Agent skill

Referee2

by scunning1975 in scunning1975/MixtapeTools

Systematic audit and review by Referee 2. An agent skill from scunning1975/MixtapeTools.

No licenceAuto-check passedResearch & Science

Install Referee2

skills CLI
$ npx skills add scunning1975/MixtapeTools --skill referee2 -a claude-code

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

GitHub CLI
$ gh skill install scunning1975/MixtapeTools referee2 --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/scunning1975/MixtapeTools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/referee2 .claude/skills/referee2 && 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
referee2
GitHub stars
470
Used in
2 other repos
Token cost
~2.4k tokens
SKILL.md length
1,149 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

Systematic audit and review by Referee 2. An agent skill from scunning1975/MixtapeTools.

  • Works in 2 steps: Produce output → run /blindspot →… → Complete the project → open fresh…
  • Reviewing slides
  • SKILL.md covers Referee 2 and Blindspot:…, Step 0: Read Your Full Persona…, Mode 1: Deck Review and Mode 2: Code Audit, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Referee2 is an agent skill from scunning1975/MixtapeTools. Systematic audit and review by Referee 2. Two modes — "deck" reviews slide presentations for rhetoric, visual quality, and compile cleanliness; "code" performs cross-language replication and econometric audit of empirical pipelines. Use when reviewing slides, auditing code, or verifying replication.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Slides and decks, Database administration and Econometrics and empirical research. The repository describes itself as: Tools for coding, teaching, and presentations with AI assistance.

When your agent uses it

  • Reviewing slides
  • Verifying replication

Example prompts

  • “/referee2”

Requirements

  • Pre-approved tools (allowed-tools): Bash(pdflatex*), Bash(latexmk*), Bash(python*), Bash(Rscript*), Bash(stata*), Bash(ls*), Bash(wc*), Bash(grep*), Bash(head*), Bash(tail*), Read, Write, Edit, Glob, Grep, Agent

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Produce output → run /blindspot → interpret and write
  2. Complete the project → open fresh terminal → run /referee2

What it can do on your machine

Read from SKILL.md and the folder at commit 9163a2e. 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(pdflatex*)
    • Bash(latexmk*)
    • Bash(python*)
    • Bash(Rscript*)
    • Bash(stata*)
    • Bash(ls*)
    • Bash(wc*)
    • Bash(grep*)
    • Bash(head*)
    • Bash(tail*)

    …and 6 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    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

Referee2 loads about 2.4k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 1,149 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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 passed

The automated check found no risky patterns in SKILL.md.

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 1,149 words (~2,373 tokens).

“You are Referee 2 — a health inspector for academic work. You have a checklist, you perform specific tests, you file a formal report.”

— opening of SKILL.md by scunning1975
name
referee2
allowed-tools
Bash(pdflatex*), Bash(latexmk*), Bash(python*), Bash(Rscript*), Bash(stata*), Bash(ls*), Bash(wc*), Bash(grep*), Bash(head*), Bash(tail*), Read, Write, Edit, Glob, Grep, Agent
argument-hint
[mode: deck|code] [path-to-project-or-file]

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/referee2 of scunning1975/MixtapeTools.

Open the folder on GitHubat commit 9163a2e

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in scunning1975/MixtapeTools, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Referee2 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.

Referee2 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Referee2 this skillscunning1975/MixtapeTools4702 repos~2.4kAutomated safety check: PassNone
Aer Replicationbrycewang-stanford/Auto-Empirical-Research-Skills4.5k1 repos~2.8kAutomated safety check: PassCustom licence
Academic Paper Verifybrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~2.9kAutomated safety check: PassCustom licence
Audit Replicationbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~984Automated safety check: NotesCustom licence
Data Depositbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~1.2kAutomated safety check: NotesCustom licence
Slide Excellencebrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~750Automated safety check: PassCustom licence

Similar skills

  • Aer Replication

    brycewang-stanford/Auto-Empirical-Research-Skills

    A skill your agent uses when assembling the AEA Data and Code Availability deposit for an AER, AER:Insights, or AEJ acceptance, writing the README, or auditing a replication package before the AEA…

    4.5k GitHub starsUsed in 1 repo~2.8k tokens
    Research & ScienceAuto-check passed
  • Academic Paper Verify

    brycewang-stanford/Auto-Empirical-Research-Skills

    Thoroughly verify all code, tables, figures, modeling decisions, and quantitative claims in an academic paper against its source R scripts and output files.

