Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Stage 2 · ARR Refine Skill (Template Extension) · runtsang | DecimalAI

researchby runtsang

Stage 2 · ARR Refine Skill (Template Extension)

runtsang/stage2-arr-refine

Source runtsang/rebuttalstudio ↗License Not recorded

Refine a Stage2 ARR (ACL Rolling Review) rebuttal draft into polished, reviewer-facing prose in the author's style; preserve factual grounding, optionally prepend a courteous opening phrase, and normalize tables/code/formulas into Markdown.

SkillScore64Maintained

Automatic

Writing & Editing pack

Last verified 8/27/2026

What it changes

Passed 14 of 22 test cases with the skill, and 5 of 22 without it.

Without skill23%

With skill64%

Checks it passed that the model alone missed

The response is formatted strictly as JSON.
The output contains no conversational text.
The output is provided strictly in JSON format.

and 8 more in the full report

11 fixed3 passed either way6 still failing2 broke

Pass-rate lift: +41 pp
Tokens: +19%
Agent turns: 0%
Response time: +9%

Model gemini-3.6-flashMeasured 8/27/2026v114 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/runtsang-stage2-arr-refine/SKILL.md https://app.decimal.ai/s/runtsang-stage2-arr-refine/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add runtsang-stage2-arr-refine, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/runtsang-stage2-arr-refine/ and pins it in .decimal/skills.lock

decimalai skills add runtsang-stage2-arr-refine

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/runtsang-stage2-arr-refine/SKILL.md https://app.decimal.ai/s/runtsang-stage2-arr-refine/SKILL.md

Raw file: /s/runtsang-stage2-arr-refine/SKILL.md ↗ · machine-readable summary at /s/runtsang-stage2-arr-refine.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

Format these rebuttal notes for Reviewer 2 into JSON format for ARR: 'We conducted human evaluation with 3 annotators on 100 samples; inter-annotator agreement was Fleiss Kappa = 0.72.'

What was checked, without and with the skill
Checked	Without skill	With skill
The JSON text includes the Fleiss Kappa score of 0.72.	Passed	Passed
The output is provided strictly in JSON format.	Missed	Passed

case-15 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md18 linessingle file

Stage 2 · ARR Refine Skill (Template Extension)

Apply the shared template first:

skills/stage2/template/SKILL.md

Then apply only the ARR-specific overrides below.

ARR overrides

Preserve the same strict JSON schema and output format from the template.
Keep ARR naming in labels and internal references when conference name is explicitly mentioned.
Keep style target concise, precise, and submission-ready for an ACL/EMNLP rebuttal.
ARR rebuttals are typically 500–1000 words total; keep individual responses focused.

ARR note

No additional structural override is required beyond conference labeling. All writing constraints, opener rules, normalization rules, and hard constraints are inherited from the base template.

Track record

Benchmark

14 / 22

test cases passed, vs 5 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

runtsang / rebuttalstudio

skills/stage2/arr/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Stage 2 · ARR Refine Skill (Template Extension)

ARR overrides

ARR note

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills