Overview
Research that lands as a folder you can revisit and extend — not a one-shot wall of text. Built for questions where being wrong is expensive: strategy calls, business plans, published pieces, hypotheses that must actually be tested. Low-risk quick answers don't deserve this weight.
It reframes the question first, pins the decision behind it and commits two to four falsifiable hypotheses; then fans searches out in parallel, archives every source as its own file with verbatim quotes, and scores it on credibility, recency and stance. A conclusion needs at least three sources of different kinds backing it, and the synthesis includes a deliberate hunt for disconfirming evidence — a claim without a source stays empty instead of gaining a plausible-looking citation.
You receive a cited report plus its plan, source index and key figures; a month later an update checks only what changed. Everything lives in your workspace, auditable line by line.
Where it helps
- Produce an auditable market-entry strategy report
- Compare N products, methods or institutions with per-cell sourcing
- Test whether an internal hypothesis survives external data
- Refresh a landscape with a delta instead of re-running the whole sweep
#research#search#synthesis#report
Examples
Examples describe the request and the shape of the expected deliverable; they are not completed run results.
01Example prompt
Research 'the cost inflection of on-device transcription for small teams', medium depth: reframe the question, state three falsifiable hypotheses and the search plan before fanning out.
Expected output
A plan and hypothesis list for your sign-off, then source files, cross-check results and the cited report.
02Example prompt
Update the competitor landscape I researched three months ago — follow the watch-list from that run and deliver only what changed.
Expected output
A delta: new entrants, changed figures and falsified old judgments, with the original folder intact.
Requirements and limits
- Install platforms
- iOS: iOS · Android: Android
- Script runtime
- No script runtime (guidance and workflow)
- Minimum app version
- 1.7.59
Reviewed permission scope
iOS · Android
- Capabilities
- Network accessRead workspace filesWrite workspace files
- Review decision
- Approved
- Review stage
- Static content review
- Reviewed on
- 2026-10-28
Implementation and runtime details
- Adaptation stage
- frozen
iOS
- Capabilities
- Network accessRead workspace filesWrite workspace files
Android
- Capabilities
- Network accessRead workspace filesWrite workspace files
License and source
Source and trace details
License
MIT
MIT (root LICENSE)
The pinned skill subtree and shipped references were audited; full applicable license and per-file adaptation/asset notes are preserved under references/licenses/ and references/PROVENANCE.md.
- Source
- https://github.com/alirezarezvani/claude-skills
- Upstream path
- research/deep-research/skills/deep-research
- Source checked
- 2026-10-26
- Publisher
- JiangNanGenius
- Publication commit (retrieval)
- 25e07dbeeb6cc93c2fe83ddc72a34302cc40832a
- Audited source commit
- 84c524b6fb483e4cad94db076e7d9c9962966c19
- Signed catalog digest
- iOS 46196ba57ed7ea7f22085e74b113207f31193e820ab8983cf7a60eee953f2340 · Android 16de89d019e2057804a40f215485ccb09d5495a25864b34d681168eeaf8f9697
- Publication snapshot (UTC)
- 2026-10-31
Publication commit 25e07dbeeb, audited source 84c524b6fb; catalog digest iOS 46196ba57ed7… · Android 16de89d019e2….
Versions and status
Version records ship with the signed catalog; the target and released versions are shown below.
- Adaptation
- Ready
- Publication state
- Curated skills are available
- Released version
- 1.0.1