Reporting Checklist
>
Install
$ agentstack add skill-neuroanalytics-data-science-harness-reporting-checklist ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-neuroanalytics-data-science-harness-reporting-checklist) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Skill: reporting-checklist
Attach the correct reporting guideline to a manuscript and work through it item by item, so the paper meets the standard its study type requires and the checklist ships with submission. This is completeness Metadata — a machine-and-reviewer-checkable record of what the paper reports. You delegate the save to the datalad doer.
Load plugins/disseminate/references/equator-guidelines.md to pick the right guideline before starting.
When to use
- A manuscript product exists (
disseminate/draft-manuscript) and needs a reporting-guideline pass,
typically before submission.
- Do NOT use to write the manuscript (
draft-manuscript) or to release/cite it (dataset-release).
Steps
- Pick the guideline — from the study design (see the reference): RCT → CONSORT;
observational → STROBE; systematic review/meta-analysis → PRISMA; animal research → ARRIVE; neuroimaging methods reporting → COBIDAS. Confirm with the author if ambiguous.
- Instantiate the checklist — write
manuscript/checklists/.mdwith each item and a
status (reported: | not-applicable: | TODO). Pre-fill items the harness can evidence from the manuscript + ledger (e.g. data-availability, provenance, registration/ pre-registration from obligations[]); leave the rest TODO for the author.
- Register + log — add the checklist path to the product's
outputs[]; append
{ ts, op: reporting-checklist, stage: disseminate, note: " checklist for ", branch: }.
- Save — delegate to the datalad doer: "save:
datalad save -m 'reporting-checklist: for '." - Report — the guideline chosen, how many items are satisfied vs.
TODO, and the gaps the
author must close before submission (e.g. a missing pre-registration → govern/preregister).
Constraints
- Choose the guideline by study design, not convenience; when in doubt, ask.
- Mark an item
reportedonly with a real section/page pointer — never claim compliance you cannot
evidence; unknowns stay TODO.
- Record the checklist under the product's
outputs[]; keeplog:append-only and the ledger
schema-valid. Delegate the save to the datalad doer.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: neuroanalytics
- Source: neuroanalytics/data-science-harness
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.