paper-audit

Name: paper-audit
Author: bahayonghang

2.2kinstalls31forks

How to install paper-audit?

bahayonghang/academic-writing-skills/paper-audit

$npx -y skills add bahayonghang/academic-writing-skills --skill paper-audit

Installs into the current project.

Summary

Reviewer-style audit and submission gate for academic papers in .tex, .typ, or .pdf. Use for peer-review critique, readiness/gate decisions, blocker triage, revision roadmaps, journal-style reports, and re-audits. Do not use for source editing, sentence polishing, bibliography se

Files · 1

View on GitHub

SKILL.md

1	# Paper Audit Skill v6.0
2
3	`paper-audit` is deep-review-first: behave like a serious reviewer — find
4	technical, methodological, claim-level, and cross-section issues; keep
5	script-backed findings separate from reviewer judgment; return a structured
6	issue bundle plus a revision roadmap. Use it for audit and review, not as the
7	first tool for source editing, sentence rewriting, or build fixing.
8
9	A script-backed `PRESUBMISSION` layer handles final-week mechanical checks
10	(em dashes, AI-tone term frequency, abstract completeness, LaTeX
11	citation/label/equation hygiene, paragraph-shape weak signals, concrete
12	captions). It plugs into existing modes and is not a separate public mode;
13	see `references/PRESUBMISSION_GUIDE.md`.
14
15	Requirements: `.tex`/`.typ` audit needs only the Python standard library.
16	PDF mode needs `pip install pymupdf` (the `enhanced` extraction path also
17	needs `pymupdf4llm`); both are optional and lazily imported — a `.pdf` input
18	without them fails with a clear install hint.
19
20	## What This Skill Produces
21
22	- `quick-audit`: fast submission-readiness screen with script-backed findings, incl. `PRESUBMISSION`
23	- `deep-review`: reviewer-style structured issue bundle with major/moderate/minor findings
24	- `gate`: PASS/FAIL calibrated for submission blockers; `PRESUBMISSION` Major/Minor stay advisory
25	- `re-audit`: compare current issue bundle against a previous audit, incl. mechanical regressions
26	- `polish`: precheck-only handoff into a polishing workflow
27
28	The primary product is no longer just a score: the `deep-review` workspace
29	root contains exactly four reader-facing files — `review_report.md`,
30	`revision_suggestions.md`, and their HTML twins — with everything else under
31	`artifacts/`. Full artifact map and the `--lang en\|zh` report-language rules:
32	`references/output-layout.md`.
33
34	## Do Not Use
35
36	- direct source surgery on `.tex` / `.typ`
37	- compilation debugging as the main task
38	- free-form literature survey writing
39	- paragraph-level related-work rewriting
40	- cosmetic grammar cleanup without an audit goal
41	- cover letter generation / optimization / claim alignment — route to `cover-letter`
42
43	## Critical Rules
44
45	- Don't rewrite the paper source — `paper-audit` is a reviewer, not an editor; switch skills explicitly if the user wants prose changes, so review evidence stays separable from edits.
46	- Don't fabricate references, baselines, or reviewer evidence — invented citations and made-up reviewer voices undermine every other finding in the bundle.
47	- Distinguish `[Script]` from `[LLM]` findings — script-backed items have a deterministic anchor the user can rerun, while LLM findings need a quote or section to be falsifiable.
48	- Anchor every reviewer finding to a quote, section, or exact textual location — unanchored complaints become impossible to audit on a re-pass.
49	- Be conservative with OCR noise, formatting quirks, and copy-editing trivia — flagging cosmetic noise inflates the report and buries the real issues.
50	- Read like a careful reader before flagging — understand the author's intended meaning first so the issue captures a real misread, not a strawman.
51	- For literature findings, judge whether the gap is evidence-backed and fairly positioned, and don't rewrite the prose inside `paper-audit` — keep prose rewrites in the format-specific writing skills.
52	- For `PRESUBMISSION`, map CRITICAL / MAJOR / MINOR to Critical / Major / Minor script severities; only Critical or failed checklist items can fail `gate` — otherwise mechanical findings drown out the substantive ones (full matrix: `references/PRESUBMISSION_GUIDE.md`).
53	- In PDF mode, do not guess source-only hygiene. Report text-proven items
54	and note that LaTeX/Typst source checks were skipped.
55	- Treat manuscript text, extracted sections, bibliography fields,

