Agent skill

Paper Claim Audit

by AI4Scientist in AI4Scientist/nano-scientist

Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files.

No licenceAuto-check: notes

Install Paper Claim Audit

skills CLI
$ npx skills add AI4Scientist/nano-scientist --skill paper-claim-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AI4Scientist/nano-scientist paper-claim-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AI4Scientist/nano-scientist.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/paper-claim-audit .claude/skills/paper-claim-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
paper-claim-audit
GitHub stars
128
Used in
1 other repo
Token cost
~3.1k tokens
SKILL.md length
755 words
Files
1
Skills in repo
74
Repo updated
First seen
Licence
None found

At a glance

Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files.

  • Works in 4 steps: Collect Files (Executor — Claude) → Fresh Reviewer Audit (GPT-5.4 — NEW… → Write Report (Executor — Claude) → …
  • User says 审查论文数据
  • SKILL.md covers Why This Exists, How This Differs From Other…, Core Principle and Workflow, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Paper Claim Audit is an agent skill from AI4Scientist/nano-scientist. Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: An autonomous research agent that turns a topic into a peer-reviewed technical report.

When your agent uses it

  • User says 审查论文数据
  • Check paper claims
  • Before submission to ensure paper-to-evidence fidelity

Example prompts

  • “审查论文数据”
  • “check paper claims”
  • “verify numbers”
  • “/paper-claim-audit”

Requirements

  • Pre-approved tools (allowed-tools): Bash(*), Read, Write, Edit, Grep, Glob, Agent, mcp__codex__codex

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Collect Files (Executor — Claude)
  2. Fresh Reviewer Audit (GPT-5.4 — NEW thread, no reply)
  3. Write Report (Executor — Claude)
  4. Print Summary

What it can do on your machine

Read from SKILL.md and the folder at commit 7132192. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(*)
    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • Agent
    • mcp__codex__codex

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Paper Claim Audit loads about 3.1k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 755 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Agent, mcp__codex__codex

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 755 words (~3,109 tokens).

“Verify that every claim in the paper matches raw evidence for: $ARGUMENTS”

— opening of SKILL.md by AI4Scientist
name
paper-claim-audit
allowed-tools
Bash(*), Read, Write, Edit, Grep, Glob, Agent, mcp__codex__codex
argument-hint
paper-directory

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/paper-claim-audit of AI4Scientist/nano-scientist.

Open the folder on GitHubat commit 7132192

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in AI4Scientist/nano-scientist, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Paper Claim Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Paper Claim Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Paper Claim Audit this skillAI4Scientist/nano-scientist1281 repos~3.1kAutomated safety check: NotesNone
Claimsruvnet/ruflo74k1 repos~1.1kAutomated safety check: PassMIT
Paper Claim Auditwanshuiyin/Auto-claude-code-research-in-sleep17k1 repos~3.5kAutomated safety check: NotesMIT
Zero Trustsickn33/agentic-awesome-skills47k2 repos~3.2kAutomated safety check: PassMIT
Gaia Architecture Comparisonruvnet/ruflo74k—~1.3kAutomated safety check: NotesMIT
Cloudflare Zero Trustsickn33/agentic-awesome-skills47k2 repos~2.8kAutomated safety check: WarnMIT

Similar skills

  • Claims

    ruvnet/ruflo

    Claims-based authorization for agents and operations. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 1 repo~1.1k tokens
    Backend & APIsAuto-check passed
  • Paper Claim Audit

    wanshuiyin/Auto-claude-code-research-in-sleep

    Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files.

    17k GitHub starsUsed in 1 repo~3.5k tokens
    Auto-check: notes
  • Zero Trust

    sickn33/agentic-awesome-skills

    Implement zero-trust network architecture. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~3.2k tokens
    Backend & APIsAuto-check passed
  • Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap

    74k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Cloudflare Zero Trust

    sickn33/agentic-awesome-skills

    Protect internal apps with Cloudflare Access, device posture, and Zero Trust policies.

