New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Paper Reviewer

by Ingar30 in Ingar30/reviewer

A skill your agent uses when the task is to review an academic paper PDF from the repo input folder, run specialized auditors, and compile a final report.

MITAuto-check passedDocuments & Office

Install Paper Reviewer

skills CLI
$ npx skills add Ingar30/reviewer --skill paper-reviewer -a claude-code

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

GitHub CLI
$ gh skill install Ingar30/reviewer paper-reviewer --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/Ingar30/reviewer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/paper-reviewer .claude/skills/paper-reviewer && 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-reviewer
GitHub stars
222
Token cost
~2k tokens
SKILL.md length
1,000 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the task is to review an academic paper PDF from the repo input folder, run specialized auditors, and compile a final report.

  • Works in 12 steps: Resolve the input PDF path. → Derive paper_id from the filename stem… → Preprocess the PDF into work//parsed/. → …
  • The task is to review an academic paper PDF from the repo input folder
  • SKILL.md covers Use this skill when, Do not use this skill when, Default input convention and Workflow, plus 3 more sections
  • Calls codex

What it does

Paper Reviewer is an agent skill from Ingar30/reviewer. Use this skill when the task is to review an academic paper PDF from the repo input folder, run specialized auditors, and compile a final report.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Documents & Office, covering PDF. The licence is MIT.

When your agent uses it

  • The task is to review an academic paper PDF from the repo input folder
  • Run specialized auditors
  • Compile a final report

Example prompts

  • “/paper-reviewer”

Workflow steps

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

  1. Resolve the input PDF path.
  2. Derive paper_id from the filename stem unless explicitly provided.
  3. Preprocess the PDF into work//parsed/.
  4. Render run-specific prompts into work//prompts/.
  5. Launch preflight reviewers from config/reviewers.json.
  6. Validate preflight JSON and stop on blocking parser-quality failures.
  7. Route substantive reviewers around parser-quality warnings using the deterministic artifacts and parser-quality JSON.
  8. Run the conservative applicability router and record its complete decision in work//selection/reviewer_selection.json. Mixed, unknown, or…
  9. Write the active run roster and selection provenance to work//selection/selected_reviewers.json.
  10. Rerender prompts using the selected reviewer roster and parser-quality guidance.
  11. Launch the 8 universal review-stage reviewers and every applicable conditional specialist. The full roster contains 19 substantive…
  12. Validate each reviewer JSON output under work//reviews/.

What it can do on your machine

Read from SKILL.md and the folder at commit c591f4a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • codex

    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 Reviewer loads about 2k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 1,000 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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

The full file from Ingar30/reviewer at commit c591f4a, republished under its MIT licence (© Ingar30). 1,000 words, ~1,987 tokens.

Download SKILL.mdSave it as .claude/skills/paper-reviewer/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
paper-reviewer
description
Use this skill when the task is to review an academic paper PDF from the repo input folder, run specialized auditors, and compile a final report.

Paper Reviewer Skill

This skill runs a reproducible multi-agent paper-review workflow for academic PDFs.

Use this skill when

  • the input is an academic paper PDF
  • the task is review, auditing, or verification
  • the user wants a structured report
  • the task involves literature claims, references, numeric checks, or internal cross-references

Do not use this skill when

  • the user wants only a summary
  • the user wants only proofreading
  • the user wants only a rewrite
  • parsed artifacts already exist and the request is unrelated to the review pipeline

Default input convention

  • If the user names a bare PDF filename, first look for it under inputs/.
  • If the user gives a repo-relative path, use it.
  • If the user gives an absolute path, use it as provided.

Workflow

For fresh runs, use scripts/review_paper.py as the primary entry point.

The pipeline stages are:

  1. Resolve the input PDF path.
  2. Derive paper_id from the filename stem unless explicitly provided.
  3. Preprocess the PDF into work/<paper_id>/parsed/.
  4. Render run-specific prompts into work/<paper_id>/prompts/.
  5. Launch preflight reviewers from config/reviewers.json.
  6. Validate preflight JSON and stop on blocking parser-quality failures.
  7. Route substantive reviewers around parser-quality warnings using the deterministic artifacts and parser-quality JSON.
  8. Run the conservative applicability router and record its complete decision in work/<paper_id>/selection/reviewer_selection.json. Mixed, unknown, or lower-confidence classifications automatically expand to every conditional specialist.
  9. Write the active run roster and selection provenance to work/<paper_id>/selection/selected_reviewers.json.
  10. Rerender prompts using the selected reviewer roster and parser-quality guidance.
  11. Launch the 8 universal review-stage reviewers and every applicable conditional specialist. The full roster contains 19 substantive reviewers.
  12. Validate each reviewer JSON output under work/<paper_id>/reviews/.
  13. Conservatively normalize reviewer outputs into a precision-first, lossless work/<paper_id>/editor/normalized_bundle.json. Preserve every source finding's details and do not merge findings merely because they share a quote or path.
  14. Build work/<paper_id>/editor/editor_input.md from the deterministic editor brief, the lossless bundle, and a compact provenance index. Validate the source reviewer JSON files, but do not duplicate them in the editor input or truncate evidence.
  15. Run the editor to write outputs/<paper_id>/report.md.
  16. Smoke-check the final report with scripts/check_final_report.py --bundle work/<paper_id>/editor/normalized_bundle.json.

