Locate Review Research Gap
Discipline And Interview Setup
Read discipline-routing.md, then only the selected discipline profile. Reuse the user's existing brief; do not restart intake at each stage. For journalism/communication or information science, use that profile's concepts, extraction fields, and appraisal checks instead of a generic social-science template.
When the user requests "grill me", 追问, or 模拟答辩, read research-interview.md. Ask one decision-relevant question per turn and wait; do not generate the stage deliverable until enough decisions are settled or the user asks to proceed. In quick/no-question mode, record assumptions and continue without inventing answers.
For evidence extraction or drafting, read review-workflow.md. With no sources, give a plan or outline, not a purported synthesis. If reference files are unavailable, retain the source guardrails below and state that discipline guidance is missing.
Goal
Turn a literature review's ending from generic "future research" into a specific, justified research direction: what predecessors have done, where the explanation gets stuck, where to cut in, and why that move matters.
Workflow
- Restate the question anchor.
- Summarize progress within the reviewed corpus, not automatically the whole field. State the search coverage and distinguish supported convergence from unresolved questions; neither consensus nor contradiction is mandatory.
- Identify where progress gets stuck: theory gap, method limitation, data blind spot, context boundary, variable/mechanism omission, or contradictory evidence.
- Select one cut-in point: a module, mechanism, variable relation, context, population, time window, or method design.
- Explain the candidate contribution and test it against the strongest available counterexample or prior work. It may clarify a concept, extend an interpretation, resolve a contradiction, or test a boundary; do not promise field-wide novelty without evidence.
- Draft a concise research outlook or contribution paragraph.
Four Required Questions
A strong research gap must answer all four:
- What have previous studies already established?
- Where exactly is the explanation stuck?
- Which specific opening will the next study enter through?
- Why is this opening worth entering?
If any answer is missing, do not present the gap as ready.
Gap Types
Use the type that matches the evidence:
- Theory gap: existing frameworks miss a mechanism or actor.
- Method gap: existing methods cannot observe the needed process, time dimension, or causal structure.
- Data gap: important samples, contexts, time windows, or measurements are absent.
- Boundary gap: known findings may not hold under certain conditions.
- Contradiction gap: studies disagree and the disagreement has a plausible unresolved source.
- Integration gap: separate modules exist but have not been connected into one explanation chain.
Output Format
Provide:
markdown## Current Progress [Consensus + tension in one sentence] ## Stuck Point [Where the literature cannot yet explain enough] ## Proposed Cut-In Point [Specific module/mechanism/variable/context/method] ## Why It Matters [How this fills a gap, resolves a contradiction, tests a boundary, or advances explanation] ## 段落草稿（需作者改写并核对来源） [Draft prose for conclusion/research outlook. Start with: "以下为草稿，请改写成你自己的论证，并逐句核对来源后再使用。" Tag every literature-dependent sentence with source and status, or [需补来源]] ## Three-Minute Oral Test - Previous studies have shown: ... - They have not explained: ... - I will focus on: ... - This is valuable because: ... ## 待核实清单 [Unverified sources, "未查到" results, sentences marked [需补来源], and inferences that still need checking; write "无" if empty] ## 给作者的问题 [Judgment calls that belong to the author; write "无" if empty]
The output sections above, and the two closing sections, keep fixed names and order; see references/output-contract.md (a copy bundled in this skill folder).
Guardrails
- Do not use "few studies have examined" as the only proof of a gap; explain why the missing piece matters.
- Do not propose an opening that is broader than the user's review question.
- Do not confuse the user's not-yet-searched area with a true research gap; mark it as "needs verification" when evidence is insufficient.
- Source integrity: follow
references/source-integrity.md. A gap claim about what the literature lacks needs sources or must be marked "needs verification". Use only sources the user provided or that are verified, tag each with a status (用户提供 / 已核验 / 未核验), write "未查到" instead of completing authors, year, journal, or pages, and put anything unverified in## 待核实清单. If that file is not available, still apply these rules.