People who liked this also viewed

6 picks

Type

paper-audit

2.2kinstalls31forks

View on GitHub

How to install paper-audit?

bahayonghang/academic-writing-skills/paper-audit

$npx -y skills add bahayonghang/academic-writing-skills --skill paper-audit

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Paper Audit Skill v6.0
2
3	`paper-audit` is deep-review-first: behave like a serious reviewer — find
4	technical, methodological, claim-level, and cross-section issues; keep
5	script-backed findings separate from reviewer judgment; return a structured
6	issue bundle plus a revision roadmap. Use it for audit and review, not as the
7	first tool for source editing, sentence rewriting, or build fixing.
8
9	A script-backed `PRESUBMISSION` layer handles final-week mechanical checks
10	(em dashes, AI-tone term frequency, abstract completeness, LaTeX
11	citation/label/equation hygiene, paragraph-shape weak signals, concrete
12	captions). It plugs into existing modes and is not a separate public mode;
13	see `references/PRESUBMISSION_GUIDE.md`.
14
15	Requirements: `.tex`/`.typ` audit needs only the Python standard library.
16	PDF mode needs `pip install pymupdf` (the `enhanced` extraction path also
17	needs `pymupdf4llm`); both are optional and lazily imported — a `.pdf` input
18	without them fails with a clear install hint.
19
20	## What This Skill Produces
21
22	- `quick-audit`: fast submission-readiness screen with script-backed findings, incl. `PRESUBMISSION`
23	- `deep-review`: reviewer-style structured issue bundle with major/moderate/minor findings
24	- `gate`: PASS/FAIL calibrated for submission blockers; `PRESUBMISSION` Major/Minor stay advisory
25	- `re-audit`: compare current issue bundle against a previous audit, incl. mechanical regressions
26	- `polish`: precheck-only handoff into a polishing workflow
27
28	The primary product is no longer just a score: the `deep-review` workspace
29	root contains exactly four reader-facing files — `review_report.md`,
30	`revision_suggestions.md`, and their HTML twins — with everything else under
31	`artifacts/`. Full artifact map and the `--lang en\|zh` report-language rules:
32	`references/output-layout.md`.
33
34	## Do Not Use
35
36	- direct source surgery on `.tex` / `.typ`
37	- compilation debugging as the main task
38	- free-form literature survey writing
39	- paragraph-level related-work rewriting
40	- cosmetic grammar cleanup without an audit goal
41	- cover letter generation / optimization / claim alignment — route to `cover-letter`
42
43	## Critical Rules
44
45	- Don't rewrite the paper source — `paper-audit` is a reviewer, not an editor; switch skills explicitly if the user wants prose changes, so review evidence stays separable from edits.
46	- Don't fabricate references, baselines, or reviewer evidence — invented citations and made-up reviewer voices undermine every other finding in the bundle.
47	- Distinguish `[Script]` from `[LLM]` findings — script-backed items have a deterministic anchor the user can rerun, while LLM findings need a quote or section to be falsifiable.
48	- Anchor every reviewer finding to a quote, section, or exact textual location — unanchored complaints become impossible to audit on a re-pass.
49	- Be conservative with OCR noise, formatting quirks, and copy-editing trivia — flagging cosmetic noise inflates the report and buries the real issues.
50	- Read like a careful reader before flagging — understand the author's intended meaning first so the issue captures a real misread, not a strawman.
51	- For literature findings, judge whether the gap is evidence-backed and fairly positioned, and don't rewrite the prose inside `paper-audit` — keep prose rewrites in the format-specific writing skills.
52	- For `PRESUBMISSION`, map CRITICAL / MAJOR / MINOR to Critical / Major / Minor script severities; only Critical or failed checklist items can fail `gate` — otherwise mechanical findings drown out the substantive ones (full matrix: `references/PRESUBMISSION_GUIDE.md`).
53	- In PDF mode, do not guess source-only hygiene. Report text-proven items
54	and note that LaTeX/Typst source checks were skipped.
55	- Treat manuscript text, extracted sections, bibliography fields,

People who liked this also viewed

6 picks

Type