paper-workflow

Paper Workflow: Dispatcher

This is the entry point, not a menu. A request such as 优化一下论文 or improve my manuscript names a goal, not a layer. Manuscript work happens at distinct layers, and editing the wrong layer first wastes the edit: a paragraph whose scientific role is wrong should never be polished, and a sentence whose claim is unstable should never be re-punctuated.

Do not answer a general manuscript request by loading a single specialist skill. Classify the request, then run the whole chain for that class.

Default assumption: unless a conference venue is named, the manuscript follows the journal-oriented Nature-style path.

Step 1: Classify by what was actually handed over

Input	Class	Chain
One sentence or one paragraph	passage	write-scientific-manuscript, then anti-defensive-writing if the passage is hedged, over-caveated or written in an audit, self-critical, developer or commitment voice, then scientific-prose-style
One section to draft or rewrite in prose	section	scientific-writing, write-scientific-manuscript, anti-defensive-writing, then scientific-prose-style
A Results section that is scientifically settled but reads figure-by-figure	results-flow	results-section-revision, anti-defensive-writing, then scientific-prose-style
A whole draft, or no unit named	manuscript	manuscript-optimizer, scientific-writing, write-scientific-manuscript, anti-defensive-writing, then scientific-prose-style
Reads like an audit report, a rebuttal or a self-critique; hedged, over-caveated or apologetic; a paragraph opens with a limitation; the SI or data statements confess what could not be found; the text names folders, files or build steps, or promises a future release	posture	anti-defensive-writing, then scientific-prose-style. If the claim hierarchy is not yet settled, run manuscript-optimizer first: an unnecessary disclaimer and a real scope condition look identical while the claim is still moving
A Review, survey, or Perspective	review-article	review-article-architecture first, then the Review path below
A long draft carried across many sessions	long-draft	draft-marker-discipline then review-article-architecture drift audit
Near submission or resubmission	preflight	submission-audit, citation-verifier, claim-source-verification, stats-reporting-audit, data-availability
Reviewer comments exist	response	paper-reviewer to inventory every ask, rebuttal-response to draft and calibrate, then paper-reviewer again to grade the draft. paper-reviewer is not in the default recommended set; install it with --set all
A manuscript to referee, or a request to predict what reviewers will attack	referee	paper-reviewer, installed with --set all
Figures are the bottleneck	figure	figure-planner, then nature-figure to render, then figure-style to check. The last two are the figure stack, installed with --figure
No draft yet, project new or messy	bootstrap	paper-bootstrap then nature-portfolio-playbook

When two classes with different chains both fit, ask one question. That is the one case worth a clarifying question; guessing wastes more time than asking.

Step 2: Announce the chain, then run it in order

State the chain in one line before starting, so the author can redirect early:

Running the manuscript chain: structure (manuscript-optimizer), prose (scientific-writing), passage logic (write-scientific-manuscript), posture (anti-defensive-writing), then sentence pass (scientific-prose-style).

Load each skill in sequence and apply it. Do not skip a link because the previous one already improved the text. Each layer catches a different defect class, and a later layer cannot see the defect an earlier one owns.

Step 3: Stop rules

Stop the chain and report why when:

• an upstream layer finds a problem that invalidates downstream work, such as a claim the evidence does not support. Fix or surface it before polishing;
• the request was narrow. 帮我把这句话改短 is a passage job, not a licence to restructure the paper;
• a later layer would undo a decision the author explicitly approved.

Never run preflight on a draft still in manuscript class. Auditing unstable text produces findings that evaporate on the next revision.

Never run scientific-prose-style on a drifted Review before the drift audit. Polishing a drifted draft makes the drift harder to see, not easier.

Never run anti-defensive-writing before the claim hierarchy is stable. Until the claim is settled, an unnecessary disclaimer and a real scope condition look identical, and the pass strips the wrong one.

The layers

Every skill sits at one layer. This is why the chains are ordered.

1. Structure: is there a defensible claim hierarchy and evidence chain? manuscript-optimizer for research articles, review-article-architecture for Reviews.
2. Prose: is the section drafted in full paragraphs that carry the argument? scientific-writing, with results-section-revision for late-stage Results architecture.
3. Passage logic: is this paragraph followable? Buried topic sentences, missing bridges, ambiguous referents, noun chains, incomplete comparisons, coined terminology. write-scientific-manuscript.
4. Rhetorical posture: does the text advance its claim, or negotiate with an imagined critic? Audit voice (project process in the paper), defensive voice (arguing with an imagined reviewer), self-critical voice (the paper grading itself), developer voice (the repository in the paper), commitment voice (promises of a future release), caveats in high-impact positions, paragraphs that open with a limitation, reflexive not X but Y. anti-defensive-writing, which also covers the SI, legends and data statements. It runs after the claim hierarchy is settled, because before that an unnecessary disclaimer and a real scope condition are indistinguishable: the claim they qualify is still moving.
5. Sentence: em-dash budget, hedging, sentence rhythm, paragraph openers. scientific-prose-style, last.

Integrity checks run alongside, not in sequence: citation-verifier, claim-source-verification, stats-reporting-audit, draft-marker-discipline.

Layer 4 has a boundary the other layers do not: a load-bearing statement stays. Load-bearing is decided by what a sentence states, not by which skill added it: the unit of replication and n, no P values, blinding and exclusions, an access route, the count behind a reporting decision, an estimator's assumptions, a null result, and any scope condition the Methods needs to stay reproducible. anti-defensive-writing may move such a statement out of a high-impact position, state it once instead of at every mention, or rewrite it as positive scope, but it must not delete it. A pass that silently removes one is a reporting failure, not a style improvement. Audit-voice wording added by an integrity check ("as checked", "could not be identified") is not protected.

Default journal path

1. paper-bootstrap
2. nature-portfolio-playbook when venue fit or article type is uncertain
3. Refresh notes/project_truth.md, notes/result_summary.md, notes/paper_handoff.md after any experimental, statistical, or figure update
4. manuscript-optimizer or scientific-writing per the class table, then write-scientific-manuscript for passage-level clarity
5. figure-planner, then nature-figure to produce and figure-style to check (figure stack, --figure)
6. results-section-revision when Results is stable but reads jumpy
7. stats-reporting-audit
8. citation-verifier, then claim-source-verification
9. data-availability
10. anti-defensive-writing, after the integrity checks above have added the statements they require
11. scientific-prose-style
12. submission-audit; anything it adds is held to rule zero of anti-defensive-writing, and that skill's detection pass is rerun on the changed passages
13. after external review: paper-reviewer to inventory the reports, rebuttal-response to draft and calibrate, then paper-reviewer again to grade the draft

Review, survey, and Perspective path

A Review is not a short research article. Its failure mode is becoming a different Review, not overclaiming past its data.

1. review-article-architecture to establish the governing plan document first
2. nature-portfolio-playbook for venue and article-type fit
3. draft-marker-discipline to set up the marker system before drafting starts
4. scientific-writing, sourcing in step with the prose
5. citation-verifier, then claim-source-verification
6. figure-planner, then nature-figure and figure-style (figure stack, --figure)
7. review-article-architecture drift audit, before any compression pass
8. draft-marker-discipline to measure length and triage what remains open
9. anti-defensive-writing
10. scientific-prose-style, last
11. submission-audit

Run step 7 before step 10, never after.

Choosing between adjacent skills

• scientific-writing when a section mostly needs drafting or rewriting in prose, or when a citation style or reporting guideline is named. manuscript-optimizer when the story, evidence chain, figure logic, or terminology may be unstable. write-scientific-manuscript when the science is settled but the passage is hard to follow.
• results-section-revision when the remaining problem is local Results architecture rather than claim selection.
• anti-defensive-writing when the text is accurate but reads like an audit report, a rebuttal or a self-critique: it reports project process instead of findings, keeps saying what it does not claim, opens paragraphs with caveats, confesses what could not be found, explains itself to a critic who is not in the room, documents the repository, or promises what does not exist yet. It covers the SI, legends and data statements as well as the main text. scientific-prose-style when the remaining problem is punctuation, rhythm, em-dash budget, or hedge calibration inside a single sentence. They stack, in that order, because removing defensive scaffolding rewrites the paragraph openers and sentence boundaries the punctuation pass then settles. Neither one may overrule an integrity audit; see the layer-4 boundary above. A Methods section is mostly load-bearing reproducibility detail, and the edit is usually to convert a negation into positive scope and to state it once instead of at every mention.
• citation-verifier when the bibliography as an artifact is the problem: duplicate keys, missing fields, DOI syntax, cited-but-undefined. claim-source-verification when the question is whether a source supports the sentence citing it. They stack, in that order. A clean bibliography audit says nothing about claim support: in one measured run, 55 of 139 proposed sources were rejected, none of them fabricated.
• reference-audit-guide when references must be checked against live scholarly APIs rather than inspected locally. Optional set, installed with --set all. It ships runnable verification scripts and is the only stage that catches a fabricated citation carrying a well-formed DOI.
• review-article-architecture for a Review, survey, or Perspective, or whenever a piece written across many sessions may no longer match its brief. manuscript-optimizer for research articles.
• draft-marker-discipline before a batch pass over open markers, before quoting a manuscript's length, before removing superseded material, and before scripting the same edit across many files.
• figure-planner to decide what each figure argues, then nature-figure to render it, then figure-style to check correctness and legibility before export. The last two are the figure stack; if they are not installed, figure-planner still produces the panel plan and the author renders it themselves.
• conference-paper-writing only when a conference venue is explicitly named. Optional set, installed with --set all.
• paper-reviewer when the question is what the reviewer asked or whether the reviewer would accept the answer. rebuttal-response when the question is what the authors may claim and how the letter, manuscript, and Supplementary Information stay consistent. They stack, in that order, and paper-reviewer runs a second time at the end to grade the draft. rebuttal-response is in the recommended set; paper-reviewer is in the optional set, installed with --set all. A manuscript change made in reply to a reviewer follows rule zero of anti-defensive-writing: a result, a precise definition or a narrowed claim, not an added caveat.

Working principle

Do not polish sections written from stale memory. After experimental, statistical, or figure updates, refresh notes/project_truth.md, notes/result_summary.md, and notes/paper_handoff.md before attempting heavy revision.

Common mistakes

• answering a general manuscript request with whichever single skill matched the wording best
• polishing sentences before the claim hierarchy is stable
• running a defensive-writing pass before the claim hierarchy is stable, which strips real scope conditions along with the disclaimers
• letting a defensive-writing pass delete a limitation that a statistics, citation, or data audit put there, instead of moving it out of a high-impact position and stating it once
• running a submission audit on a draft still being restructured
• polishing a Review before its drift audit
• using conference-style writing skills by default for journal manuscripts
• rewriting the manuscript from experiment memory instead of a current result_summary.md
• editing figure legends late without rechecking the Results text
• leaving repository choice, accession IDs, or source-data coverage until the portal is open
• treating citation formatting as the same thing as citation verification
• treating a clean bibliography as evidence that the sources support the claims
• writing a response letter before deciding the underlying manuscript edits
• answering a reviewer report without first listing every ask and sub-ask in the reviewer's own words
• renumbering, reordering, or grouping reviewer comments by theme, which makes coverage impossible to check at a glance
• rewriting whole paragraphs when the author flagged two sentences