Ready to supercharge your AI agents?

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

Get Started Free →

Paper Audit Skill v4.2 · brycewang-stanford | DecimalAI

researchby brycewang-stanford

Paper Audit Skill v4.2

brycewang-stanford/paper-audit

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

Deep-review-first audit for Chinese and English academic papers across LaTeX, Typst, and PDF formats.

SkillScore57Maintained

Automatic

Research pack

Last verified 8/8/2026

What it changes

Passed 12 of 21 test cases with the skill, and 11 of 21 without it.

Without skill52%

With skill57%

Checks it passed that the model alone missed

States that severe policy violations mandate a failing summary score.
Executes initial editorial screening first to catch fatal desk-reject issues before deep review.
Explains that a Desk Reject determination caps the overall consensus score regardless of minor strengths.

and 1 more in the full report

2 fixed11 passed either way9 still failing1 broke

Pass-rate lift: +4 pp
Tokens: +158%
Agent turns: 0%
Response time: -27%

Model gemini-3.6-flashMeasured 8/8/2026v113 of 23 cases passed with skill · 21 comparable

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/brycewang-stanford-paper-audit/SKILL.md https://app.decimal.ai/s/brycewang-stanford-paper-audit/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-paper-audit, 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/brycewang-stanford-paper-audit/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-paper-audit

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

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-paper-audit/SKILL.md https://app.decimal.ai/s/brycewang-stanford-paper-audit/SKILL.md

Raw file: /s/brycewang-stanford-paper-audit/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-paper-audit.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

If an Editor-in-Chief flags a paper for Desk Reject due to anonymization violation or scope mismatch, can high scores in methodology or writing raise the overall consensus score above a failing threshold?

What was checked, without and with the skill
Checked	Without skill	With skill
Explains that a Desk Reject determination caps the overall consensus score regardless of minor strengths.	Missed	Passed
States that severe policy violations mandate a failing summary score.	Missed	Passed

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

What's inside

The instructions your model reads when the skill loads.

SKILL.md373 lines43 filesincludes scripts

Paper Audit Skill v4.2

paper-audit is now deep-review-first. Its core job is to behave like a serious reviewer: find technical, methodological, claim-level, and cross-section issues; keep script-backed findings separate from reviewer judgment; and return a structured issue bundle plus a revision roadmap.

Use it for audit and review. Do not use it as the first tool for source editing, sentence rewriting, or build fixing.

What This Skill Produces

quick-audit: fast submission-readiness screen with script-backed findings
deep-review: reviewer-style structured issue bundle with major/moderate/minor findings
gate: PASS/FAIL decision calibrated for submission blockers
re-audit: compare current issue bundle against a previous audit
polish: precheck-only handoff into a polishing workflow

The primary product is no longer just a score. For deep-review, the main outputs are:

final_issues.json
overall_assessment.txt
review_report.md
revision_roadmap.md

Do Not Use

direct source surgery on .tex / .typ
compilation debugging as the main task
free-form literature survey writing
cosmetic grammar cleanup without an audit goal

Critical Rules

Never rewrite the paper source unless the user explicitly switches to an editing skill.
Never fabricate references, baselines, or reviewer evidence.
Always distinguish [Script] from [LLM] findings.
Always anchor reviewer findings to a quote, section, or exact textual location.
Be conservative with OCR noise, formatting quirks, and obvious copy-editing trivia.
Review like a careful reader: understand the author's intended meaning before flagging an issue.

Mode Selection

| Requested intent | Mode |

Track record

Benchmark

12 / 21

test cases passed, vs 11 / 21 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 — 8/2/2026

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

brycewang-stanford / Auto-Empirical-Research-Skills

skills/35-bahayonghang-academic-writing-skills/skills/paper-audit/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1Bundled 42 files · scripts

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

Paper Audit Skill v4.2

What This Skill Produces

Do Not Use

Critical Rules

Mode Selection

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills