skills/camera-ready-finalizer/SKILL.md
Finalize accepted ML/AI papers for camera-ready submission. Use for de-anonymization, rebuttal promises, supplement updates, final LaTeX checks, and release handoff.
npx skillsauth add a-green-hand-jack/ml-research-skills camera-ready-finalizerInstall 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.
Finalize an accepted paper so the submitted camera-ready version is consistent, de-anonymized, claim-safe, and ready to hand off to code release or artifact evaluation.
Use this skill when:
Do not use this skill for pre-submission readiness. Use submit-paper before initial submission. Use rebuttal-strategist while reviews are still active. Use release-code for the public code repository after paper-facing obligations are clear.
Pair this skill with:
rebuttal-strategist to recover reviewer issues, response promises, and promised revisionspaper-evidence-board to close final claim/evidence/provenance/risk/action/handoff linksfigure-results-review to recheck final figures, captions, and tables after editscitation-audit for final BibTeX, citation, label, and metadata correctnesscitation-coverage-audit when accepted-paper edits reveal missing related workconference-writing-adapter for final wording of accepted reviewer criticism or limitationssubmit-paper for final format and compile checksrelease-code and artifact-evaluation-prep for public code and artifact handoffadd-git-tag when marking the accepted/camera-ready milestoneresearch-project-memory when final paper status should persist across sessions<installed-skill-dir>/
├── SKILL.md
└── references/
├── claim-evidence-final-lock.md
├── de-anonymization.md
├── final-submission-audit.md
├── memory-writeback.md
├── rebuttal-promise-audit.md
├── release-handoff.md
├── report-template.md
└── supplement-consistency.md
references/rebuttal-promise-audit.md, references/de-anonymization.md, references/claim-evidence-final-lock.md, and references/final-submission-audit.md.references/supplement-consistency.md when appendix, supplement, checklist, or extra material exists.references/release-handoff.md when code, project page, artifact, data, checkpoints, or reproduction links are involved.references/report-template.md before writing the final report.references/memory-writeback.md when the project has memory/, component .agent/ folders, or the user asks for persistent memory.local, Overleaf-GitHub, CI, or unknown) to decide where final compile evidence comes from.paper-worktrees/ for camera-ready finalization when the main paper branch must preserve the submitted or arXiv state.camera-ready-public or publisher-artifact unless the user explicitly says the source package remains private.Collect:
paper/ or a paper-worktrees/ camera-ready worktreeCLM-###, EVD-###, RSK-###, ACT-###, REV-###, or PROM-###If no promise list exists, create one from reviews, rebuttal, and discussion before editing the paper.
Read references/rebuttal-promise-audit.md.
Build a promise ledger:
Statuses:
fulfilledpartially-fulfilledsupersedednot-applicablemissingneeds-author-decisionDo not silently drop a promise because it is inconvenient. If a promise cannot be fulfilled, mark the risk and draft a conservative note or limitation if needed.
Read references/de-anonymization.md.
Check:
Do not invent funding, affiliation, or author-order details. Ask the user if a required personal/institutional detail is missing.
Read references/claim-evidence-final-lock.md.
For each main claim:
If a claim is unsupported, either narrow it, move it to limitations/future work, or cut it.
Read references/supplement-consistency.md when relevant.
Check:
Read references/final-submission-audit.md.
Check:
.tex files.agent/, AGENTS.md, CLAUDE.md, raw CSVs, internal result docs, plotting scripts, notebooks, provenance ledgers, reviewer/rebuttal scratch, or private paths in the source packageUse citation-audit and submit-paper for detailed checks when needed.
If the compile backend is local, detect the compiler at runtime before compiling. If the backend is Overleaf-GitHub, confirm the GitHub remote, push the camera-ready source when requested, and ask the user to compile in Overleaf. If the backend is CI, use CI logs and artifacts. Use remote logs or screenshots to drive any final LaTeX fixes.
Read references/release-handoff.md when relevant.
Produce handoff items for:
release-code: repository visibility, README, license, citation file, tag, model/data links, reproduction commandsartifact-evaluation-prep: install instructions, expected runtime, minimal demo, hardware, checkpoints, data, troubleshootingadd-git-tag: accepted/camera-ready milestone summaryKeep paper finalization separate from code release, but make obligations explicit.
Read references/report-template.md.
If saving to a project and no path is given, use:
docs/submission/camera_ready_audit_YYYY-MM-DD_<venue>.md
The report must include:
Read references/memory-writeback.md when memory exists.
Update:
memory/decision-log.md: acceptance and camera-ready decisionsmemory/claim-board.md: final claim statusmemory/evidence-board.md: final paper-ready evidence and artifact linksmemory/risk-board.md: any residual accepted risksmemory/action-board.md: final blockers, release tasks, artifact tasks, and tag tasksmemory/source-visibility-board.md: final source visibility tier, cleanup gate, public-clean audit status, and remaining source-package blockerspaper/.agent/: camera-ready status, final metadata, final PDF path, final upload notesrebuttal/.agent/: promise fulfillment status and accepted outcomeBefore finalizing:
citation-auditsubmit-papersubmit-paper / source cleanuptesting
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.