    4.5k GitHub stars~2.9k tokensUpdated 3 days ago
    Research & ScienceAuto-check passed
  • Audit Replication

    brycewang-stanford/Auto-Empirical-Research-Skills

    Validate the replication package for the sewage-house-prices project.

    4.5k GitHub stars~984 tokensUpdated 3 days ago
    Research & ScienceAuto-check: notes
  • Data Deposit

    brycewang-stanford/Auto-Empirical-Research-Skills

    Prepare a replication package for the sewage-house-prices project.

    4.5k GitHub stars~1.2k tokensUpdated 3 days ago
    Research & ScienceAuto-check: notes
  • Slide Excellence

    brycewang-stanford/Auto-Empirical-Research-Skills

    Multi-agent review for research presentation slides in the sewage-house-prices project (visual, econometric fidelity, proofreading, substance).

    4.5k GitHub stars~750 tokensUpdated 3 days ago
    Research & ScienceAuto-check passed
  • Ectheory Replication And Data Policy

    franklee16/academic-research-skills

    A skill your agent uses to handle reproducibility and the supplementary-material file for an Econometric Theory (ET) paper — ET has no mandatory data/code archive (theory journal); the relevant…

    223 GitHub starsUsed in 1 repo~983 tokens
    Research & ScienceAuto-check passed

More from scunning1975/MixtapeTools

All 9 skills in this repo
  • Compiledeck

    scunning1975/MixtapeTools

    Create and compile beautiful Beamer presentations following the Rhetoric of Decks philosophy.

    470 GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed
  • Split PDF

    scunning1975/MixtapeTools

    Download, split, and deeply read academic PDFs. An agent skill from scunning1975/MixtapeTools.

    470 GitHub starsUsed in 2 repos~2.9k tokens
    Auto-check passed
  • Newproject

    scunning1975/MixtapeTools

    Scaffold a new research project with standard directory structure, CLAUDE.md template, and documented README.

    470 GitHub starsUsed in 1 repo~850 tokens
    Auto-check passed
  • Bibcheck

    scunning1975/MixtapeTools

    Many-agent bibliography audit. An agent skill from scunning1975/MixtapeTools.

    470 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Blindspot

    scunning1975/MixtapeTools

    Peripheral vision audit for empirical output. An agent skill from scunning1975/MixtapeTools.

    470 GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Gtd

    scunning1975/MixtapeTools

    Warrant-first research GTD system. An agent skill from scunning1975/MixtapeTools.

    470 GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check: notes

Questions about Referee2

What does Referee2 do?

Systematic audit and review by Referee 2. An agent skill from scunning1975/MixtapeTools. Referee2 is an agent skill from scunning1975/MixtapeTools. Systematic audit and review by Referee 2.

When should I use Referee2?

Referee2 fits situations like: reviewing slides; verifying replication.

How do I install Referee2 in Claude Code?

Run `npx skills add scunning1975/MixtapeTools --skill referee2 -a claude-code`. Or copy the skill folder (.claude/skills/referee2 in scunning1975/MixtapeTools) into .claude/skills/referee2 in your project. Claude Code loads it when a task matches its description.

How do I install Referee2 in Codex?

Run `npx skills add scunning1975/MixtapeTools --skill referee2 -a codex`. Or copy the skill folder (.claude/skills/referee2 in scunning1975/MixtapeTools) into .agents/skills/referee2 in your project. Codex loads it when a task matches its description.

Can I use Referee2 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 scunning1975/MixtapeTools --skill referee2 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/referee2, .gemini/skills/referee2, .github/skills/referee2 and .opencode/skills/referee2 in your project.

What does Referee2 need to run?

SKILL.md names no scripts, command-line tools or credentials: Referee2 is instructions for the agent only. Its frontmatter pre-approves these tools: Bash(pdflatex*), Bash(latexmk*), Bash(python*), Bash(Rscript*), Bash(stata*), Bash(ls*), Bash(wc*), Bash(grep*), Bash(head*), Bash(tail*), Read, Write, Edit, Glob, Grep, Agent.

Does Referee2 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 Referee2 safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Referee2 use?

No licence was found for Referee2 or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Referee2 use?

About 2.4k tokens (SKILL.md is roughly 9.5k 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 Referee2?

Skills that share tags, products or a category with Referee2: Aer Replication (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Academic Paper Verify (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Audit Replication (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars) and Data Deposit (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Referee2?

scunning1975 (a GitHub user) maintains it in scunning1975/MixtapeTools, which has 470 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 26, 2026.

Source: scunning1975/MixtapeTools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.