rebuttal
Skill9 starsChanged 3 months agoMITView on GitHub
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says \"rebuttal\", \"reply to reviewers\", \"ICML rebuttal\", \"OpenReview response\", or wants to answer external reviews safely.
15 other projects use a version of this, 6 of them edited.
Adopted by
Most recently taken up by
- adithyanraj03/dsh-skills-packtheir own version, first seen Nov 15, 2026
- NilsHellwig/acl-paper-skillstheir own version, first seen Nov 8, 2026
- acprk/crypto-research-agentstheir own version, first seen Nov 4, 2026
- kfangw/research-opstheir own version, first seen Oct 25, 2026
- PKU-DAIR/AutoScitheir own version, first seen Oct 25, 2026
- DAIR-AutoResearch/AutoScitheir own version, first seen Oct 15, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
skyllwtSkillexp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
phanghonghaoSkillposter
HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.
Also in 4 projects that use this
- +6 more from Lambenthan
- +1 more from skyllwt
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 6
- wanshuiyin/Auto-claude-code-research-in-sleep★ 19k51% same
- Chanw-research/claude-code-paper-writing★ 4259% same
- catalsqlb-cmd/Prism-H★ 1686% same
- yvesory/academic-research-suite★ 954% same
- raja21068/AutoResearch★ 259% same
- talhaMah56/claude_skills★ 050% same
Wrote their own version · 9
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- skyllwt/OmegaWiki★ 1.7ksame name
- Lambenthan/empiricalwiki★ 85same name
- acprk/crypto-research-agents★ 15same name
- NilsHellwig/acl-paper-skills★ 3same name
- adithyanraj03/dsh-skills-pack★ 0same name
- kfangw/research-ops★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- autodl-hpcSkill
- experiment-bridgeSkill
- experiment-planSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
- autodl-hpcSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-writeSkill
- research-refineSkill
- research-reviewSkill
- experiment-bridgeSkill
- experiment-planSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- grant-proposalSkill
- idea-creatorSkill
- idea-discoverySkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-posterSkill
- paper-slidesSkill
- paper-writeSkill
- paper-writingSkill
- research-refineSkill
- research-reviewSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
32 rules. 0 are common, 22 are distinctive, and 10 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
22
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
follow-up rounds: after the initial rebuttal
- Distinctive: line 32
run new experiments automatically
- Distinctive: line 37
If the user already has new results, derivations, or approved commitments, the skill can incorporate them as user-confirmed evidence.
- Distinctive: line 72
If venue rules or limit are missing, stop and ask before drafting.
- Very specific: line 86
If rebuttal/REBUTTAL_STATE.md exists → resume from recorded phase
- Distinctive: line 95
If ambiguous, pause and ask
- Distinctive: line 118
If unresolved blockers → pause and present to user
- Very specific: line 120
QUICK_MODE exit: If QUICK_MODE = true, stop here.
- Very specific: line 126
If the strategy plan identifies issues that require new empirical evidence (tagged response_mode: grounded_evidence with evidence_source: …
- Very specific: line 138
Wait for results, then update ISSUE_BOARD.md:
- Distinctive: line 140
Update evidence source for relevant issue cards
- Distinctive: line 142
If experiments fail or are inconclusive:
- Distinctive: line 144
Do NOT fabricate positive results
- Distinctive: line 148
Time guard: If estimated GPU-hours exceed rebuttal deadline, skip and flag for manual handling.
- Distinctive: line 159
Default reply pattern per issue:
- Distinctive: line 174
NEVER invent experiments, numbers, derivations, citations, or links
- Distinctive: line 175
NEVER promise what user hasn't approved
- Distinctive: line 176
If no strong evidence exists, say less not more
- Very specific: line 210
Every checklist item must map to at least one issue_id from ISSUE_BOARD.md.
- Very specific: line 211
Every promise in REBUTTAL_DRAFT_v1.md that implies a paper edit must appear as a checklist item — if it is not in the plan, it is a …
- Distinctive: line 212
Never add items that are not backed by the draft or by user-confirmed evidence.
- Distinctive: line 253
No markdown formatting, no extras
- Distinctive: line 271
When new reviewer comments arrive:
- Very specific: line 276
Update rebuttal/REVISION_PLAN.md in place — add any new checklist items introduced by the follow-up, tick off items the author has already …
- Distinctive: line 278
Use Codex MCP reply for continuity if useful
- Very specific: line 283
After Phase 6 (initial rebuttal) or Phase 8 (follow-up rounds) finalize rebuttal/REBUTTAL_DRAFT_rich.md, invoke:
- Very specific: line 291
Non-blocking: if /render-html fails, log the failure and treat the rebuttal phase as complete — the PASTE_READY.txt and …
- Distinctive: line 297
Large file handling: If Write fails, retry with Bash heredoc silently.
- Distinctive: line 298
Never fabricate: No invented evidence, numbers, derivations, citations, or links.
- Distinctive: line 299
Never overpromise: Only promise what user explicitly approved.
- Distinctive: line 300
Full coverage: Every reviewer concern tracked and accounted for.
- Very specific: line 314
After each spawn_agent or send_input reviewer call, save the trace following ../shared-references/review-tracing.md.
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Workflow 4: Rebuttal
Capability Routing
This is a first-layer entry skill. Keep it loaded as the user-facing route; when a request needs a specialized capability below, resolve the debuffer repo root from .debuffer_skills/installed-skills-codex.txt (repo_root) when available, read the referenced library SKILL.md, then follow that skill. Do not copy the whole library skill into this file.
/auto-paper-improvement-loop: read../../skills-codex-library/review/auto-paper-improvement-loop/SKILL.md./kill-argument: read../../skills-codex-library/review/kill-argument/SKILL.md./paper-claim-audit: read../../skills-codex-library/review/paper-claim-audit/SKILL.md./citation-audit: read../../skills-codex-library/review/citation-audit/SKILL.md.
Prepare and maintain a grounded, venue-compliant rebuttal for: $ARGUMENTS
Scope
This skill is optimized for:
- ICML-style text-only rebuttal
- strict character limits
- multiple reviewers
- follow-up rounds after the initial rebuttal
- safe drafting with no fabrication, no overpromise, and full issue coverage
This skill does not:
- run new experiments automatically
- generate new theorem claims automatically
- edit or upload a revised PDF
- submit to OpenReview / CMT / HotCRP
If the user already has new results, derivations, or approved commitments, the skill can incorporate them as user-confirmed evidence.
Lifecycle Position
Workflow 1: idea-discovery
Workflow 1.5: experiment-bridge
Workflow 2: auto-review-loop (pre-submission)
Workflow 3: paper-writing
Workflow 4: rebuttal (post-submission external reviews)Constants
- VENUE =
ICML— Default venue. Override if needed. - RESPONSE_MODE =
TEXT_ONLY— v1 default. - REVIEWER_MODEL = resolve from the shared model policy or an explicit per-run override; never hard-code a workflow default.
- REVIEWER_BACKEND =
codex— Default: Codex xhigh stress tester. Use--reviewer: oracle-proonly when explicitly requested; if Oracle is unavailable, warn and fall back to Codex xhigh. See../shared-references/reviewer-routing.md. - MAX_INTERNAL_DRAFT_ROUNDS = 2 — draft → lint → revise.
- MAX_STRESS_TEST_ROUNDS = 1 — One Codex MCP critique round.
- MAX_FOLLOWUP_ROUNDS = 3 — per reviewer thread.
- AUTO_EXPERIMENT = false — When
true, automatically invoke/experiment-bridgeto run supplementary experiments when the strategy plan identifies reviewer concerns that require new empirical evidence. Whenfalse(default), pause and present the evidence gap to the user for manual handling. - QUICK_MODE = false — When
true, only run Phase 0-3 (parse reviews, atomize concerns, build strategy). OutputsISSUE_BOARD.md+STRATEGY_PLAN.mdand stops — no drafting, no stress test. Useful for quickly understanding what reviewers want before deciding how to respond. - REBUTTAL_DIR =
rebuttal/ - RENDER_HTML = true — When
true(default), auto-renderrebuttal/REBUTTAL_DRAFT_rich.mdto HTML after Phase 6 / Phase 8 finalization via/render-html. Uses full review gate (reviewer-facing pre-submission deliverable). The plain-textPASTE_READY.txtis NOT rendered (it's character-counted plain text by design). Setfalseto skip, or pass— render html: false. Non-blocking: failures don't invalidate the rebuttal.
Override:
/rebuttal "paper/" — venue: NeurIPS, character limit: 5000
Required Inputs
- Paper source — PDF, LaTeX directory, or narrative summary
- Raw reviews — pasted text, markdown, or PDF with reviewer IDs
- Venue rules — venue name, character/word limit, text-only or revised PDF allowed
- Current stage — initial rebuttal or follow-up round
If venue rules or limit are missing, stop and ask before drafting.
Safety Model
Three hard gates — if any fails, do NOT finalize:
- Provenance gate — every factual statement maps to:
paper,review,user_confirmed_result,user_confirmed_derivation, orfuture_work. No source = blocked. - Commitment gate — every promise maps to:
already_done,approved_for_rebuttal, orfuture_work_only. Not approved = blocked. - Coverage gate — every reviewer concern ends in:
answered,deferred_intentionally, orneeds_user_input. No issue disappears.
Workflow
Phase 0: Resume or Initialize
- If
rebuttal/REBUTTAL_STATE.mdexists → resume from recorded phase - Otherwise → create
rebuttal/, initialize all output documents - Load paper, reviews, venue rules, any user-confirmed evidence
Phase 1: Validate Inputs and Normalize Reviews
- Validate venue rules are explicit
- Normalize all reviewer text into
rebuttal/REVIEWS_RAW.md(verbatim) - Record metadata in
rebuttal/REBUTTAL_STATE.md - If ambiguous, pause and ask
Phase 2: Atomize and Classify Reviewer Concerns
Create rebuttal/ISSUE_BOARD.md.
For each atomic concern:
issue_id(e.g., R1-C2)reviewer,round,raw_anchor(short quote)issue_type: assumptions / theorem_rigor / novelty / empirical_support / baseline_comparison / complexity / practical_significance / clarity / reproducibility / otherseverity: critical / major / minorreviewer_stance: positive / swing / negative / unknownresponse_mode: direct_clarification / grounded_evidence / nearest_work_delta / assumption_hierarchy / narrow_concession / future_work_boundarystatus: open / answered / deferred / needs_user_input
Phase 3: Build Strategy Plan
Create rebuttal/STRATEGY_PLAN.md.
- Identify 2-4 global themes resolving shared concerns
- Choose response mode per issue
- Build character budget (10-15% opener, 75-80% per-reviewer, 5-10% closing)
- Identify blocked claims (ungrounded or unapproved)
- If unresolved blockers → pause and present to user
QUICK_MODE exit: If QUICK_MODE = true, stop here. Present ISSUE_BOARD.md + STRATEGY_PLAN.md to the user and summarize: how many issues per reviewer, shared vs unique concerns, recommended priorities, and evidence gaps. The user can then decide to continue with full rebuttal (/rebuttal — quick mode: false) or write manually.
Phase 3.5: Evidence Sprint (when AUTO_EXPERIMENT = true)
Skip entirely if AUTO_EXPERIMENT is false — instead, pause and present the evidence gaps to the user.
If the strategy plan identifies issues that require new empirical evidence (tagged response_mode: grounded_evidence with evidence_source: needs_experiment):
- Generate a mini experiment plan from the reviewer concerns:
- What to run (ablation, baseline comparison, scale-up, condition check)
- Success criterion (what result would satisfy the reviewer)
- Estimated GPU-hours
- Invoke
/experiment-bridgewith the mini plan:/experiment-bridge "rebuttal/REBUTTAL_EXPERIMENT_PLAN.md" - Wait for results, then update
ISSUE_BOARD.md:- Tag completed experiments as
user_confirmed_result - Update evidence source for relevant issue cards
- Tag completed experiments as
- If experiments fail or are inconclusive:
- Switch response mode to
narrow_concessionorfuture_work_boundary - Do NOT fabricate positive results
- Switch response mode to
- Save experiment results to
rebuttal/REBUTTAL_EXPERIMENTS.mdfor provenance tracking.
Time guard: If estimated GPU-hours exceed rebuttal deadline, skip and flag for manual handling.
Phase 4: Draft Initial Rebuttal
Create rebuttal/REBUTTAL_DRAFT_v1.md.
Structure:
- Short opener — thank reviewers + 2-4 global resolutions
- Per-reviewer numbered responses — answer → evidence → implication
- Short closing — resolved / remaining / acceptance case
Default reply pattern per issue:
- Sentence 1: direct answer
- Sentence 2-4: grounded evidence
- Last sentence: implication for the paper
Heuristics from 5 successful rebuttals:
- Evidence > assertion
- Global narrative first, per-reviewer detail second
- Concrete numbers for counter-intuitive points
- Name closest prior work + exact delta for novelty disputes
- Concede narrowly when reviewer is right
- For theory: separate core vs technical assumptions
- Answer friendly reviewers too
Hard rules:
- NEVER invent experiments, numbers, derivations, citations, or links
- NEVER promise what user hasn't approved
- If no strong evidence exists, say less not more
Also generate rebuttal/PASTE_READY.txt (plain text, exact character count).
Also generate rebuttal/REVISION_PLAN.md — the overall revision checklist.
This document is the single source of truth for every paper revision promised (explicitly or implicitly) in the rebuttal draft. It exists so the author can track follow-through after the rebuttal is submitted, and so the commitment gate in Phase 5 has a concrete artifact to validate against.
Structure:
- Header
- Paper title, venue, character limit, rebuttal round
- Links back to
ISSUE_BOARD.md,STRATEGY_PLAN.md,REBUTTAL_DRAFT_v1.md
Overall checklist — a single flat GitHub-style checklist covering every revision item, so the author can tick items off as they land in the camera-ready / revised PDF:
## Overall Checklist - [ ] (R1-C2) Add assumption hierarchy table to Section 3.1 — commitment: `approved_for_rebuttal` — owner: author — status: pending - [ ] (R2-C1) Clarify novelty delta vs. Smith'24 in Section 2 related work — commitment: `already_done` — status: verify wording - [ ] (R3-C4) Add runtime breakdown figure to Appendix B — commitment: `future_work_only` — status: deferred, note in camera-ready - ...Checklist items must be atomic (one paper edit per line) and each must reference its
issue_idso it maps back toISSUE_BOARD.md.- Grouped view — the same items regrouped by (a) paper section/location and (b) severity, so the author can plan the revision pass efficiently.
- Commitment summary — counts of
already_done/approved_for_rebuttal/future_work_only, plus anyneeds_user_inputitems that are blocking. - Out-of-scope log — reviewer concerns that will not trigger a paper revision (e.g.
deferred_intentionally,narrow_concessionwith no edit), with a one-line reason each. This keeps the checklist honest: nothing silently disappears.
Rules for REVISION_PLAN.md:
- Every checklist item must map to at least one
issue_idfromISSUE_BOARD.md. - Every promise in
REBUTTAL_DRAFT_v1.mdthat implies a paper edit must appear as a checklist item — if it is not in the plan, it is a commitment-gate violation. - Never add items that are not backed by the draft or by user-confirmed evidence.
- On rerun / follow-up rounds, update checkbox state in place rather than regenerating from scratch.
Phase 5: Safety Validation
Run all lints:
- Coverage — every issue maps to draft anchor
- Provenance — every factual sentence has source
- Commitment — promises are approved AND every paper-edit promise in the draft appears as a checklist item in
REVISION_PLAN.md(and vice versa — no orphan items in the plan) - Tone — flag aggressive/submissive/evasive phrases
- Consistency — no contradictions across reviewer replies
- Limit — exact character count, compress if over (redundancy → friendly → opener → wording, never drop critical answers)
Phase 6: Codex Reviewer Stress Test
spawn_agent:
reasoning_effort: xhigh
message: |
Stress-test this rebuttal draft:
[raw reviews + issue board + draft + venue rules]
1. Unanswered or weakly answered concerns?
2. Unsupported factual statements?
3. Risky or unapproved promises?
4. Tone problems?
5. Paragraph most likely to backfire with meta-reviewer?
6. Minimal grounded fixes only. Do NOT invent evidence.
Verdict: safe to submit / needs revisionSave full response to rebuttal/MCP_STRESS_TEST.md. If hard safety blocker → revise before finalizing.
Phase 7: Finalize — Two Versions
Produce two outputs for different purposes:
rebuttal/PASTE_READY.txt— the strict version- Plain text, exact character count, fits venue limit
- Ready to paste directly into OpenReview / CMT / HotCRP
- No markdown formatting, no extras
rebuttal/REBUTTAL_DRAFT_rich.md— the extended version- Same structure but with more detail: fuller explanations, additional evidence, optional paragraphs
- Marked with
[OPTIONAL — cut if over limit]for sections that exceed the strict version - Author can read this to understand the full reasoning, then manually decide what to keep/cut/rewrite
- Useful for follow-up rounds — the extra material is pre-written
- Update
rebuttal/REBUTTAL_STATE.md - Refresh
rebuttal/REVISION_PLAN.mdso the overall checklist matches the final draft (add items, markalready_doneas checked, carry forward anypendingitems) - Present to user:
PASTE_READY.txtcharacter count vs venue limitREBUTTAL_DRAFT_rich.mdfor review and manual editingREVISION_PLAN.mdchecklist — counts of pending / approved / deferred- Remaining risks + lines needing manual approval
Phase 8: Follow-Up Rounds
When new reviewer comments arrive:
- Append verbatim to
rebuttal/FOLLOWUP_LOG.md - Link to existing issues or create new ones
- Draft delta reply only (not full rewrite)
- Update
rebuttal/REVISION_PLAN.mdin place — add any new checklist items introduced by the follow-up, tick off items the author has already completed, and keep existing items' status current - Re-run safety lints
- Use Codex MCP reply for continuity if useful
- Rules: escalate technically not rhetorically; concede if reviewer is correct; stop arguing if reviewer is immovable and no new evidence exists
Phase 9: Render HTML view (auto, when RENDER_HTML = true, default)
After Phase 6 (initial rebuttal) or Phase 8 (follow-up rounds) finalize rebuttal/REBUTTAL_DRAFT_rich.md, invoke:
/render-html "rebuttal/REBUTTAL_DRAFT_rich.md"Full review gate (reviewer-facing pre-submission deliverable). Do NOT render rebuttal/PASTE_READY.txt (it's exact-character-count plain text by design).
Non-blocking: if /render-html fails, log the failure and treat the rebuttal phase as complete — the PASTE_READY.txt and REBUTTAL_DRAFT_rich.md are the canonical outputs.
Skip if RENDER_HTML = false.
Key Rules
- Large file handling: If Write fails, retry with Bash heredoc silently.
- Never fabricate. No invented evidence, numbers, derivations, citations, or links.
- Never overpromise. Only promise what user explicitly approved.
- Full coverage. Every reviewer concern tracked and accounted for.
- Preserve raw records. Reviews and MCP outputs stored verbatim.
- Global + per-reviewer structure. Shared concerns in opener.
- Answer friendly reviewers too. Reinforce supportive framing.
- Meta-reviewer closing. Summarize resolved/remaining/why accept.
- Evidence > rhetoric. Derivations and numbers over prose.
- Concede selectively. Narrow honest concessions > broad denials.
- Don't waste space on unwinnable arguments. Answer once, move on.
- Respect the limit. Character budget is a hard constraint.
- Resume cleanly. Continue from REBUTTAL_STATE.md on rerun.
- Anti-hallucination citations. Any reference added must go through DBLP → CrossRef → [VERIFY].
Review Tracing
After each spawn_agent or send_input reviewer call, save the trace following ../shared-references/review-tracing.md. Write files directly to .debuffer_skills/traces/rebuttal/<date>_run<NN>/. Respect the --- trace: parameter when present (default: full).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

