nature-statistics

Name: nature-statistics
Author: Yuan1z0825

985installs1.8kforks

How to install nature-statistics?

yuan1z0825/nature-skills/nature-statistics

$npx -y skills add Yuan1z0825/nature-skills --skill nature-statistics

Installs into the current project.

Summary

Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, mult

Files · 1

View on GitHub

SKILL.md

1	# Nature Statistics Reporting Skill
2
3	Use this skill to make manuscript statistics transparent, reproducible, and appropriately bounded. It is a reporting and review skill, not a substitute for a statistician reanalysing raw data unless the user supplies the data and explicitly asks for computation.
4
5	## Default stance
6
7	- Prioritize design transparency over decorative statistical language.
8	- Separate three questions: what was measured, what unit was analysed, and what inference was claimed.
9	- Treat the independent experimental unit as the default `n`; do not silently treat cells, fields of view, repeated readings, spectra, model runs, or technical replicates as independent biological or experimental samples.
10	- Prefer effect sizes, uncertainty intervals, sample sizes, and exact test definitions over significance-only phrasing.
11	- State missing information as `AUTHOR_INPUT_NEEDED` instead of inventing sample sizes, tests, software, corrections, exclusion rules, randomization, or blinding.
12	- If a journal-specific instruction, study-type guideline, or field standard conflicts with this skill, follow the more specific source and mark the source used.
13
14	## Accepted inputs
15
16	The skill may receive:
17
18	- a Statistical analysis / Methods subsection
19	- Results paragraphs containing test statistics or p values
20	- figure panels, legends, captions, or source-data notes
21	- reviewer comments about statistics
22	- author notes in Chinese or English
23	- tables of reported comparisons
24	- raw or summary data, only when the user wants a concrete reanalysis or figure-statistics check
25
26	If the input is partial, run a bounded audit and state which parts cannot be assessed.
27
28	## Workflow
29
30	1. Classify the task. Decide whether the user wants audit, rewrite, draft, reviewer-response support, figure-statistics alignment, or data-backed reanalysis.
31	2. Extract the design. Identify groups, treatments, time points, endpoints, blocking factors, repeated measures, randomization, blinding, exclusions, and missing-data handling.
32	3. Define `n` and replication. Separate independent experimental units, biological replicates, technical replicates, repeated measures, cells/fields/subsamples, simulations, and pooled observations.
33	4. Map claims to analyses. For each result claim, record the comparison/model, test family, assumptions, correction strategy, effect estimate, uncertainty, and exact p-value policy.
34	5. Check common failure modes. Use `references/common-failure-modes.md` when the text involves nested data, many comparisons, cell-level measurements, interaction claims, correlations, regression, outliers, small samples, or significance-only reasoning.
35	6. Check reporting completeness. Use `references/statistical-reporting.md` to verify that Methods and Results give enough information for readers and reviewers to understand the analysis.
36	7. Align figure statistics. Use `references/figure-statistics.md` when figure legends, panel labels, stars, error bars, box plots, violin plots, source data, or supplementary figure notes are involved.
37	8. Draft or revise. Produce conservative, ready-to-paste text. Keep claims within the supplied design and evidence. Do not upgrade statistical association into mechanism or causality.
38	9. Run final QA. Use `references/reviewer-checklist.md` before final delivery for severity labels, unresolved author questions, and reviewer-facing risk.
39
40	## Output format
41
42	Unless the user asks for another format, return:
43
44	```text
45	Statistics review scope
46	- Input reviewed:
47	- Boundary / missing materials:
48	- Study design readout:
49	- Independent unit and replication readout:
50
51	Major statistical issues
52	- [P0/P1/P2] Issue:
53	Evidence from supplied text:
54	Why it matters:
55	Fix:
56
57	Ready-to-paste revision
58	[Rewritten Statistical analysis / Results / figure legend text]
59
60	AUTHOR_INPUT_NEEDED
61	- [short factual questions only]
62
63	Reviewer-risk note
64	- What a statistical reviewer may still challenge:
65	```
66
67	For a clean drafting request with enough information, skip the long issue list and return:
68
69	```text
70	Draft Statistical analysis
71	[ready-to-paste text]
72
73	Reporting notes
74	- n definition:
75	- tests/models:
76	- multiple comparisons:
77	- software/version:
78	- unresolved fields:
79	```
80
81	## Red lines
82
83	- Do not invent p values, sample sizes, degrees of freedom, confidence intervals, software versions, correction metho

People who liked this also viewed

6 picks

Type

nature-statistics

985installs1.8kforks

View on GitHub

How to install nature-statistics?

yuan1z0825/nature-skills/nature-statistics

$npx -y skills add Yuan1z0825/nature-skills --skill nature-statistics

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Nature Statistics Reporting Skill
2
3	Use this skill to make manuscript statistics transparent, reproducible, and appropriately bounded. It is a reporting and review skill, not a substitute for a statistician reanalysing raw data unless the user supplies the data and explicitly asks for computation.
4
5	## Default stance
6
7	- Prioritize design transparency over decorative statistical language.
8	- Separate three questions: what was measured, what unit was analysed, and what inference was claimed.
9	- Treat the independent experimental unit as the default `n`; do not silently treat cells, fields of view, repeated readings, spectra, model runs, or technical replicates as independent biological or experimental samples.
10	- Prefer effect sizes, uncertainty intervals, sample sizes, and exact test definitions over significance-only phrasing.
11	- State missing information as `AUTHOR_INPUT_NEEDED` instead of inventing sample sizes, tests, software, corrections, exclusion rules, randomization, or blinding.
12	- If a journal-specific instruction, study-type guideline, or field standard conflicts with this skill, follow the more specific source and mark the source used.
13
14	## Accepted inputs
15
16	The skill may receive:
17
18	- a Statistical analysis / Methods subsection
19	- Results paragraphs containing test statistics or p values
20	- figure panels, legends, captions, or source-data notes
21	- reviewer comments about statistics
22	- author notes in Chinese or English
23	- tables of reported comparisons
24	- raw or summary data, only when the user wants a concrete reanalysis or figure-statistics check
25
26	If the input is partial, run a bounded audit and state which parts cannot be assessed.
27
28	## Workflow
29
30	1. Classify the task. Decide whether the user wants audit, rewrite, draft, reviewer-response support, figure-statistics alignment, or data-backed reanalysis.
31	2. Extract the design. Identify groups, treatments, time points, endpoints, blocking factors, repeated measures, randomization, blinding, exclusions, and missing-data handling.
32	3. Define `n` and replication. Separate independent experimental units, biological replicates, technical replicates, repeated measures, cells/fields/subsamples, simulations, and pooled observations.
33	4. Map claims to analyses. For each result claim, record the comparison/model, test family, assumptions, correction strategy, effect estimate, uncertainty, and exact p-value policy.
34	5. Check common failure modes. Use `references/common-failure-modes.md` when the text involves nested data, many comparisons, cell-level measurements, interaction claims, correlations, regression, outliers, small samples, or significance-only reasoning.
35	6. Check reporting completeness. Use `references/statistical-reporting.md` to verify that Methods and Results give enough information for readers and reviewers to understand the analysis.
36	7. Align figure statistics. Use `references/figure-statistics.md` when figure legends, panel labels, stars, error bars, box plots, violin plots, source data, or supplementary figure notes are involved.
37	8. Draft or revise. Produce conservative, ready-to-paste text. Keep claims within the supplied design and evidence. Do not upgrade statistical association into mechanism or causality.
38	9. Run final QA. Use `references/reviewer-checklist.md` before final delivery for severity labels, unresolved author questions, and reviewer-facing risk.
39
40	## Output format
41
42	Unless the user asks for another format, return:
43
44	```text
45	Statistics review scope
46	- Input reviewed:
47	- Boundary / missing materials:
48	- Study design readout:
49	- Independent unit and replication readout:
50
51	Major statistical issues
52	- [P0/P1/P2] Issue:
53	Evidence from supplied text:
54	Why it matters:
55	Fix:
56
57	Ready-to-paste revision
58	[Rewritten Statistical analysis / Results / figure legend text]
59
60	AUTHOR_INPUT_NEEDED
61	- [short factual questions only]
62
63	Reviewer-risk note
64	- What a statistical reviewer may still challenge:
65	```
66
67	For a clean drafting request with enough information, skip the long issue list and return:
68
69	```text
70	Draft Statistical analysis
71	[ready-to-paste text]
72
73	Reporting notes
74	- n definition:
75	- tests/models:
76	- multiple comparisons:
77	- software/version:
78	- unresolved fields:
79	```
80
81	## Red lines
82
83	- Do not invent p values, sample sizes, degrees of freedom, confidence intervals, software versions, correction metho

People who liked this also viewed

6 picks

Type