Research-Grade Skills: curated literature-review guidance

A separately maintained, K-Dense-derived skill collection includes a structured literature-review guide and explicit documentation of its structural checks and open limitations.

L2Research workflow Source Repository-documented Outcome Not empirically evaluated here

Evidence & verification

Source level

Repository-documented
Grounded in a maintainer repository/README. Availability, stars and forks do not establish research benefit or correctness.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-19 (UTC)

Source scope: Full README, selected literature-review skill and maintainer advisory review. Documentation/reference inclusion does not establish an empirical research benefit.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (3)

Research applicability

A maintained literature-review skill curation with explicit upstream lineage and limitations.

Getting started

Read the linked primary sources and the stated adoption requirements. Reuse suggestions are editorial and untested; no setup recipe or trial was executed.

Maintenance

Sources last checked on 2026-10-19. Future availability, maintenance, provider terms and compatibility were not verified.

License

The README states MIT with K-Dense attribution and possible per-skill terms; licence files and compatibility were not audited.

Workflow & human oversight

Intended L2 for the selected literature-review skill: researcher questions and criteria guide search, screening, extraction/appraisal, synthesis, reference checks and review. This is a separately maintained K-Dense-derived curation, not an independently invented method or a level for the whole collection.

Workflow level is not an evidence score; higher is not better evidence.

Approach

The selected guide covers planning, multi-database search, screening, extraction/appraisal, thematic synthesis, citation checks and document review. Documentation distinguishes structural CI from an unfinished editorial audit; the advisory review records script, proxy and commercial-model dependencies.

Limitations

README, selected literature-review skill and maintainer advisory review only; not all skills, scripts, CI runs or references were audited. Shared K-Dense lineage also overlaps the separately catalogued Kalaris guidance. Structural syntax/link checks and maintainer self-review do not establish scientific quality or safety. Prestige, citation-count and reputation filters can bias inclusion. The advisory review reports little script testing, optional untrusted free proxies and paid figure-model dependencies. Figures are optional; study counts must not be invented. Moving HEAD documents are unpinned and non-atomic.

Reproducibility

Source text was checked only within this scope: Full README, selected literature-review skill and maintainer advisory review. No software, dataset, experiment or result was independently reproduced.

Adoption requirements

Untested suggestion: select only needed instructions, check upstream attribution and per-skill terms, remove unjustified prestige filters, and assess scripts, providers and source validity before use.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.