The supported quality defaults are gpt-6-sol, xhigh reasoning for substantive reviewers and the editor, and high for parser-quality preflight and applicability routing. GPT-6 Luna (gpt-6-luna) is an optional lower-cost override using the same workflow. Selected reviewer tests and one complete pipeline comparison found uneven Luna coverage; Sol remains the default. The full comparison required manual Luna recovery after a sleep-related timeout, and structural report checks did not establish semantic completeness. It is not a general accuracy or unattended-recovery benchmark. There is one public workflow rather than separate static and dynamic modes.

Editor-only refresh

If parsed artifacts, all selected reviewer JSON files, and work/<paper_id>/selection/selected_reviewers.json already exist, use scripts/refresh_editor.py --paper-id <paper_id> to resume synthesis without rerunning reviewers. The helper:

  1. Validates every selected reviewer JSON against the schema, semantic rules, and provenance constraints.
  2. Rebuilds the precision-first lossless work/<paper_id>/editor/normalized_bundle.json from the validated reviews.
  3. Rerenders prompts and rebuilds the deterministic brief, lossless bundle, and provenance-only editor input using the active reviewer config.
  4. With --run-editor, reruns the editor and smoke-checks the final report.

Do not use editor-only refresh when reviewer evidence, parser artifacts, or reviewer selection needs to change. Correct or rerun invalid reviewer output first; the helper will refuse to synthesize it.

Use editor-only refresh to test narrowly scoped editor prompt changes against the same evidence bundle before changing the full workflow. This is especially useful for checking whether report emphasis improved without changing reviewer evidence, such as when adjusting how parser/preprocessing caveats are surfaced in prose.

Show full SKILL.md (408 more words)Show less

Critical rules

  • Internal reviewers return JSON only.
  • The editor is the only component that emits final markdown.
  • Literature and reference verification require web search when enabled.
  • Never guess missing evidence; use cannot_verify.
  • Preserve exact source locations whenever possible.
  • If parsed artifacts are poor, fix preprocessing before trusting reviewer outputs.
  • Treat parser-quality preflight warnings as reportable caveats; treat high-confidence blocking parser findings as a reason to stop before substantive review.
  • Never generate or infer repaired parser content. Do not invoke an external parsing service or an LLM-generated repair layer. If deterministic artifacts do not support a reliable check, use cannot_verify.
  • Keep final-report traceability in the traceability appendix. Do not reintroduce repeated traceability footers in the body.
  • Literature and novelty critiques must be grounded in concrete studies or marked cannot_verify; do not assert lack of novelty from vague prior-work impressions.
  • If the final report cites external studies, registry records, web pages, or other external evidence, include the external-sources appendix using only source details already present in reviewer evidence.
  • Put parser/preprocessing issues in the technical appendix and describe them as limitations of the review artifacts. Mention one in the main report only when it materially reduces confidence in a substantive conclusion or prevents verification of an important claim.
  • Treat scripts/check_final_report.py as a structure and traceability smoke check, not as independent verification that external sources are real or current.
  • Treat every conditional specialist as a full-quality reviewer. Skip one only when a high-confidence classification shows that its entire remit is materially absent. The theory-logic specialist checks formal validity and assumption-to-result logic; the universal model/equation auditor separately checks notation, definitions, and text-equation consistency.
  • If a reviewer's assigned scope is absent, return run_status: ok with an empty findings array. Do not turn the absence of an empirical design, formal model, dataset, experiment, or other method into a criticism.
  • If codex exec --output-last-message writes only a short acknowledgement for the editor, rely on the wrapper's recovery from the editor transcript and then rerun the final report checker.

Output conventions

  • Parsed artifacts: work/<paper_id>/parsed/
  • Reviewer selection: work/<paper_id>/selection/
  • Reviewer outputs: work/<paper_id>/reviews/
  • Final report: outputs/<paper_id>/report.md

The expected final report shape is synthesis-first and consequence-ranked: a compact executive summary; 3 to 6 confirmed corrections when supported; a concise revision sequence; separate material qualifications and exploratory development advice; domain sections; and late appendices for bibliography maintenance, copyediting, external sources, parser limitations, review scope, and traceability. Use one short plain-language review-scope paragraph near the end rather than listing agents or routing metadata.

