Overview
Literature reviews done to method — systematic, scoping or narrative. Define the question and search plan, retrieve across academic sources, screen records in and out with counts at each stage, deduplicate and merge by DOI and identifiers, extract per-study evidence tables, synthesize into text and check citations against sources. The queries and eligibility criteria stay in the documents so anyone can re-run them.
Citation checking works only against records already retrieved: what can be verified is verified, what can't is marked missing, an unreachable database is named rather than glossed, and nothing is paraphrased from text that was never fetched.
The deliverable is a full review kit in your workspace: protocol, screening record, evidence tables and a drafted review.
Where it helps
- Produce a review protocol with search strings and eligibility criteria
- Screen two hundred candidates into a core set with PRISMA counts
- Build per-study evidence tables and synthesize a review draft
- Check every reference's DOI and provenance before submission
#literature#review#dedup#BibTeX
Examples
Examples describe the request and the shape of the expected deliverable; they are not completed run results.
01Example prompt
Systematic review for 'effects of dry farming on soil bulk density': search plan and in/exclusion criteria first, then dedup and screen, with counts at each stage.
Expected output
A re-runnable protocol, screening results with counts and the corpus; unreachable sources named, not glossed.
02Example prompt
Verify every citation in this draft against the retrieved records; list title/author/year mismatches and mark anything unsourced as missing.
Expected output
A per-citation verification table with suggested fixes; missing fields stay missing — no fabricated pages or years.
Requirements and limits
- Install platforms
- iOS: iOS · Android: Android
- Script runtime
- Runs scripts in the task environment
- Minimum app version
- 1.7.59
Reviewed permission scope
iOS · Android
- Capabilities
- Remote executionNetwork accessRead workspace filesWrite workspace files
- Reviewed tools
- Shell commands
- Review decision
- Approved
- Review stage
- Guest execution qualification
- Reviewed on
- 2026-10-27
Implementation and runtime details
- Adaptation stage
- frozen
iOS
- Tools
- Shell commands
- Capabilities
- Remote executionNetwork accessRead workspace filesWrite workspace files
- Runtime environment
- linux / riscv64 · guest-verified
Android
- Tools
- Shell commands
- Capabilities
- Remote executionNetwork accessRead workspace filesWrite workspace files
- Runtime environment
- linux / riscv64 · guest-verified
License and source
Source and trace details
License
MIT
MIT (root LICENSE.md)
MIT at the pinned upstream revision; full license and per-file adaptation/asset audit are preserved in references/licenses/. Floe additions and synthetic fixtures are identified separately.
- Source
- https://github.com/K-Dense-AI/scientific-agent-skills
- Upstream path
- skills/literature-review
- 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
- Deep adaptation
- Yes
- Released version
- 1.0.0