Ready to supercharge your AI agents?

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

Get Started Free →

Stage 1 · ICLR Breakdown Skill (Template Extension) · runtsang | DecimalAI

researchby runtsang

Stage 1 · ICLR Breakdown Skill (Template Extension)

runtsang/stage1-iclr-breakdown

Source runtsang/rebuttalstudio ↗License Not recorded

Break down full ICLR reviewer responses into structured rebuttal units.

SkillScore57Maintained

Automatic

Research pack

Last verified 8/28/2026

What it changes

Passed 13 of 23 test cases with the skill, and 8 of 23 without it.

Without skill35%

With skill57%

Checks it passed that the model alone missed

The score section header is '## Scores'.
The score header is exactly '## Scores'.
The score section heading is '## Scores'.

and 8 more in the full report

7 fixed6 passed either way8 still failing2 broke

Pass-rate lift: +22 pp
Tokens: +77%
Agent turns: 0%
Response time: +48%

Model gemini-3.6-flashMeasured 8/28/2026v113 of 23 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-stage1-iclr-breakdown/SKILL.md https://app.decimal.ai/s/runtsang-stage1-iclr-breakdown/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add runtsang-stage1-iclr-breakdown, 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-stage1-iclr-breakdown/ and pins it in .decimal/skills.lock

decimalai skills add runtsang-stage1-iclr-breakdown

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

curl -fsSL --create-dirs -o .claude/skills/runtsang-stage1-iclr-breakdown/SKILL.md https://app.decimal.ai/s/runtsang-stage1-iclr-breakdown/SKILL.md

Raw file: /s/runtsang-stage1-iclr-breakdown/SKILL.md ↗ · machine-readable summary at /s/runtsang-stage1-iclr-breakdown.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Standardize the evaluation scores from an ICLR submission: Overall Rating: 6 out of 10, Confidence: 3, Soundness: 3, Presentation: 3, Contribution: 3. Extract the overall rating as 'overall_score: 6'.

What was checked, without and with the skill
Checked	Without skill	With skill
The score block uses the key name 'rating' for the overall score.	Missed	Passed

case-16 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md38 linessingle file

Stage 1 · ICLR Breakdown Skill (Template Extension)

Apply the shared template first:

skills/stage1/template/SKILL.md

Then apply only the ICLR-specific overrides below.

ICLR overrides

Score mapping (required keys)

Extract exactly these five keys (numbers only):

rating <- ICLR rating
confidence <- ICLR confidence
soundness <- ICLR soundness
presentation <- ICLR presentation
contribution <- ICLR contribution

Preserved section mapping

summary <- summary
strength <- strength

Atomic issue source mapping

weakness-type source <- weakness
question-type source <- question

Output header and score block

Header must be exactly: # Stage1 ICLR Breakdown
## Scores must contain exactly the five keys above.

ICLR note

If reviewer text mixes free-form paragraphs and bullets, keep template splitting rules unchanged and split only by independent concerns.

Track record

Benchmark

13 / 23

test cases passed, vs 8 / 23 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/stage1/iclr/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 1 · ICLR Breakdown Skill (Template Extension)

ICLR overrides

Score mapping (required keys)

Preserved section mapping

Atomic issue source mapping

Output header and score block

ICLR note

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills