Use when preparing the transparency, open-science, and reproducibility materials for a Communication Research (CR) manuscript — data-availability statement, deposited data/code/materials, preregistration, and the restricted-data path. Prepares the materials; it does not waive requirements.
SkillScore95Maintained
Automatic
◆Research pack
Last verified 9/1/2026
What it changes
Passed 21 of 22 test cases with the skill, and 19 of 22 without it.
Without skill86%
With skill95%
Checks it passed that the model alone missed
Requires pinning software package versions.
Advises providing contact details for third-party data access requests.
2 fixed19 passed either way1 still failing0 broke
Pass-rate lift
+9 pp
Tokens
+37%
Agent turns
0%
Response time
-21%
Model gemini-3.6-flashMeasured 9/1/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
Our topic modeling script relies on Latent Dirichlet Allocation (LDA) which uses random initialization. We stored the code on GitHub with a list of dependencies. Should we do anything else regarding stochastic operations for reproducibility?
What was checked, without and with the skill
Checked
Without skill
With skill
Requires setting explicit random seeds for stochastic reproducibility.
Passed
Passed
Requires pinning software package versions.
Missed
Passed
case-09 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md94 linessingle file
Transparency & Data (commres-transparency-and-data)
CR is a quantitative, social-scientific journal, and its reviewers increasingly expect the materials
that let others scrutinize how the numbers were produced. SAGE supports a data-availability
statement and open-practices options; build the statement and supporting materials as you write
so submission and any open-practice claim go smoothly. Confirm the journal's current wording on the
SAGE author page (待核实 on exact policy).
When to trigger
Drafting the data-availability statement
Deciding whether to share data, code, and materials, or to preregister
Preparing a preregistration / pre-analysis plan for a prospective design (note it in the cover letter)
Data cannot be fully shared (privacy, ethics, platform/legal restrictions) and you need the path forward
What CR / SAGE expects (verify current wording on the policy page)
Data-availability statement. State where the data are (repository + identifier), under what
conditions they can be accessed, and — if they cannot be shared — why, with instructions for how
others might obtain them.
Open practices (where pursued).
Open data — data and a codebook deposited in a trusted repository with a persistent identifier.
Open materials — stimuli, instruments, scales, and code deposited so the study can be reproduced.
Preregistration — a time-stamped, registered design/analysis plan; note it in the cover letter.
Quantitative materials. Data, code, codebook, scale items, and documentation sufficient to
regenerate every reported result; master script + README + pinned versions + seeds.
ORCID and ethics. Provide ORCID where requested; state IRB/ethics approval and informed consent;
for content analysis, deposit the codebook and intercoder-reliability report.
When data cannot be shared (restricted-data path)
Explain why in the data-availability statement (ethical/privacy concerns, platform terms of
service, or legal restrictions by the provider).
Provide instructions on how others can obtain the data (access process, application, provider contact).
Where possible, provide synthetic or de-identified data so the code can be run.
Build-as-you-go checklist
Data-availability statement drafted (repository, identifier, access conditions, or exemption)
One master script regenerates every table and figure from raw/constructed data