zrwangems/dsh-zrwang-plugin / ars/skills/academic-paper-reviewer
academic-paper-reviewer
Flagged模拟同行评审:期刊匹配审稿人 + 3 位动态领域审稿人 + 魔鬼代言人,输出编辑决定(接收/小修/大修/拒稿)与返修路线图,可做方法论专项评审与再审核验。Triggers: review paper, peer review, manuscript review, check methodology, re-review | 审稿, 同行评审, 评审论文, 检查方法, 复审。只做评审,不改写稿件。
references/review_criteria_framework.md
View on GitHub> 输出语言(本 DSH 集成强制):所有面向用户的文字、稿件、摘要、评审与报告一律使用**简体中文**;英文术语与引文保持英文。文中的 `zh-TW` / `zh-tw-en` 只是上游语言代码与脚本参数,不代表要用繁体输出。用户明确要求其他语言时以用户为准。
>
> 多角色执行(评审团、十阶段流水线、角色扮演)必须使用 DSH 的 Agent Team 工具(`spawn_teammate`、`team_task_*`、`wait_agent`、`send_message`);当前会话看不到这些工具,说明用户没开 Agent Team,必须先提示用户开启,不得退化成单会话顺序扮演。
# Review Criteria Framework — Structured Review Criteria Framework
This document defines shared review criteria and article-type extensions. Apply every criterion through the criterion-bound judgement form in `quality_rubrics.md`; the framework contains no numerical scoring or aggregation rule.
## 1. Universal Review Dimensions
| Dimension | Core question |
|---|---|
| Originality | What defensible contribution does the paper make relative to the relevant literature and target venue? |
| Methodological Rigor | Can the design, execution, analysis, and reporting support the inferences made? |
| Evidence Sufficiency | Does each material claim have evidence of the appropriate type, quality, relevance, and coverage? |
| Argument Coherence | Do the problem, gap, question, method, findings, and implications form a traceable argument? |
| Writing Quality | Is the reasoning communicated precisely enough to interpret and verify without conflating language polish with research quality? |
| Literature Integration | Does the paper critically integrate the literature needed for its question, alternatives, and contribution? |
| Significance & Impact | Do the claimed implications follow from the evidence and matter for the stated audience? |
For each applicable dimension, use `EXCEEDS`, `MEETS`, `PARTLY_MEETS`, `DOES_NOT_MEET`, or `NOT_ASSESSED`, together with a criterion source, evidence anchors, rationale, uncertainty, and decision-bearing explanation. These labels are local to the named criterion and must not be converted to points, totals, or rankings.
## 2. Paper Type-Specific Criteria
### 2.1 Empirical Research
| Additional criterion | Review focus |
|---|---|
| Research hypothesis clarity | Are hypotheses testable and consistent with the stated theory? |
| Variable operational definitions | Are variables or constructs defined and measured precisely? |
| Internal validity | Are plausible confounds and alternative explanations addressed? |
| External validity | Is the claimed scope of generalization supported? |
| Statistical reporting completeness | Are effect sizes, uncertainty, assumptions, and exclusions reported as required? |
| Conclusion conservatism | Do conclusions stay within what the design and data support? |
### 2.2 Theoretical/Conceptual Paper
| Additional criterion | Review focus |
|---|---|
| Conceptual definition precision | Are core concepts clearly delineated? |
| Argument logic structure | Is the premise-to-inference-to-conclusion chain complete? |
| Counterargument handling | Are material alternatives considered and answered? |
| Theoretical novelty | Does the paper advance theoretical understanding rather than merely rename it? |
| Testability | Can the theory generate discriminating propositions or implications? |
### 2.3 Literature Review / Meta-analysis
| Additional criterion | Review focus |
|---|---|
| Search strategy | Is it sufficiently comprehensive and reproducible for the stated review type? |
| Inclusion/exclusion criteria | Are criteria clear, justified, and consistently applied? |
| Risk-of-bias assessment | Is the quality or bias risk of included studies assessed appropriately? |
| Heterogeneity handling | Is statistical and conceptual heterogeneity handled appropriately? |
| Synthesis method | Does the method support the synthesis and conclusions? |
| Publication bias | Is publication bias assessed and discussed where applicable? |
### 2.4 Case Study
| Additional criterion | Review focus |
|---|---|
| Case selection justification | Why was this case chosen, and what can it illuminate? |
| Sampling logic | Is case selection theoretically or analytically grounded? |
| Triangulation | Are evidence sources sufficient for the claims made? |
| Contextual detail | Is the context described well enough to interpret the case? |
| Transferability | Are claims beyond the case bounded and justified? |
| Researcher reflexivity | Is the researcher's relationship with the case addressed where relevant? |
### 2.5 Policy Analysis / Policy Brief
| Additional criterion | Review focus |
|---|---|
| Policy problem definition | Is the problem clearly defined and evidence-supported? |
| Stakeholder analysis | Are relevant stakeholders and interests represented? |
| Policy option analysis | Are viable alternatives compared on explicit criteria? |
| Feasibility assessment | Are implementation constraints and trade-offs addressed? |
| Evidence quality | Are recommendations supported by fit-for-purpose evidence? |
| Unintended consequences | Are material adverse or distributional effects considered? |
## 3. Common Review Pitfalls
| Pitfall | Corrective discipline |
|---|---|
| Hypercriticism | Acknowledge genuine strengths, distinguish decision-bearing findings from copyediting, and avoid finding quotas. |
| Confirmation bias | Seek disconfirming evidence and plausible alternative interpretations. |
| Preference projection | Ask whether the author's method answers the question, not whether it is the reviewer's preferred method. |
| Paradigm bias | Apply criteria appropriate to the paper's research paradigm and article type. |
| Prestige bias | Evaluate the manuscript evidence, not institutional or author status. |
| Novelty bias | Judge the contribution claimed; replication and boundary tests can be valuable. |
| Length bias | Evaluate evidence and argument coverage, not page count or reference count. |
| Language discrimination | Separate problems of meaning from non-native phrasing or surface polish. |
### Principles of constructive feedback
1. Be specific: identify what is wrong and where.
2. Explain why the issue matters to a named criterion.
3. Propose a proportionate, feasible remedy when one exists.
4. Distinguish required revisions from optional suggestions.
5. State uncertainty and reviewer-scope limits.
## 4. Judgement synthesis
Do not aggregate dimension judgements numerically. The synthesis should identify which criteria are positively verified, which remain unresolved, whether each weakness is repairable, and how those particular findings support the recommendation under `editorial_decision_standards.md` or the active sprint contract. A decision-bearing failure cannot be cancelled by strengths elsewhere, and reviewer disagreement must remain visible rather than being averaged away.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |