科研 Skill
人文论证结构规划
planning-humanities-argument
Sequences claims, warrants, evidence, and objections into a defensible argument plan. Use once a question and sources exist but the argument order is not fixed.
SKILL.md
Planning a Humanities Argument
Purpose
Convert a research question and bounded source base into an explicit argument architecture. The skill makes inferential dependencies visible before prose hides them. It does not manufacture a thesis, create evidence, or convert thematic organization into argument by tone alone.
Contract
Accepts
- A
ResearchQuestion,ScopeBoundary, provisional thesis, source inventory, and notes. - Optional venue constraints, word limit, disciplinary expectations, and section drafts.
Requires
- A research question that can be answered propositionally.
- A provisional thesis supplied or approved by the researcher.
- At least one identifiable evidence class for every major claim.
- A declared scope boundary.
Produces
- One argument map composed of
Claim,EvidenceItem,Inference,ArgumentNode, andObjectionrecords. - A dependency-ordered section plan.
- An evidence-gap register.
- An argument-planning gate report.
May produce
- Alternative architectures when more than one defensible sequence exists.
CONDITIONAL PASSwhen the structure is usable but evidence or warrants remain incomplete.FAILwhen the thesis cannot be decomposed into supportable claims.
Fails when
- The thesis is only a topic, slogan, moral preference, or conclusion copied from the prompt.
- A major claim lacks both evidence and a feasible evidence plan.
- Section order depends on concepts not yet defined or claims not yet established.
- The requested architecture requires invented evidence or literature consensus.
Guarantees
- Every major claim is paired with an explicit warrant and evidence status.
- Section order reflects argumentative dependency rather than topic sequence alone.
- Missing inferential work remains visible.
Does not guarantee
- That the thesis is true, original, significant, or publishable.
- That planned evidence will ultimately support the claim.
- That a complete map will yield persuasive prose without further scholarly judgment.
When to use
Use after the research question and scope have stabilized and before substantial drafting. Use during revision when a manuscript contains strong passages but no clear inferential progression, when the conclusion introduces claims not earned earlier, or when sections merely accumulate theorists, themes, or examples.
Do not use this skill to generate an argument from a title alone. Do not treat a table of contents as an argument map. If the researcher has not yet chosen a provisional thesis, route back to formulating-research-question or request a researcher decision.
Inputs required
Collect:
- Primary research question.
- Scope boundary and exclusions.
- Provisional thesis, marked
hypothesisorresearcher-supplied. - Source and evidence inventory with verification states.
- Key concepts and working definitions.
- Venue, length, audience, and deadline.
- Known objections or rival explanations.
If the thesis or scope is missing, stop. If evidence is incomplete but identifiable, continue with explicit gap markers.
Procedure
1. Normalize the thesis
Rewrite the provisional thesis as one contestable proposition without changing its meaning. Separate descriptive, interpretive, causal, genealogical, and normative components. A single sentence that contains several claim types may need to become a claim cluster.
2. Derive enabling claims
Ask what must be established before the thesis can be accepted. Create three to five enabling claims where possible. Each must perform necessary work; a section that can disappear without affecting the conclusion is probably contextual, redundant, or misplaced.
3. Build claim records
For each claim record:
Claim
+ Evidence
+ Warrant
+ Qualification
+ Objection
+ Consequence
Distinguish direct evidence from contextual support and theoretical framing. Do not allow a theory name to stand in for a warrant.
4. Classify inferential movement
Mark transitions as definition, distinction, interpretation, comparison, genealogy, explanation, evaluation, or implication. This prevents silent movement from local observation to historical generalization or from interpretation to causal explanation.
5. Create the dependency graph
Order claims by logical dependence. Definitions precede applications; local readings precede broader implications; source-supported historical claims precede genealogical conclusions. Circular dependencies must be exposed rather than disguised through section headings.
6. Assign section functions
Give every section one primary argumentative function, such as defining a concept, establishing a historical transformation, interpreting a corpus, testing a rival account, or deriving implications. A section may contain context, but context must serve its function.
7. Audit evidence distribution
Check whether one source or example is asked to support incompatible propositions. Mark overused evidence, unsupported claims, and claims supported only by secondary summaries when primary evidence is required.
8. Place objections
Attach objections to the claims they threaten. Do not postpone every objection to a final limitations section. Rank each objection as fatal, major, or minor and indicate whether the planned response is rebuttal, concession, narrowing, or redesign.
9. Budget space
Allocate words according to inferential burden, not enthusiasm. Claims that introduce new concepts, contest established readings, or depend on difficult evidence receive more space than descriptive background.
10. Run removal and reversal tests
For each section, ask what fails if it is removed. Then test whether reversing two adjacent sections creates circularity or premature claims. Record sections whose function remains uncertain.
11. Issue the gate report
Return PASS only when the thesis, enabling claims, warrants, evidence path, objections, and dependencies are explicit. Return CONDITIONAL PASS for non-blocking evidence gaps. Return FAIL when the map is decorative rather than inferential.
Stop signals
Stop when:
- the thesis changes meaning across notes;
- the same evidence is used to prove mutually incompatible claims;
- a claim relies on a concept defined only after its application;
- the evidence path depends on unavailable materials;
- the researcher requests “a persuasive outline” while refusing to state a claim;
- the structure would conceal a fatal objection rather than address it.
Record Researcher decision required rather than choosing a substantive thesis on the researcher’s behalf.
Completion criteria
Complete only when:
- the thesis answers the primary question;
- every major claim has a warrant and evidence status;
- claims are dependency-ordered;
- section functions are non-duplicative;
- major objections are attached to target claims;
- evidence gaps are explicit;
- the final implication does not exceed the scope boundary;
- the gate report identifies the next skill.
Anti-fabrication rules
- Do not invent evidence to fill a clean-looking map.
- Do not convert a theorist’s name into a warrant.
- Do not mark researcher-supplied claims as verified.
- Do not infer consensus from a small source set.
- Do not label a thesis original before literature dialogue and lineage checks.
- Preserve contradictory evidence and unresolved dependencies.
Output format
## Thesis
Statement:
Claim types:
Verification state:
## Argument map
### Claim C1
Function:
Depends on:
Evidence:
Warrant:
Qualification:
Strongest objection:
Response:
Status:
## Section architecture
| Section | Primary function | Claims advanced | Evidence used | Dependency | Word budget |
## Evidence gaps
## Unresolved items
## Gate report
Gate: Argument-planning gate
Status: PASS | CONDITIONAL PASS | FAIL
Evidence checked:
Blocking issues:
Non-blocking risks:
Researcher decisions required:
Required next action:
Next skill: performing-close-reading
Good invocation
Use my approved research question, scope statement, verified source notes, and provisional thesis to create a dependency-ordered argument map. Mark every missing warrant and do not invent evidence.
Bad invocation
Make a persuasive five-part argument proving that AI has changed humanity forever. Use whatever evidence sounds right.
The bad invocation supplies an inflated conclusion, no bounded corpus, and permission to fabricate support.
Next skills
performing-close-readingto generate accountable object-level evidence.structuring-humanities-argumentto organize researcher-authored material around the map.stress-testing-argumentto challenge the architecture before drafting.
Friction triggers
Create claim–evidence friction when a central claim lacks support, counterevidence is hidden, a verified source is irrelevant, or a warrant promotes inference into fact.
Friction checks
For every major claim inspect supporting, qualifying, contradicting, disputed, and insufficient ledger entries. Do not pass by counting supportive sources.
Judgment boundary
Alternative thesis structures and responses may be recommended, but choosing a thesis, concession, or acceptable limitation remains the researcher's decision.
Evidence ledger updates
Connect each Claim to ledger entries and display evidential_standing alongside verification state and limitations.
Interpretation history impact
Reference the exact interpretation version used by a claim. New readings append versions and trigger dependency review rather than silently changing the warrant.
Possible epistemic return
New evidence that changes the question or core premise may return to question, scope, literature, or interpretation. Missing planned support remains rollback or pause.
Productive refusal
When evidence cannot establish a major claim, give the supported narrower proposition, missing evidence, affected dependencies, and next valid research action.
Gate impact
Unresolved central CONTRADICTS or INSUFFICIENT standing prevents PASS. Material Claim or EvidenceItem changes require bounded citation, argument-review, and submission rechecks.
Limitations
Argument maps clarify dependencies but cannot settle interpretive disputes or determine disciplinary value. Some humanities arguments are deliberately recursive, fragmentary, or essayistic; such forms still require a defensible account of how their sequence produces knowledge.
示例提示词
我已有研究问题和证据,帮我规划出论点、理由和反驳的合理顺序。
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
人文论证结构规划能做什么?
Sequences claims, warrants, evidence, and objections into a defensible argument plan. Use once a question and sources exist but the argument order is not fixed。
如何安装人文论证结构规划?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「人文论证结构规划」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。
人文论证结构规划需要哪些权限?
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。
人文论证结构规划经过官方审核吗?
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。