© Ingar30, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/paper-reviewer of Ingar30/reviewer.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit c591f4a

Compare with similar skills

Paper Reviewer 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 Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Paper Reviewer this skillIngar30/reviewer222—~2kAutomated safety check: PassMIT
PDFzai-org/ZCode7.7k—~18kAutomated safety check: NotesProprietary
Split PDFscunning1975/MixtapeTools4742 repos~2.9kAutomated safety check: PassNone
Paper Interpretationdigoal/blog8.6k—~1.5kAutomated safety check: PassGPL-2.0
Paper2slidesQuZhan51496/paper2anything450—~3.8kAutomated safety check: NotesApache-2.0
Paper LensYSQ-boop/paper-lens101—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • PDF

    zai-org/ZCode

    Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.

    7.7k GitHub stars~18k tokensUpdated today
    Documents & OfficeAuto-check: notes

  • Split PDF

    scunning1975/MixtapeTools

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

    474 GitHub starsUsed in 2 repos~2.9k tokens
    Documents & OfficeAuto-check passed

  • Paper Interpretation

    digoal/blog

    从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed

  • Paper2slides

    QuZhan51496/paper2anything

    Turn an academic paper PDF into a presentation deck (.pptx) end-to-end.

    450 GitHub stars~3.8k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check: notes

  • Paper Lens

    YSQ-boop/paper-lens

    Read and critically analyze one academic paper from an arXiv URL/ID or a local PDF, producing a source-grounded Markdown report that can grow from a quick read into a reviewer-level deep review.

    101 GitHub stars~1.3k tokensUpdated 12 days ago
    Documents & OfficeAuto-check passed

  • Geng Academic Fraud Detector

    wooly99/geng-academic-fraud-detector

    学术论文打假检测器，致敬耿同学。分析学术论文 PDF，检测数据造假、图片复用/拼接、Western blot 操纵、统计异常等学术不端行为。当用户提供论文 PDF 要求"查重"、"打假"、"检测造假"、"论文分析"、"学术打假"时使用。

    278 GitHub stars~970 tokensUpdated 4 mo ago
    Documents & OfficeAuto-check passed

More from Ingar30/reviewer

  • Review Paper

    Ingar30/reviewer

    Review an attached academic economics paper PDF with independent specialist audits and a complete evidence-grounded report, resume an interrupted paper review, or export a completed Reviewer report…

    222 GitHub stars~1.8k tokensUpdated 8 days ago
    Auto-check passed

Categories

Questions about Paper Reviewer

What does Paper Reviewer do?

A skill your agent uses when the task is to review an academic paper PDF from the repo input folder, run specialized auditors, and compile a final report. Paper Reviewer is an agent skill from Ingar30/reviewer. Use this skill when the task is to review an academic paper PDF from the repo input folder, run specialized auditors, and compile a final report.

When should I use Paper Reviewer?

Paper Reviewer fits situations like: the task is to review an academic paper PDF from the repo input folder; run specialized auditors; compile a final report.

How do I install Paper Reviewer in Claude Code?

Run `npx skills add Ingar30/reviewer --skill paper-reviewer -a claude-code`. Or copy the skill folder (.agents/skills/paper-reviewer in Ingar30/reviewer) into .claude/skills/paper-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Paper Reviewer in Codex?

Run `npx skills add Ingar30/reviewer --skill paper-reviewer -a codex`. Or copy the skill folder (.agents/skills/paper-reviewer in Ingar30/reviewer) into .agents/skills/paper-reviewer in your project. Codex loads it when a task matches its description.

Can I use Paper Reviewer 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 Ingar30/reviewer --skill paper-reviewer -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-reviewer, .gemini/skills/paper-reviewer, .github/skills/paper-reviewer and .opencode/skills/paper-reviewer in your project.

What does Paper Reviewer need to run?

Going by SKILL.md and its folder, Paper Reviewer needs the command-line tools its instructions call (codex).

Does Paper Reviewer 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 Reviewer 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 Paper Reviewer use?

Paper Reviewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paper Reviewer use?

About 2k tokens (SKILL.md is roughly 7.9k 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 Reviewer?

Skills that share tags, products or a category with Paper Reviewer: PDF (zai-org/ZCode, 7.7k stars), Split PDF (scunning1975/MixtapeTools, 474 stars), Paper Interpretation (digoal/blog, 8.6k stars) and Paper2slides (QuZhan51496/paper2anything, 450 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper Reviewer?

Ingar30 (a GitHub user) maintains it in Ingar30/reviewer, which has 222 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 2, 2026.

Source: Ingar30/reviewer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.