zrwangems/dsh-zrwang-plugin / ars/skills/academic-pipeline
academic-pipeline
Flagged学术研究总编排:研究→写作→诚信检查→评审→返修→复审→终检→定稿的十阶段流水线,每阶段停在用户确认点,含材料护照与 7 类 AI 研究失败模式检查。Triggers: academic pipeline, research to paper, full paper workflow, end-to-end paper | 完整论文流程, 从研究到论文, 端到端写论文, 论文流水线。
_shared/contracts/evaluator/full.json
View on GitHub{
"contract_id": "academic_paper/evaluator_full/v1",
"mode": "evaluator_full",
"stage": "evaluator_full_evaluation",
"baseline_version": "v3.6.6",
"acceptance_dimensions": [
{
"id": "D1",
"name": "originality",
"description": "Novel contribution to the field; new framework, new evidence, or unique perspective; not a restatement of existing work.",
"priority": "high"
},
{
"id": "D2",
"name": "methodological_rigor",
"description": "Research design matches the question; method is appropriate, replicable, and limitations are disclosed.",
"priority": "mandatory"
},
{
"id": "D3",
"name": "evidence_sufficiency",
"description": "Every claim is supported by adequate citations or data; no unsupported assertions; no cherry-picking. Exception (#548): a search-bounded absence/novelty claim is supported by documented-search provenance plus the named nearest prior work (or its explicit absence within the search) — do not penalize it for lacking a citation to the absence itself.",
"priority": "mandatory"
},
{
"id": "D4",
"name": "argument_coherence",
"description": "Logic flows across sections; transitions are smooth; thesis-to-conclusion alignment holds; no self-contradiction.",
"priority": "high"
},
{
"id": "D5",
"name": "writing_quality",
"description": "Language is clear and precise; grammar, formatting, and citation style are consistent; readability fits the venue.",
"priority": "normal"
}
],
"disagreement_handling": {
"paraphrase_minimum_dimensions": "all",
"scoring_plan": {
"per_dimension_criteria": [
{
"dimension_id": "D1",
"what_to_look_for": "Introduction's contribution statement names a specific gap; Discussion engages prior work substantively (not list-citation); Literature Review identifies the gap the paper fills.",
"what_triggers_block": "Contribution statement is vague or absent; Discussion lists prior work without engagement; paper restates known conclusions in a new context with no added evidence.",
"what_triggers_warn": "Contribution exists but is weakly differentiated from cited prior work; Discussion engagement is uneven across cited sources."
},
{
"dimension_id": "D2",
"what_to_look_for": "Method is named and justified against the research question; sample / data sources are appropriate; analysis steps are described in enough detail for replication; limitations are explicit.",
"what_triggers_block": "Method does not match the research question; significant design flaws; limitations are not discussed; analysis cannot be replicated from the description.",
"what_triggers_warn": "Method is fundamentally sound but insufficiently detailed; some choices lack justification; limitations are mentioned but not engaged with."
},
{
"dimension_id": "D3",
"what_to_look_for": "Every factual claim carries a citation; cited sources are appropriate quality for the field; inferences in Discussion stay within what the data supports.",
"what_triggers_block": "Multiple core claims lack evidence; over-reliance on a single source; Discussion inferences exceed what the data supports; cherry-picking of favorable evidence.",
"what_triggers_warn": "Core claims have evidence but some secondary claims lack support; citation density is uneven across sections."
},
{
"dimension_id": "D4",
"what_to_look_for": "Introduction's research question is answered in the Conclusion; section-to-section transitions are present; thesis statement is consistent across Abstract, Introduction, and Conclusion.",
"what_triggers_block": "Multiple logical gaps between sections; conclusion disconnected from the introduction's research question; self-contradictory passages.",
"what_triggers_warn": "Overall logic holds but some transitions feel forced; minor inconsistencies between section claims."
},
{
"dimension_id": "D5",
"what_to_look_for": "Register is consistently academic; grammar errors are rare; citation format is internally consistent; figures and tables are referenced in text.",
"what_triggers_block": "Difficult to understand; numerous grammar errors; colloquial register; citation format inconsistent across the manuscript.",
"what_triggers_warn": "Readable but with several grammar or word-choice issues; some paragraphs overly long; minor citation format inconsistencies."
}
]
},
"pre_commitment_check_protocol": {
"check_writer_artifact": "pre_commitment_artifacts"
},
"disagreement_resolution": {
"on_dimension_disagreement": "evaluator_decision=request_revision",
"on_structural_drift": "evaluator_decision=request_revision"
}
},
"failure_conditions": [
{
"condition_id": "F1",
"severity": 90,
"expression": "any mandatory dimension scores 'block'",
"action": "evaluator_decision=request_revision"
},
{
"condition_id": "F2",
"severity": 70,
"expression": "one or more mandatory dimensions score 'warn'",
"action": "evaluator_decision=request_revision"
},
{
"condition_id": "F3",
"severity": 60,
"expression": "any high-priority dimension scores 'block'",
"action": "evaluator_decision=request_revision"
},
{
"condition_id": "F6",
"severity": 55,
"expression": "any normal-priority dimension scores 'block'",
"action": "evaluator_decision=request_revision"
},
{
"condition_id": "F4",
"severity": 50,
"expression": "the evaluator's own scoring plan triggers 'warn' on a high or normal-priority dimension AND no mandatory dimension scores 'block' or 'warn'",
"action": "evaluator_decision=accept_with_dissent_note"
},
{
"condition_id": "F5",
"severity": 95,
"expression": "round 2 still shows mandatory-dimension block after a writer revise_in_phase_4b attempt",
"action": "evaluator_decision=flag_for_reviewer_stage"
},
{
"condition_id": "F0",
"severity": 10,
"expression": "every mandatory dimension scores 'pass' AND no dimension scores 'block'",
"action": "evaluator_decision=accept"
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |