Skip to content
Agentmart
Submit a tool

autorebuttal

Automatically plan, draft, and compliance-check a complete evidence-grounded rebuttal from a confirmed baseline.

Skill by Optima-CityU

IndexedBSD-3-Clause★ 677
Write a review

Chalk Labs

Need help deploying autorebuttal?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/optima-cityu-autorebuttal

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Automatically plan, draft, and compliance-check a complete evidence-grounded rebuttal from a confirmed baseline.

Use cases: security, writing-editing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/autorebuttal

What's inside

Skill name
autorebuttal
Description
Automatically plan, draft, and compliance-check a complete evidence-grounded rebuttal from a confirmed baseline.
License
BSD-3-Clause
Instructions
55 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

<!-- Adapted from YoujunZhao/AutoRebuttal; see /app/skills/autorebuttal-shared/ATTRIBUTION.md. -->

# AutoRebuttal

Read these shared references completely before acting:

- `/app/skills/autorebuttal-shared/references/input-contract.md`
- `/app/skills/autorebuttal-shared/references/strategy-and-format.md`
- `/app/skills/autorebuttal-shared/references/drafting-and-compliance.md`
- `/app/skills/autorebuttal-shared/references/rebuttal-playbook.md`
- `/app/skills/autorebuttal-shared/references/reviewer-model.md`
- `/app/skills/autorebuttal-shared/references/initial-rebuttal-style.md`
- `/app/skills/autorebuttal-shared/references/human-rebuttal-style.md`
- `/app/skills/autorebuttal-shared/references/venue-policies.md`
- `/app/skills/autorebuttal-shared/references/evidence-policy.md`
- `/app/skills/autorebuttal-shared/references/artifact-contracts.md`

If the baseline lacks details needed for a reply, read the saved review files
or ask the author to paste the relevant original passage into the conversation.
Do not treat an OpenReview link alone as evidence of the review's contents.

Read the confirmed intake and analysis from the rebuttal context before doing
any generation. This author-facing phase contains three internal steps that
must run in order without asking the author to type “continue.”

## Step 1: Response strategy

Resolve shared issues, priority reviewers, response moves, output structure,
and a reviewer-complete strategy. Decide whether shared concerns belong in one
global response or in reviewer-specific blocks. Keep the stable reviewer UUIDs
from the confirmed baseline; display labels are presentation only.

## Step 2: Drafting

Write concise responses covering every analyzed concern exactly once across
the global response and reviewer-specific entries. Ground factual claims in
the paper or explicit author evidence and attach auditable source references.
Use visible `[AUTHOR: ...]` placeholders when only the author can provide a
result or decision.

## Step 3: Compliance review

Audit and refine the full draft for concern coverage, reviewer identity,
global/shared consistency, evidence integrity, and submission readiness. Fix
non-blocking writing problems directly. Assemble the exact final submission in
`rendered_text`; it must agree with the final global response and entries. Keep
unresolved evidence visible and set `ready_for_submission` false when author
action remains. Publish concise author-facing guidance for those unresolved
items: identify what is missing, why it matters, and a practical next step.
Do not expose the internal compliance checklist as user guidance.

Publish the complete AutoRebuttal phase contract exactly once with
`publish_stage_result` and idempotency key `autorebuttal-v1`.

From Optima-CityU/LLM4AD_Next, BSD-3-Clause.

More from Optima-CityU/LLM4AD_Next

Compare and alternatives

    Featured in

    Signals

    Stars
    677
    Forks
    44
    Open issues
    1
    Last commit (this folder)
    Sep 24, 2026 (1 month ago)
    Last release
    Sep 29, 2026 (1 month ago)

    From GitHub (fetched Oct 24, 2026).

    Details

    License
    BSD-3-Clause
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026

    More from Optima-CityU

    Done for you

    Rather not set it up yourself?

    Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

    See how we build AI agents →Read the case studies

    Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

    launches shipped
    50+
    launches shipped
    media placements
    500+
    media placements
    founders on every account
    2
    founders on every account

    Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

    Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

    Get autorebuttal running in your business

    Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

    Goes to the Chalk Labs founders, not the newsletter. Privacy

    Need help deploying autorebuttal?

    CallGet help
    Cite this page

    autorebuttal skill. Agent Mart. https://agentmart.dev/skills/optima-cityu-autorebuttal (last updated 2026-10-24)