research by brycewang-stanford
Workflow 4: Rebuttal brycewang-stanford/rebuttal
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.
What it changes View full report → Passed 19 of 23 test cases with the skill, and 8 of 23 without it.
Without skill 35%
With skill 83%
Checks it passed that the model alone missed and 16 more in the full report
13 fixed6 passed either way2 still failing2 broke
Pass-rate lift +48 pp
Tokens +51%
Agent turns 0%
Response time -39% Model gemini-3.6-flashMeasured 8/11/2026 v2 19 of 23 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-rebuttal/SKILL.md https://app.decimal.ai/s/brycewang-stanford-rebuttal/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-rebuttal, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/brycewang-stanford-rebuttal/ and pins it in .decimal/skills.lock
$ decimalai skills add brycewang-stanford-rebuttalCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-rebuttal/SKILL.md https://app.decimal.ai/s/brycewang-stanford-rebuttal/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 2 Ratings 0
See it in action One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt When initializing the rebuttal workflow without explicit configuration overrides, what are the default venue and response mode values?
What was checked, without and with the skill Checked Without skill With skill Identifies ICML as default venue. Identifies TEXT_ONLY as default response mode.
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 189 lines single file
Workflow 4: Rebuttal
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 rebuttalsafe drafting with no fabrication , no overpromise , and full issue coverage
This skill does not :
run new experiments automatically unless AUTO_EXPERIMENT = true
generate new theorem claims automatically
edit or upload a revised PDF
submit to OpenReview / CMT / HotCRP
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 venueRESPONSE_MODE = TEXT_ONLY — v1 defaultREVIEWER_MODEL = gpt-5.4 — Used via a secondary Codex agent for internal stress-testingMAX_INTERNAL_DRAFT_ROUNDS = 2 MAX_STRESS_TEST_ROUNDS = 1 MAX_FOLLOWUP_ROUNDS = 3 AUTO_EXPERIMENT = false — When true, invoke /experiment-bridge for reviewer concerns that require new evidence When it activates Automatically, when a task matches.
Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.
Track record Benchmark 19 / 23
test cases passed, vs 8 / 23 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/9/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported brycewang-stanford / Auto-Empirical-Research-Skills
skills/42-wanshuiyin-ARIS/skills/rebuttal/SKILL.md
View on GitHub ↗ License NOASSERTIONImported 8/9/2026Version v2