data-availability

Name: data-availability
Author: Boom5426

43installs28forks

How to install data-availability?

boom5426/nature-paper-skills/data-availability

$npx -y skills add Boom5426/Nature-Paper-Skills --skill data-availability

Installs into the current project.

Summary

Use when drafting, auditing, or revising Data Availability statements, repository plans, accession-number placement, source-data coverage, or restricted-data wording for journal submission or resubmission.

Files · 1

View on GitHub

SKILL.md

1	# Data Availability
2
3	## Overview
4
5	Use this skill to turn manuscript-supporting data into a submission-ready availability package: statement text, repository plan, source-data mapping, and unresolved-risk flags.
6
7	This skill is narrower than `submission-audit` and more operational than `scientific-writing`. Use it when the bottleneck is no longer the paper's story, but whether the data-sharing package is specific, durable, and journal-ready.
8
9	## When To Use
10
11	Use this skill when:
12	- the manuscript needs a `Data Availability` statement
13	- accession numbers, DOIs, repository records, or source-data files are missing or unstable
14	- the paper mixes generated data, reused public data, and restricted data
15	- "available upon request" wording needs to be tightened or replaced
16	- a submission or revision needs data-sharing text that editors can audit quickly
17
18	Do not use this skill for:
19	- generic section rewriting unrelated to data sharing
20	- full manuscript restructuring
21	- bibliography cleanup that does not affect dataset availability
22
23	## Workflow
24
25	1. Identify the target journal and article type.
26	2. Inventory the datasets that support the main and supplementary claims:
27	- raw data
28	- processed data
29	- figure source data
30	- reused public datasets
31	- code-adjacent outputs that are necessary to inspect the results
32	3. Assign each dataset one access route only:
33	- public repository
34	- controlled-access repository
35	- within paper or supplement
36	- reused public source
37	- third-party restricted
38	- justified request route
39	4. Choose repository and identifier strategy before drafting the statement.
40	5. Draft explicit dataset-to-location wording.
41	6. Check that the statement covers both newly generated and reused data.
42	7. Flag unresolved fields rather than inventing repository names, accession IDs, DOIs, or access rules.
43
44	## Working Rules
45
46	- Prefer public, discipline-specific repositories when possible.
47	- Treat `available upon request` as weak unless a real legal, ethical, commercial, or third-party restriction exists.
48	- If data cannot be public, state:
49	- why access is restricted
50	- who controls access
51	- how requests are reviewed
52	- what metadata, source data, or derived data remain public
53	- Do not merge data, code, protocols, and materials into one vague availability sentence unless the journal explicitly wants that.
54	- Do not invent accession numbers, DOIs, repository names, reviewer links, or embargo terms.
55
56	## Related Files
57
58	Open these only when needed:
59
60	- `references/statement-patterns.md`
61	Use when drafting or repairing the actual statement text.
62	- `references/repository-routing.md`
63	Use when deciding where each dataset should live and what identifier type is needed.
64	- `references/source-data-checks.md`
65	Use when checking whether figures, tables, and supplements expose enough underlying data.
66	- `references/fair-metadata-checklist.md`
67	Use when the journal expects FAIR or DataCite-style dataset metadata, or a formal dataset citation.
68	- `references/chinese-author-alignment.md`
69	Use when aligning a Chinese-language data-availability draft to English submission wording.
70
71	## Output Standard
72
73	When using this skill, return:
74	- ready-to-paste `Data Availability` text
75	- repository and identifier actions still required
76	- missing information or blocking risks
77	- a short note on whether the current package is:
78	- `ready_to_submit`
79	- `draft_with_placeholders`
80	- `needs_author_input`
81	- `blocked`

People who liked this also viewed

6 picks

Type

data-availability

43installs28forks

View on GitHub

How to install data-availability?

boom5426/nature-paper-skills/data-availability

$npx -y skills add Boom5426/Nature-Paper-Skills --skill data-availability

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Data Availability
2
3	## Overview
4
5	Use this skill to turn manuscript-supporting data into a submission-ready availability package: statement text, repository plan, source-data mapping, and unresolved-risk flags.
6
7	This skill is narrower than `submission-audit` and more operational than `scientific-writing`. Use it when the bottleneck is no longer the paper's story, but whether the data-sharing package is specific, durable, and journal-ready.
8
9	## When To Use
10
11	Use this skill when:
12	- the manuscript needs a `Data Availability` statement
13	- accession numbers, DOIs, repository records, or source-data files are missing or unstable
14	- the paper mixes generated data, reused public data, and restricted data
15	- "available upon request" wording needs to be tightened or replaced
16	- a submission or revision needs data-sharing text that editors can audit quickly
17
18	Do not use this skill for:
19	- generic section rewriting unrelated to data sharing
20	- full manuscript restructuring
21	- bibliography cleanup that does not affect dataset availability
22
23	## Workflow
24
25	1. Identify the target journal and article type.
26	2. Inventory the datasets that support the main and supplementary claims:
27	- raw data
28	- processed data
29	- figure source data
30	- reused public datasets
31	- code-adjacent outputs that are necessary to inspect the results
32	3. Assign each dataset one access route only:
33	- public repository
34	- controlled-access repository
35	- within paper or supplement
36	- reused public source
37	- third-party restricted
38	- justified request route
39	4. Choose repository and identifier strategy before drafting the statement.
40	5. Draft explicit dataset-to-location wording.
41	6. Check that the statement covers both newly generated and reused data.
42	7. Flag unresolved fields rather than inventing repository names, accession IDs, DOIs, or access rules.
43
44	## Working Rules
45
46	- Prefer public, discipline-specific repositories when possible.
47	- Treat `available upon request` as weak unless a real legal, ethical, commercial, or third-party restriction exists.
48	- If data cannot be public, state:
49	- why access is restricted
50	- who controls access
51	- how requests are reviewed
52	- what metadata, source data, or derived data remain public
53	- Do not merge data, code, protocols, and materials into one vague availability sentence unless the journal explicitly wants that.
54	- Do not invent accession numbers, DOIs, repository names, reviewer links, or embargo terms.
55
56	## Related Files
57
58	Open these only when needed:
59
60	- `references/statement-patterns.md`
61	Use when drafting or repairing the actual statement text.
62	- `references/repository-routing.md`
63	Use when deciding where each dataset should live and what identifier type is needed.
64	- `references/source-data-checks.md`
65	Use when checking whether figures, tables, and supplements expose enough underlying data.
66	- `references/fair-metadata-checklist.md`
67	Use when the journal expects FAIR or DataCite-style dataset metadata, or a formal dataset citation.
68	- `references/chinese-author-alignment.md`
69	Use when aligning a Chinese-language data-availability draft to English submission wording.
70
71	## Output Standard
72
73	When using this skill, return:
74	- ready-to-paste `Data Availability` text
75	- repository and identifier actions still required
76	- missing information or blocking risks
77	- a short note on whether the current package is:
78	- `ready_to_submit`
79	- `draft_with_placeholders`
80	- `needs_author_input`
81	- `blocked`

People who liked this also viewed

6 picks

Type