skills/paper-draft-consistency-editor/SKILL.md
Edit ML/AI paper drafts for internal consistency. Use after sections exist to align claims, terminology, figures, tables, captions, limitations, and conclusion.
npx skillsauth add a-green-hand-jack/ml-research-skills paper-draft-consistency-editorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Check and fix whether a paper draft is internally coherent. This skill is an editor pass, not a reviewer simulation and not a first-draft writer. It makes the title, abstract, introduction, methods, results, figures, tables, captions, related work, limitations, and conclusion agree with the paper's active claims and evidence.
Use this skill for:
PROVISIONAL-RESULT or PR-### placeholderspaper/.agent/writing-contract.mdDo not use this skill to decide the paper's positioning from scratch. Use paper-positioning-planner for that. Do not use it to write major new prose. Use paper-writing-memory-manager to record stale locations, dependency conflicts, and open writing threads found during consistency checks. Use paper-writing-assistant after consistency issues are identified. Do not simulate hostile reviewers; use paper-reviewer-simulator for acceptance-risk critique.
<installed-skill-dir>/
├── SKILL.md
├── references/
│ ├── consistency-rules.md
│ └── edit-protocol.md
└── templates/
└── consistency-report.md
references/consistency-rules.md.paper-writing-assistant/references/paper-quality-heuristics.md when auditing broad paper quality, readability, evidence integrity, or whether the draft hides unfair comparisons.references/edit-protocol.md before editing paper source.paper-writing-assistant/references/edit-whitelist-contract.md when declaring a controlled rewrite pass with frozen and allowed operation types.templates/consistency-report.md for substantial reports.paper/.agent/writing-contract.md when present.paper/.agent/writing-memory/, paper/.agent/writing-style.md, paper/.agent/writing-style-lessons.md, paper/.agent/notation-contract.md, paper/.agent/paper-evidence-board.md, paper/.agent/provisional-results.md, and root memory/claim-board.md / memory/evidence-board.md when present.Find:
paper/, current directory, or user-provided pathpaper/.agent/writing-contract.md or .agent/writing-contract.mdpaper/.agent/paper-evidence-board.mdpaper/.agent/provisional-results.mdmain.tex, paper.tex, sections/*.tex, appendix, figure wrappers, table filesmemory/claim-board.md, memory/evidence-board.md, memory/action-board.mdIf no writing contract exists, still run the consistency pass from the draft, but recommend paper-writing-contract-planner.
Modes:
audit: produce a report with issues and proposed fixesedit: make narrow source edits for clear inconsistenciesreport: save a report under paper/.agent/draft-consistency-report.mdScopes:
full: all checksclaims: title/abstract/intro/result/conclusion claim alignmentterms: names, notation, metrics, datasets, baselinesfigures: figures, captions, callouts, visual jobsresults: tables, numbers, result prose, provisional placeholdersDefault to audit and full unless the user asks for direct edits.
Extract a compact map:
## Draft Story Map
- Title promise:
- Abstract claims:
- Intro thesis:
- Contribution bullets:
- Method claims:
- Experiment claims:
- Figure/table takeaways:
- Limitation scope:
- Conclusion claims:
- Active contract:
Mark claim IDs such as CLM-### when available. If IDs are missing, use local labels like CLM-DRAFT-001.
Read references/consistency-rules.md.
Check:
writing-style.md or record a new lesson/preference?Classify each issue:
blocking: could make the draft misleading or unsupportedmajor: materially confuses the paper storyminor: naming, wording, or local flow inconsistencystyle: polish issue that does not affect meaningRead references/edit-protocol.md.
For each issue, choose:
direct-edit: safe local wording/name/reference fixrewrite-request: needs paper-writing-assistantcontract-update: needs paper-writing-contract-plannerevidence-update: needs paper-evidence-boardwriting-memory-update: needs paper-writing-memory-manager to record dependency conflicts, stale locations, or closed threads — always write: sections audited, issues resolved, issues left open, and any protected invariants identified during this passstyle-memory-update: needs paper-writing-memory-manager to record a writing-layer lesson, preference, project contract, protected invariant, or notation ruleexperiment-action: needs experiment-design-plannerdiagnosis: needs result-diagnosisleave-note: intentional inconsistency or unresolved decisionWhen editing:
Use templates/consistency-report.md for substantial audits.
If saving and no path is specified, use:
paper/.agent/draft-consistency-report.md
Report:
Before finalizing:
testing
Bootstrap project-local ml-research-skills. Use from global installs when creating a new ML research project, enabling this collection in an existing ML research repo, or deciding whether to install the full bundle locally. Route to project-init for new projects; do not handle paper or experiment work directly.
development
Route project operations tasks — git, memory, bootstrap, remote, workspace, code review, timeline, ops — to the correct skill. Use when the task involves commits, pushes, worktrees, project memory, enabling project-local skills, SSH/server coordination, sidecar runners, or audits. Do not solve the ops task directly.
testing
Route ML/AI paper writing tasks to the correct skill — contract planning, prose drafting, section writing, consistency editing, review simulation, rebuttal, submission, or citation work. Use when the task involves writing, revising, reviewing, or submitting a paper instead of guessing between paper-writing-assistant, paper-writing-contract-planner, paper-reviewer-simulator, auto-paper-improvement-loop, or citation skills. Do not draft prose directly.
data-ai
Project-local router for ML research skill selection. Use inside an initialized ML research project, or while maintaining this skill repo, when the user describes an ML research/paper/experiment/discovery/ops/release workflow and may not know the skill; route to a domain router or high-signal leaf. Do not use for generic non-ML projects.