科研 Skill
人文论证逻辑梳理
structuring-humanities-argument
Organizes an approved argument map and notes into manuscript structure while keeping the researcher’s own interpretation. Use to convert materials into ordered prose.
SKILL.md
Structuring a Humanities Argument
Purpose
Organize researcher-provided intellectual material into a coherent section or manuscript while preserving provenance, uncertainty, and authorial responsibility. This skill repairs sequence, paragraph function, transitions, redundancy, and missing warrants; it is not a ghostwriting license.
Contract
Accepts
- An approved argument map or thesis-and-claims structure.
- Researcher-authored notes, draft passages, definitions, interpretations, and verified evidence.
- Genre, audience, length, and stylistic constraints.
Requires
- A researcher-approved thesis or central claim.
- Enough evidence and interpretation to support the requested unit.
- Clear separation, where possible, among source language, researcher language, and agent-proposed connective language.
Produces
- A structured outline, paragraph plan, or revised draft based on supplied material.
- Inline provenance and gap markers.
- A provenance note describing transformations.
- A structuring gate report.
May produce
- Alternative sequences with trade-offs.
- A list of surplus or misplaced material.
FAILwhen the requested contribution would need to be invented.
Fails when
- No thesis or argument map has been approved.
- The evidence base is too thin for the requested prose.
- The agent cannot distinguish quotation, paraphrase, and researcher-authored claim.
- The request asks the agent to invent the scholar’s original theory, interpretation, or personal voice.
Guarantees
- New factual and bibliographic claims will not be introduced without explicit support.
- Missing warrants and author decisions will remain marked.
- The provenance note will distinguish reordering, compression, paraphrase, and newly proposed connective language.
Does not guarantee
- Originality, stylistic excellence, publication readiness, or authentic representation of the researcher’s voice.
- That structurally coherent prose is substantively correct.
When to use
Use after planning-humanities-argument and source-grounded analysis. Use when notes are rich but unordered, when paragraphs lack functions, when transitions conceal logical gaps, or when revisions require moving, compressing, or splitting material.
Do not use from a title alone. Do not ask this skill to simulate a personal voice, hide AI involvement, invent a theoretical contribution, or create citations to support missing claims.
Inputs required
Collect:
- Approved thesis and claim map.
- Target unit: paragraph, subsection, chapter, article, response letter.
- Researcher-authored notes and passages.
- Verified evidence and citation records.
- Definitions and terminology ledger.
- Audience, venue, length, and citation style.
- Permissions concerning paraphrase and line editing.
Identify each input’s provenance before restructuring.
Procedure
1. Inventory and label materials
Classify supplied items as claim, evidence, quotation, paraphrase, observation, interpretation, inference, context, transition, or unresolved note. Mark uncertain provenance immediately.
2. Align with the argument map
Assign each item to a claim and section function. Place unmatched material in Surplus / unresolved placement rather than forcing it into the draft.
3. Build paragraph contracts
For each paragraph define:
Function
+ Claim
+ Evidence
+ Analysis
+ Warrant
+ Link forward
Not every paragraph needs all elements, but every paragraph needs a declared function and relation to the argument.
4. Separate connective work from substantive judgment
The agent may propose order, signposting, compression, and explicit warrants already latent in supplied material. When a transition requires a new substantive claim, insert [AUTHOR DECISION REQUIRED] rather than supplying it as fact.
5. Repair sequence
Order paragraphs by inferential need: definition before application, observation before interpretation, evidence before generalization, objection before qualified conclusion. Preserve deliberate nonlinear form only when its epistemic purpose is stated.
6. Control repetition
Distinguish productive recurrence from redundancy. Consolidate repeated definitions and claims, but preserve repeated textual features when repetition is itself evidence.
7. Mark gaps visibly
Use:
[EVIDENCE NEEDED][WARRANT NEEDED][CONTEXT VERIFICATION NEEDED][AUTHOR DECISION REQUIRED][TERMINOLOGY DECISION REQUIRED][CITATION VERIFICATION NEEDED]
Markers must not be silently removed during polishing.
8. Preserve epistemic status
Do not upgrade hypothesis to conclusion, interpretation to fact, or researcher-supplied context to verified history. Retain disagreement and qualification.
9. Produce provenance notes
For each substantial block record whether it was retained, reordered, compressed, lightly edited, paraphrased from supplied text, or newly proposed as connective language. Do not claim exact authorship attribution when collaboration is entangled; state the limits.
10. Run paragraph-function audit
Check for evidence dumps, theory-name paragraphs, unearned conclusions, delayed definitions, and transitions that merely announce topic changes. Verify that each paragraph advances, qualifies, supports, or tests a claim.
11. Issue the gate report
Return PASS only when the requested unit is structurally coherent and no blocking authorship or evidence gap remains. Return CONDITIONAL PASS when visible non-blocking markers remain. Return FAIL when original contribution or evidence would need invention.
Stop signals
Stop when:
- the user asks for a “complete original paper” from a title or abstract;
- source and researcher language are mixed without attribution;
- the only way to connect sections is to invent a claim;
- a requested rewrite would suppress uncertainty or disagreement;
- a personal style imitation is requested to conceal provenance;
- unsupported citations are required to make prose appear complete.
Completion criteria
Complete only when:
- each paragraph or section has an argumentative function;
- material is aligned with the argument map;
- no unsupported factual or bibliographic claims were added;
- all missing decisions and warrants are visibly marked;
- terminology is stable or flagged;
- provenance transformations are documented;
- the gate report records residual risks and next action.
Anti-fabrication rules
- Do not invent original contribution, interpretation, evidence, or citations.
- Do not imitate a living researcher’s voice to obscure authorship.
- Do not erase unresolved markers for fluency.
- Do not merge contradictory sources into false consensus.
- Do not present agent-proposed connective language as verified scholarship.
- Do not infer permissions to rewrite quoted or archival material.
Output format
## Structural plan
Target unit:
Primary function:
Claims advanced:
## Revised structure or draft
[Use provenance and gap markers inline.]
## Surplus / unresolved placement
## Provenance note
Retained:
Reordered:
Compressed:
Paraphrased from supplied material:
Agent-proposed connective language:
Limits of attribution:
## Gate report
Gate: Argument-structuring gate
Status: PASS | CONDITIONAL PASS | FAIL
Evidence checked:
Blocking issues:
Non-blocking risks:
Researcher decisions required:
Required next action:
Next skill: stress-testing-argument
Good invocation
Reorganize these researcher-written notes and verified passages according to the approved argument map. Mark missing warrants and distinguish all newly proposed connective language.
Bad invocation
Write my original theoretical contribution in my personal style from this title and make the citations look complete.
The bad invocation delegates authorship and requests deceptive completion.
Next skills
stress-testing-argumentto expose structural and substantive vulnerabilities.checking-terminology-consistencyafter the sequence stabilizes.reviewing-manuscriptfor whole-manuscript evaluation.
Friction triggers
Create rhetorical-smoothing friction when restructuring deletes tension, qualification, counterevidence, provenance, or unresolved markers, or makes prose seem more complete than the argument.
Friction checks
Compare structured output with the argument map, ledger, interpretation versions, and open frictions. Fluency MUST NOT close an unresolved scholarly object.
Judgment boundary
Ordering and connective recommendations remain agent proposals. New substantive transitions, exclusions, or conclusions require researcher decision and provenance.
Evidence ledger updates
Carry ledger references into affected claims and retain qualifying or contradicting entries. Do not convert context-only material into evidence through placement.
Interpretation history impact
Structure may cite or relocate an interpretation version but must not silently revise or accept it. Material reinterpretation returns to close reading.
Possible epistemic return
New tension exposed during structuring may reopen argument, interpretation, scope, or question. A missing warrant remains repair-oriented rollback.
Productive refusal
If coherence requires inventing a claim or erasing a conflict, preserve the gap, explain the missing judgment, and identify the narrow structuring work still possible.
Gate impact
Rhetorical coherence cannot restore an invalidated gate. Changed substantive dependencies require their original gates to be rerun before review or submission.
Limitations
The boundary between legitimate structuring assistance and substantive co-authorship varies by institution, venue, and research culture. Researchers must follow applicable disclosure and authorship policies. Provenance notes improve transparency but cannot reconstruct every micro-level contribution with certainty.
示例提示词
我已有论证地图和草稿段落,帮我把它们组织成逻辑连贯的章节结构。
所属插件
安装该插件会一并获得同领域的 62 个 Skill / MCP。
同插件的其他科研 Skill
- 学术文献获取下载Auto-downloads open-access PDFs for graded sources and writes a manual worklist for paywalled items. Use after literature-review, before ingest-source.
- 单篇文献入库管理Adds one verified PDF to a shared bibliography library, computing its citation key and keywords. Use to register a single document outside the full workflow.
- 数字人文计算方法Surveys computational DH methods: text mining, NLP, corpus linguistics, archive standards, GIS, network analysis, and OCR. Use for an overview of available DH tools.
- 考古地理信息系统分析Runs archaeological GIS analysis with GeoPandas: catchment analysis, viewshed, kernel density, spatial statistics. Use for mapping archaeological site locations.
- 论证结构提取可视化Extracts and visualizes argument structure: Toulmin reconstruction, support/attack graphs, circularity detection. Use to diagram an argument’s logical structure.
- 考古遗物类型学分析Performs artifact analysis: typological classification, ceramic attribute coding, lithic reduction analysis. Use when classifying excavated artifacts statistically.
- 引文与出处核查Checks citations, quotations, page numbers, and bibliography entries for accuracy and source fit. Use before submission to verify source-supported claims.
- 研究选题构思设计Explores research intent, field state, methodology, and ethics, then writes an approved design doc. Use before starting a new research question or chapter.
- 术语译名一致性检查Audits a manuscript for terms, translations, abbreviations, and names whose forms must stay stable. Use when terminology drift could undermine an argument.
- 计算语用学分析Runs computational pragmatics: speech act classification, implicature detection, discourse coherence, politeness analysis. Use for language-use-and-meaning studies.
- 文献综述学术对话构建Turns verified sources into a structured scholarly conversation among positions, not a chronological summary. Use when synthesizing literature into a debate narrative.
- 语料库语言学分析Performs corpus analysis with NLTK/spaCy: collocation, keyword analysis, KWIC concordance, word2vec, diachronic trends. Use for quantitative text-corpus research.
- 数字档案馆资源检索Queries digital archive REST APIs: Europeana, Chronicling America, Internet Archive, HathiTrust, DPLA, OAI-PMH. Use when searching or harvesting heritage metadata.
- 学术手稿章节撰写Drafts a chapter or article section by section from synthesized wiki content, agreeing each section’s argument first. Use to turn stable research synthesis into prose.
- 研究项目漂移状态检测Checks a shared source library and registered projects for drift: un-indexed PDFs, unmerged keywords, bibkey collisions. Use to audit a multi-project research setup.
- EMI课堂语料转写分析Segments and annotates classroom transcripts, coding language choice and discourse function with anonymised output. Use to quantify classroom talk or translanguaging.
- 人工智能伦理分析Analyzes AI ethics: algorithmic fairness metrics, bias auditing, value alignment, moral philosophy reasoning. Use to evaluate an AI system’s ethical dimensions.
- 研究计划任务执行Executes a ready research plan task by task, gating acquisition before ingest and dispatching analysis. Use after writing-research-plan to run the planned work.
- 研究项目结项清单Runs the final completion checklist: rendering, bibliography, wiki, data, reproducibility, archiving. Use when a manuscript is finalized and ready to publish.
- 形式逻辑自动推理Applies formal logic tools: Z3 SMT solver, modal logic S5, SAT encoding, Lean4 proof verification. Use to formalize or mechanically check a logical argument.
- 研究问题凝练构建Turns a broad topic or intuition into a precise, contestable, researchable question. Use at the start of a project when no defensible question yet exists.
- 历史地理信息系统分析Performs historical GIS work: georeferencing old maps, digitizing boundaries, temporal territory overlays, population interpolation. Use for historical spatial analysis.
- 历史语言学比较分析Analyzes historical linguistics in Python: sound correspondences, cognate detection, phylogenetic trees, Swadesh lists. Use when reconstructing language relationships.
- 历史社会网络分析Builds historical network analyses: correspondence networks, prosopography, temporal community detection, Gephi export. Use to map relationships among historical actors.
常见问题
人文论证逻辑梳理能做什么?
Organizes an approved argument map and notes into manuscript structure while keeping the researcher’s own interpretation. Use to convert materials into ordered prose。
如何安装人文论证逻辑梳理?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「人文论证逻辑梳理」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
人文论证逻辑梳理需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
人文论证逻辑梳理经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。