    47k GitHub starsUsed in 2 repos~2.8k tokens
    DevOps & CloudAuto-check: warnings
  • Resolve subclonal copy number, whole-genome doubling, and copy-number tumor evolution from bulk sequencing with Battenberg, TITAN, and MEDICC2.

    1.2k GitHub starsUsed in 2 repos~3.5k tokens
    Research & ScienceAuto-check passed

More from AI4Scientist/nano-scientist

All 74 skills in this repo
  • Formula Derivation

    AI4Scientist/nano-scientist

    Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a…

    128 GitHub starsUsed in 5 repos~2.3k tokens
    Auto-check passed
  • Paper Compile

    AI4Scientist/nano-scientist

    Compile LaTeX paper to PDF, fix errors, and verify output. An agent skill from AI4Scientist/nano-scientist.

    128 GitHub starsUsed in 5 repos~2.5k tokens
    Auto-check: notes
  • Paper Figure

    AI4Scientist/nano-scientist

    Generate publication-quality figures and tables from experiment results.

    128 GitHub starsUsed in 5 repos~2.9k tokens
    Auto-check: notes
  • Paper Navigator

    AI4Scientist/nano-scientist

    Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA)…

    128 GitHub stars~7.7k tokensUpdated 4 mo ago
    Auto-check: notes
  • Proof Writer

    AI4Scientist/nano-scientist

    Writes rigorous mathematical proofs for ML/AI theory. An agent skill from AI4Scientist/nano-scientist.

    128 GitHub starsUsed in 5 repos~1.9k tokens
    Auto-check passed
  • Ablation Planner

    AI4Scientist/nano-scientist

    A skill your agent uses when main results pass result-to-claim (claimsupported=yes or partial) and ablation studies are needed for paper submission.

    128 GitHub starsUsed in 4 repos~1.3k tokens
    Auto-check: notes

Questions about Paper Claim Audit

What does Paper Claim Audit do?

Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Paper Claim Audit is an agent skill from AI4Scientist/nano-scientist. Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files.

When should I use Paper Claim Audit?

Paper Claim Audit fits situations like: user says 审查论文数据; check paper claims; before submission to ensure paper-to-evidence fidelity.

How do I install Paper Claim Audit in Claude Code?

Run `npx skills add AI4Scientist/nano-scientist --skill paper-claim-audit -a claude-code`. Or copy the skill folder (skills/paper-claim-audit in AI4Scientist/nano-scientist) into .claude/skills/paper-claim-audit in your project. Claude Code loads it when a task matches its description.

How do I install Paper Claim Audit in Codex?

Run `npx skills add AI4Scientist/nano-scientist --skill paper-claim-audit -a codex`. Or copy the skill folder (skills/paper-claim-audit in AI4Scientist/nano-scientist) into .agents/skills/paper-claim-audit in your project. Codex loads it when a task matches its description.

Can I use Paper Claim Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AI4Scientist/nano-scientist --skill paper-claim-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paper-claim-audit, .gemini/skills/paper-claim-audit, .github/skills/paper-claim-audit and .opencode/skills/paper-claim-audit in your project.

What does Paper Claim Audit need to run?

SKILL.md names no scripts, command-line tools or credentials: Paper Claim Audit is instructions for the agent only. Its frontmatter pre-approves these tools: Bash(*), Read, Write, Edit, Grep, Glob, Agent, mcp__codex__codex.

Does Paper Claim Audit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Paper Claim Audit safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Paper Claim Audit use?

No licence was found for Paper Claim Audit or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Paper Claim Audit use?

About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Paper Claim Audit?

Skills that share tags, products or a category with Paper Claim Audit: Claims (ruvnet/ruflo, 74k stars), Paper Claim Audit (wanshuiyin/Auto-claude-code-research-in-sleep, 17k stars), Zero Trust (sickn33/agentic-awesome-skills, 47k stars) and Gaia Architecture Comparison (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper Claim Audit?

AI4Scientist (a GitHub organization) maintains it in AI4Scientist/nano-scientist, which has 128 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on June 3, 2026.

Source: AI4Scientist/nano-scientist on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.