Agent skill · AI & Agents

deep-research

GOD MODE deep research skill. Multi-phase autonomous research loop: query decomposition → multi-source crawling → claim cross-referencing → conflict resolution → structured synthesis with inline citations. Use for any question that demands depth, sourcing, and verifiable accuracy.

shobcoder583★ · 1 repos on radarProfile →
claude-codecodexcursorMIT
Install
npx skills add shobcoder/shob --skill research-knowledge --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/research-knowledge/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 583
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Deep Research — GOD MODE ## Trigger `/deep-research <query>` or when user says "research this deeply", "go deep on", "full research report on", "investigate this thoroughly". ## Core Philosophy > Raw search results are noise. Verified synthesis is signal. > Every claim needs a source. Every conflict needs a resolution. > A great deep research report is a structured intelligence brief, not a search summary. ## Architecture ``` Query └── Phase 1: Decompose → Sub-questions └── Phase 2: Parallel Search → Raw Sources └── Phase 3: Crawl & Extract → Claims └── Phase 4: Cross-Reference → Verify / Conflict └── Phase 5: Synthesize → Report └── Phase 6: Quality Gates → Deliver ``` --- ## Phase 1 — Query Decomposition Break the user's query into **3–7 atomic sub-questions**. Each must be: - Independently searchable - Non-overlapping with others - Ordered from foundational to advanced **Example:** > Query: "Is Company X profitable?" Sub-questions: 1. What is Company X's current revenue model? 2. What are its reported ARR and revenue figures? 3. What is its burn rate and cost structure? 4. What do investors say about its path to profitability? 5. How does it compare to competitors on unit econ

What's inside
Steps it walks through
  1. Trigger
  2. Core Philosophy
  3. Architecture
  4. Phase 1 — Query Decomposition
  5. Phase 2 — Multi-Source Search Strategy
  6. Phase 3 — Deep Crawl and Extraction
  7. Phase 4 — Cross-Reference and Conflict Resolution
  8. 4a. Claim Clustering
  9. 4b. Conflict Detection
  10. 4c. Gap Detection
  11. 4d. Confidence Scoring
  12. Phase 5 — Report Synthesis
  13. Report Structure
  14. Phase 6 — Quality Gates
More from shob
All skills →
About this skill
What does the deep-research skill do?

GOD MODE deep research skill. Multi-phase autonomous research loop: query decomposition → multi-source crawling → claim cross-referencing → conflict resolution → structured synthesis with inline citations. Use for any question that demands depth, sourcing, and verifiable accuracy.

How do I install it?

Run `npx skills add shobcoder/shob --skill research-knowledge --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From shobcoder/shob, a repository with 583 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going