analytical/comparative questions that depend on foundational answers
- Aim for 4-8 nodes. If the topic needs more, cap at 12.
- Each node should be answerable with 1-3 web searches
…
The line at the top of this page pins the label git:20260728.80a7ab6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_f5ygurddtvax6i75
GET https://markdownregistry.com/api/v1/resolve?ref=fabioc-aloha/alex_skill_mall/deep-dive
GET https://markdownregistry.com/api/v1/blob/469d4235b721662319342c759697eb488a52d7d7661bf72ef5fcf981ade3224a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
fabioc-aloha/alex_skill_mall · .github/skills/source-inventory/SKILL.md · Maintain the source registry in sources/supported-stores.json — add a new third-party plugin store, retire one, refresh…
fabioc-aloha/alex_skill_mall · .github/skills/staleness-discipline/SKILL.md · Detect, classify, and prune stale source stores in the Mall — define what stale means and how to remove gracefully…
fabioc-aloha/alex_skill_mall · .github/skills/store-evaluation/SKILL.md · Evaluate a proposed store for inclusion in Alex_ACT_Plugin_Mall using a quality scorecard
fabioc-aloha/alex_skill_mall · plugins/3d-graphics/spline-3d-integration/skills/spline-3d-integration/SKILL.md · Use when adding interactive 3D scenes from Spline.design to web projects, including React embedding and runtime control…
fabioc-aloha/alex_skill_mall · plugins/academic-research/academic-paper-drafting/skills/academic-paper-drafting/SKILL.md · End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting…
fabioc-aloha/alex_skill_mall · plugins/academic-research/academic-research/skills/academic-research/SKILL.md · Research project scaffolding, thesis/dissertation writing, literature reviews, publication workflows, and the AI…
zereight/gitlab-mcp · .github/skills/deep-dive/SKILL.md · 2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive…
zaxbyhub/opencode-swarm · .opencode/skills/deep-dive/SKILL.md · Full execution protocol for MODE: DEEP_DIVE — read-only codebase audit with parallel explorer waves, 2 independent…
zaxbyhub/opencode-swarm · .claude/skills/deep-dive/SKILL.md · Full execution protocol for MODE: DEEP_DIVE — read-only codebase audit with parallel explorer waves, 2 independent…
