submission-audit

Name: submission-audit
Author: Boom5426

71installs28forks

How to install submission-audit?

boom5426/nature-paper-skills/submission-audit

$npx -y skills add Boom5426/Nature-Paper-Skills --skill submission-audit

Installs into the current project.

Summary

Use when a manuscript is close to submission or resubmission and you need a preflight audit for claim support, figure-panel coverage, legend sync, methods references, terminology stability, and venue-facing risks.

Files · 1

View on GitHub

SKILL.md

1	# Submission Audit
2
3	## Overview
4
5	Use this skill for late-stage manuscript QA. It is narrower than `manuscript-optimizer`: do not use it to redesign a paper from scratch. Use it when the structure mostly exists and the main task is to catch the failures that survive normal revision cycles.
6
7	The core rule is simple: never treat a clean-looking manuscript as submission-ready until the front half, figures, legends, methods, supplement, and venue expectations have been checked against each other.
8
9	Use the helper script when you want a fast local pass over figure citations:
10
11	```bash
12	python ~/.codex/skills/submission-audit/scripts/check_figure_refs.py path/to/manuscript.md
13	# Claude Code (global install): replace ~/.codex/skills with ~/.claude/skills
14	# Claude Code (project-local install): replace ~/.codex/skills with .claude/skills
15	```
16
17	## When To Use
18
19	Use this skill when:
20	- The draft is near submission, resubmission, or internal circulation
21	- Figures and legends are mostly finalized
22	- The paper needs a last pass for overclaim, missing references, or cross-section drift
23	- A revision round compressed the prose and may have dropped supporting detail
24	- The supplement exists and may no longer match the main text
25
26	Do not use this skill for:
27	- Early brainstorming
28	- Initial section drafting
29	- Citation discovery from scratch
30	- Heavy structural rewrites that belong in `manuscript-optimizer`
31
32	## Audit Order
33
34	1. Front-half alignment
35	- check title, abstract, introduction, and discussion against the actual Results
36	- flag any claim stronger than the downstream evidence
37	2. Figure and legend coverage
38	- verify that every main-figure panel and supplementary panel cited in the paper actually exists
39	- verify that panel letters, metrics, datasets, and numbers agree across figure, legend, and main text
40	3. Methods and supplement anchoring
41	- check that methods are cited where needed from Results
42	- check that supplementary figures, tables, and notes are referenced precisely enough to be usable
43	4. Terminology and metrics
44	- enforce one canonical name per concept
45	- check abbreviations, metric naming, domain-shift labels, cohort names, and model names
46	5. Risk pass
47	- overclaim
48	- evidence gaps
49	- unsupported mechanism language
50	- venue-specific style drift
51	6. Nature Portfolio preflight when relevant
52	- reporting-summary readiness
53	- data and code availability statements
54	- accession IDs, repositories, and disclosure of sharing restrictions
55	- image-integrity and raw-data readiness
56	- AI-use disclosure
57	- preprint, related-manuscript, and conference-proceedings disclosure
58	7. Reviewer-side rejection pass
59	- contribution sufficiency
60	- writing clarity and reproducibility
61	- empirical strength
62	- evaluation completeness
63	- design or framework soundness
64
65	## Required Checks
66
67	- Does every substantive abstract claim map to a figure, table, or supplement item?
68	- Does every Results subsection cite the correct panel range?
69	- Does every figure legend still reflect the current plot content?
70	- Are `Methods` cross-references present where interpretation depends on setup or metric definition?
71	- Is the supplement indexed precisely enough, including panel letters when needed?
72	- Are strong causal or mechanism words used only where direct evidence exists?
73	- Are title, abstract, and discussion consistent about the paper's actual contribution type?
74	- If the target is `Nature Portfolio`, are the reporting-summary inputs, data/code statements, image-integrity materials, and disclosure items actually ready rather than merely planned?
75	- If a submission form or portal draft already exists, do the title, abstract, keywords, availability statements, and related metadata still match the manuscript exactly?
76	- Has the paper been pressure-tested against the main rejection dimensions: insufficient contribution, weak clarity, weak empirical effect, incomplete evaluation, and questionable design?
77
78	## Finding Format
79
80	Report findings in this order:
81	- High: submission-blocking or claim-distorting issues
82	- Medium: credibility or reader-friction issues
83	- Low: consistency and polish issues
84
85	Each finding should include:
86	- exact file reference
87	- what is wrong
88	- why it matters
89	- the minimum safe fix
90
91	If no major problems exist, say that explicitly and then list only the residual risks or final checks still worth doing.
92
93	## Common Failure Modes
94
95	- Abstract promise stronger than Results support
96	- Figure panel mentioned in text but not actually indexed or explained
97	- Legend still describing an old version of the plot
98	- Supplementary figure cited at whole-figure level when the argument depends on one panel
99	- Metric names drifting between sections
100	- Discussion slipping into mechanism-l

