paper-review-lite

Name: paper-review-lite
Author: scdenney

34stars0forks

How to install paper-review-lite?

scdenney/open-science-skills/paper-review-lite

$npx -y skills add scdenney/open-science-skills --skill paper-review-lite

Installs into the current project.

Summary

Run a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistration, and replication readiness.

Files · 1

View on GitHub

SKILL.md

1	# Paper Pre-Submission Review (Lite)
2
3	## Heritage and scope
4
5	This is the in-session, Codex-native counterpart to [`presubmit`](https://github.com/scdenney/presubmit), itself descended from the [reviewer2](https://github.com/isitcredible/reviewer2) adversarial peer-review pipeline. The design inherits two things from that lineage:
6
7	1. A Critical-Reviewer posture. Review sub-agents adopt the persona of a rigorous, epistemically humble reviewer who is brutally honest about weaknesses but impervious to prestige (reputation, journal status, citation counts, prior peer review) and grounds every finding in a quote from the manuscript.
8	2. A verification cascade. Red Team findings are cross-checked against the source before they enter the final report; claims that cannot be pinned to a quoted passage are dropped as likely hallucinations.
9
10	What this skill is: an approximately 11-subagent review that runs inside a Codex session with no extra review tool to install. It is intended for fast feedback during writing.
11
12	What it is NOT: the full reviewer2/`presubmit` pipeline. That tool runs ~30 stages with a dedicated Red Team (Breaker, Butcher, Shredder, Collector, Void), Blue Team defence, numbers/fact-check/citation-verification cascades, and a legal pass — and it is resumable and cost-tracked. Reach for `presubmit` when you want deeper adversarial pressure, need a standalone deliverable (a review report file), or are preparing a manuscript for final external peer review. This skill is the fast in-flow check.
13
14	## Delegation gate
15
16	Run the subagent workflow only when the user explicitly invokes `$paper-review-lite` or asks for parallel/subagent review. If the skill loads implicitly, either perform the dimensions sequentially in the lead context or ask before spawning agents.
17
18	## Instructions
19
20	Run a comprehensive pre-submission review of the academic paper using parallel review agents. Each agent examines a different dimension; cross-check agents audit Phase 1 findings for false positives and missed issues. The final output is a structured pre-submit report with severity-ranked findings and a journal-readiness checklist.
21
22	Critical-Reviewer posture (required for every sub-agent). Every review sub-agent must (a) cite a direct quote from the manuscript for every `[CRITICAL]` and `[RECOMMENDED]` finding — a short verbatim span is sufficient, and (b) attack the argument or the data, not the authors. Framing like "fraudulent" or "incompetent" is out of scope; "the claim on line X is not supported by the evidence on line Y" is in scope. The standard is brutally honest on the work, fair to the people.
23
24	This review can be re-run after fixes to verify issues are resolved.
25
26	### 1. Orientation (do this yourself before launching agents)
27
28	Read the paper yourself to understand its structure before writing agent prompts. Determine:
29
30	- Where the paper source lives (LaTeX `.tex` vs Pandoc `.md` vs Word) and what the build command is
31	- Whether a Supplementary Information file exists and where it lives
32	- Where figures are stored and how they are referenced (relative paths, figure directories)
33	- Whether a replication archive exists (look for `replication/`, `archive/`, `data/`, README files)
34	- The paper's rough structure: section names, approximate page count, key claims in the abstract
35	- The bibliography format and location (`.bib`, inline, etc.)
36	- Design family. Is this a conjoint/factorial-vignette paper, a list experiment, a topic-modeling or LLM-classification study, or a VLM-OCR corpus paper? If so, also invoke the relevant sibling skill (`conjoint-diagnostics`, `list-experiment`, `topic-modeling`, `text-classification`, `vlm-ocr-pipeline`) and fold its domain-specific checklist into Agent 9's deliverable. For any experimental manuscript, also run `methods-reporting` in audit mode so its 45-item checklist becomes the baseline for Agents 1, 2, 6, 7, and 8.
37
38	Use this knowledge to write specific agent prompts that reference actual file paths, section names, and relevant files. Generic prompts produce shallow results.
39
40	Orchestration contract. Before Phase 2, create a scratch directory `.review-tmp/` in the paper's working directory. Each Phase 2 agent writes its structured findings to a dedicated file — `agent-1-content.md`, `agent-2-numbers.md`, `agent-3-references.md`, `agent-4-dois.md`, `agent-5-writing.md`, `agent-6-consort.md`, `agent-7-prereg.md`, `agent-8-figures.md`, `agent-9-archive.md` — using the output format specified below. Use these exact filenames; Phase 3 reads them directly. Phase 3 cross-checkers read these files directly; you do not need to paste findings back into their prompts. Launch Phase 2 agents in parallel batches that respect the runtime's concurrency limit; launch Phase 3 after ever

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

paper-review-lite

34stars0forks

View on GitHub

How to install paper-review-lite?

scdenney/open-science-skills/paper-review-lite

$npx -y skills add scdenney/open-science-skills --skill paper-review-lite

Installs into the current project.

Summary

Run a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistration, and replication readiness.

Files · 1

View on GitHub

SKILL.md

1	# Paper Pre-Submission Review (Lite)
2
3	## Heritage and scope
4
5	This is the in-session, Codex-native counterpart to [`presubmit`](https://github.com/scdenney/presubmit), itself descended from the [reviewer2](https://github.com/isitcredible/reviewer2) adversarial peer-review pipeline. The design inherits two things from that lineage:
6
7	1. A Critical-Reviewer posture. Review sub-agents adopt the persona of a rigorous, epistemically humble reviewer who is brutally honest about weaknesses but impervious to prestige (reputation, journal status, citation counts, prior peer review) and grounds every finding in a quote from the manuscript.
8	2. A verification cascade. Red Team findings are cross-checked against the source before they enter the final report; claims that cannot be pinned to a quoted passage are dropped as likely hallucinations.
9
10	What this skill is: an approximately 11-subagent review that runs inside a Codex session with no extra review tool to install. It is intended for fast feedback during writing.
11
12	What it is NOT: the full reviewer2/`presubmit` pipeline. That tool runs ~30 stages with a dedicated Red Team (Breaker, Butcher, Shredder, Collector, Void), Blue Team defence, numbers/fact-check/citation-verification cascades, and a legal pass — and it is resumable and cost-tracked. Reach for `presubmit` when you want deeper adversarial pressure, need a standalone deliverable (a review report file), or are preparing a manuscript for final external peer review. This skill is the fast in-flow check.
13
14	## Delegation gate
15
16	Run the subagent workflow only when the user explicitly invokes `$paper-review-lite` or asks for parallel/subagent review. If the skill loads implicitly, either perform the dimensions sequentially in the lead context or ask before spawning agents.
17
18	## Instructions
19
20	Run a comprehensive pre-submission review of the academic paper using parallel review agents. Each agent examines a different dimension; cross-check agents audit Phase 1 findings for false positives and missed issues. The final output is a structured pre-submit report with severity-ranked findings and a journal-readiness checklist.
21
22	Critical-Reviewer posture (required for every sub-agent). Every review sub-agent must (a) cite a direct quote from the manuscript for every `[CRITICAL]` and `[RECOMMENDED]` finding — a short verbatim span is sufficient, and (b) attack the argument or the data, not the authors. Framing like "fraudulent" or "incompetent" is out of scope; "the claim on line X is not supported by the evidence on line Y" is in scope. The standard is brutally honest on the work, fair to the people.
23
24	This review can be re-run after fixes to verify issues are resolved.
25
26	### 1. Orientation (do this yourself before launching agents)
27
28	Read the paper yourself to understand its structure before writing agent prompts. Determine:
29
30	- Where the paper source lives (LaTeX `.tex` vs Pandoc `.md` vs Word) and what the build command is
31	- Whether a Supplementary Information file exists and where it lives
32	- Where figures are stored and how they are referenced (relative paths, figure directories)
33	- Whether a replication archive exists (look for `replication/`, `archive/`, `data/`, README files)
34	- The paper's rough structure: section names, approximate page count, key claims in the abstract
35	- The bibliography format and location (`.bib`, inline, etc.)
36	- Design family. Is this a conjoint/factorial-vignette paper, a list experiment, a topic-modeling or LLM-classification study, or a VLM-OCR corpus paper? If so, also invoke the relevant sibling skill (`conjoint-diagnostics`, `list-experiment`, `topic-modeling`, `text-classification`, `vlm-ocr-pipeline`) and fold its domain-specific checklist into Agent 9's deliverable. For any experimental manuscript, also run `methods-reporting` in audit mode so its 45-item checklist becomes the baseline for Agents 1, 2, 6, 7, and 8.
37
38	Use this knowledge to write specific agent prompts that reference actual file paths, section names, and relevant files. Generic prompts produce shallow results.
39
40	Orchestration contract. Before Phase 2, create a scratch directory `.review-tmp/` in the paper's working directory. Each Phase 2 agent writes its structured findings to a dedicated file — `agent-1-content.md`, `agent-2-numbers.md`, `agent-3-references.md`, `agent-4-dois.md`, `agent-5-writing.md`, `agent-6-consort.md`, `agent-7-prereg.md`, `agent-8-figures.md`, `agent-9-archive.md` — using the output format specified below. Use these exact filenames; Phase 3 reads them directly. Phase 3 cross-checkers read these files directly; you do not need to paste findings back into their prompts. Launch Phase 2 agents in parallel batches that respect the runtime's concurrency limit; launch Phase 3 after ever

People who liked this also viewed

6 picks

Type