Install
$ agentstack add skill-neuroanalytics-data-science-harness-status-report ✓ 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.
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: status-report
Turn the ledger into a readable report. project.yaml is the machine-actionable source of truth; this skill renders a PROJECT.md (or a funder/progress report) from it so people can read the project's state without parsing YAML. The report is generated, never hand-edited — edits go to the ledger via the owning skills. You delegate the ledger read and the save to the datalad doer.
> Distinct from the coordinator agent: the coordinator gives a fast interactive "where am I / what's > next" on load; status-report produces a durable, shareable written artifact (PROJECT.md / a funder > report) committed to the dataset.
When to use
- The user wants a written summary, a
PROJECT.md, or a progress/funder report. - Do NOT use to change project state — this only reads the ledger and renders it. To record a
decision use project/log-decision; to credit people use project/people.
Steps
- Read the ledger (datalad doer) — delegate: "read
project.yamland report itsproject,
products, obligations, contributors, and recent log entries." Optionally include datalad log highlights for the provenance section.
- Render the report — write
PROJECT.md(or the requested report path) with:
- Overview — study name/description, current stage (from the last log op), branch.
- Products — each product: kind, status, comparisons, outputs, DOIs, relations.
- Obligations — pending (highlight due/overdue), met, waived.
- People — contributors with CRediT roles + ORCIDs.
- Recent activity — the last several log entries.
Fill only from the ledger; mark anything absent (e.g. "no DOI — unreleased"), do not invent.
- Register + log — append
{ ts, op: status-report, stage: manage, note: "rendered ", branch: }. - Save — delegate to the datalad doer: "save:
datalad save -m 'status-report: render '." - Report — the report path and a one-line summary of project state.
Constraints
- Generated, not authored:
PROJECT.mdis rendered from the ledger and should not be hand-edited;
never write project state into the report that is not in the ledger.
- Render only what the ledger contains; mark gaps rather than filling them.
- Keep
log:append-only and the ledger schema-valid; delegate reads/saves 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.