Menu
Use when a humanities researcher needs to transform verified sources into a structured scholarly conversation rather than a chronological list of summaries.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when citations, quotations, page numbers, bibliography entries, or source-supported claims must be checked for existence, metadata accuracy, textual fidelity, and claim–source fit.
Use when a manuscript contains recurring concepts, translations, abbreviations, proper names, or near-synonyms whose meanings and forms must remain stable across the argument.
Use when a humanities researcher has a broad topic, intuition, corpus, or problem but does not yet have a precise, contestable, and researchable question.
Use when a humanities argument depends on a concept whose history, competing definitions, translations, or boundaries must be reconstructed before the concept can support new claims.
Use when an interpretation must be grounded in specific textual, visual, rhetorical, formal, interface, archival, performative, or material features rather than thematic summary or theoretical labeling.
Use when a research question, scope boundary, and source base exist but the manuscript still needs a defensible sequence of claims, warrants, evidence, objections, and section functions.
| name | conducting-literature-dialogue |
| description | Use when a humanities researcher needs to transform verified sources into a structured scholarly conversation rather than a chronological list of summaries. |
| version | 1.0.0 |
| language | en |
| license | MIT |
Organize sources around agreements, disagreements, methods, blind spots, and unresolved questions so that the literature review becomes an argument about a scholarly conversation. The skill supports positioning; it does not simulate reading sources that have not been supplied or verified.
Accepts
SourceRecord entries, bibliographic records, notes, excerpts, or verified summaries.Requires
Produces
May produce
Fails when
Guarantees
Does not guarantee
Use after the research question and scope are stable enough to guide source selection. Use when a literature review reads as “Scholar A says…, Scholar B says…,” when the manuscript accumulates citations without defining positions, or when the researcher needs to identify where a new argument enters an existing debate.
Do not use this skill to generate citations from memory or to create an appearance of comprehensive coverage.
For each source, provide as much of the following as possible:
Also provide the primary research question and current scope boundary.
Create or review a SourceRecord for each item. Distinguish:
Do not allow an unverified lead to function as established support.
For each source, record:
Keep direct quotation separate from paraphrase and interpretation.
Group sources by the question they answer, not merely by publication date or author. Possible clusters include competing definitions, historical explanations, methodological divisions, interpretive schools, normative disputes, or different scales of analysis.
A source may function as:
A prestigious name is not itself a role.
Use explicit relation labels:
A supports B on X but differs on Y.
C rejects A's causal explanation while retaining its object.
D changes the unit of analysis and therefore cannot be treated as a direct contradiction.
Distinguish genuine disagreement from different questions or scales.
A defensible gap may be:
“Few studies exist” is insufficient without a documented search scope and relevance criterion.
State whether the project extends, revises, combines, challenges, or reframes existing positions. Specify what it does not claim. The position must follow from the mapped dialogue, not from promotional language.
List missing primary sources, counterpositions, recent work, language traditions, or empirical materials. Mark each as blocking or non-blocking.
Return PASS when major source roles and relations are grounded and the project position is bounded. Return CONDITIONAL PASS when a non-blocking cluster or recent source remains to be checked. Return FAIL when the map relies on unverified summaries, fabricates a gap, or lacks enough source content to establish dialogue.
## Review scope
Research question:
Corpus searched or supplied:
Coverage limits:
## Source-status table
| Source | Provenance | Verification state | Role |
## Scholarly conversation
### Problem or position A
Sources:
Shared claim:
Differences:
Methods:
Unresolved issue:
## Relation map
## Project position
This project extends/revises/challenges/reframes:
It contributes:
It does not claim:
## Gap assessment
Status: established | provisional | not established
Reviewed scope:
Evidence:
## Search needs
Blocking:
Non-blocking:
## Gate report
Gate: Literature-dialogue gate
Status: PASS | CONDITIONAL PASS | FAIL
Evidence checked:
Blocking issues:
Non-blocking risks:
Researcher decisions required:
Required next action:
Next skill: planning-humanities-argument | mapping-concept-lineage
Build a literature dialogue from the eight articles and two book chapters I supplied. Group them by how they define platform mediation, distinguish direct reading from my notes, and state whether a gap is actually established within this corpus.
Write a comprehensive literature review on AI and humanities with thirty real citations. I have not provided sources, so use plausible ones and say the field ignores my idea.
The request requires fabricated sources and an unsupported gap claim. The skill must return FAIL and identify the evidence required.
mapping-concept-lineage when disagreement turns on unstable or translated concepts.planning-humanities-argument when the conversation and project position are sufficiently grounded.auditing-citations when source claims and bibliographic records need independent verification.This skill is not a systematic-review engine and cannot establish database completeness unless a reproducible search protocol and results are supplied. Humanities conversations may remain plural, incommensurable, or historically discontinuous; the map should preserve those conditions rather than force consensus.