People who liked this also viewed

6 picks

Type

submission-audit

71installs28forks

View on GitHub

How to install submission-audit?

boom5426/nature-paper-skills/submission-audit

$npx -y skills add Boom5426/Nature-Paper-Skills --skill submission-audit

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Submission Audit
2
3	## Overview
4
5	Use this skill for late-stage manuscript QA. It is narrower than `manuscript-optimizer`: do not use it to redesign a paper from scratch. Use it when the structure mostly exists and the main task is to catch the failures that survive normal revision cycles.
6
7	The core rule is simple: never treat a clean-looking manuscript as submission-ready until the front half, figures, legends, methods, supplement, and venue expectations have been checked against each other.
8
9	Use the helper script when you want a fast local pass over figure citations:
10
11	```bash
12	python ~/.codex/skills/submission-audit/scripts/check_figure_refs.py path/to/manuscript.md
13	# Claude Code (global install): replace ~/.codex/skills with ~/.claude/skills
14	# Claude Code (project-local install): replace ~/.codex/skills with .claude/skills
15	```
16
17	## When To Use
18
19	Use this skill when:
20	- The draft is near submission, resubmission, or internal circulation
21	- Figures and legends are mostly finalized
22	- The paper needs a last pass for overclaim, missing references, or cross-section drift
23	- A revision round compressed the prose and may have dropped supporting detail
24	- The supplement exists and may no longer match the main text
25
26	Do not use this skill for:
27	- Early brainstorming
28	- Initial section drafting
29	- Citation discovery from scratch
30	- Heavy structural rewrites that belong in `manuscript-optimizer`
31
32	## Audit Order
33
34	1. Front-half alignment
35	- check title, abstract, introduction, and discussion against the actual Results
36	- flag any claim stronger than the downstream evidence
37	2. Figure and legend coverage
38	- verify that every main-figure panel and supplementary panel cited in the paper actually exists
39	- verify that panel letters, metrics, datasets, and numbers agree across figure, legend, and main text
40	3. Methods and supplement anchoring
41	- check that methods are cited where needed from Results
42	- check that supplementary figures, tables, and notes are referenced precisely enough to be usable
43	4. Terminology and metrics
44	- enforce one canonical name per concept
45	- check abbreviations, metric naming, domain-shift labels, cohort names, and model names
46	5. Risk pass
47	- overclaim
48	- evidence gaps
49	- unsupported mechanism language
50	- venue-specific style drift
51	6. Nature Portfolio preflight when relevant
52	- reporting-summary readiness
53	- data and code availability statements
54	- accession IDs, repositories, and disclosure of sharing restrictions
55	- image-integrity and raw-data readiness
56	- AI-use disclosure
57	- preprint, related-manuscript, and conference-proceedings disclosure
58	7. Reviewer-side rejection pass
59	- contribution sufficiency
60	- writing clarity and reproducibility
61	- empirical strength
62	- evaluation completeness
63	- design or framework soundness
64
65	## Required Checks
66
67	- Does every substantive abstract claim map to a figure, table, or supplement item?
68	- Does every Results subsection cite the correct panel range?
69	- Does every figure legend still reflect the current plot content?
70	- Are `Methods` cross-references present where interpretation depends on setup or metric definition?
71	- Is the supplement indexed precisely enough, including panel letters when needed?
72	- Are strong causal or mechanism words used only where direct evidence exists?
73	- Are title, abstract, and discussion consistent about the paper's actual contribution type?
74	- If the target is `Nature Portfolio`, are the reporting-summary inputs, data/code statements, image-integrity materials, and disclosure items actually ready rather than merely planned?
75	- If a submission form or portal draft already exists, do the title, abstract, keywords, availability statements, and related metadata still match the manuscript exactly?
76	- Has the paper been pressure-tested against the main rejection dimensions: insufficient contribution, weak clarity, weak empirical effect, incomplete evaluation, and questionable design?
77
78	## Finding Format
79
80	Report findings in this order:
81	- High: submission-blocking or claim-distorting issues
82	- Medium: credibility or reader-friction issues
83	- Low: consistency and polish issues
84
85	Each finding should include:
86	- exact file reference
87	- what is wrong
88	- why it matters
89	- the minimum safe fix
90
91	If no major problems exist, say that explicitly and then list only the residual risks or final checks still worth doing.
92
93	## Common Failure Modes
94
95	- Abstract promise stronger than Results support
96	- Figure panel mentioned in text but not actually indexed or explained
97	- Legend still describing an old version of the plot
98	- Supplementary figure cited at whole-figure level when the argument depends on one panel
99	- Metric names drifting between sections
100	- Discussion slipping into mechanism-l

People who liked this also viewed

6 picks

Type