Install
$ agentstack add skill-neuroanalytics-data-science-harness-datalad-status ✓ 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: datalad-status
Inspect the current state of a DataLad dataset — what files are modified, untracked, added, or deleted — without making any changes.
Steps
- Verify DataLad context — check for
.datalad/in the current directory or any
parent: ``bash ls .datalad/ 2>/dev/null || git rev-parse --show-toplevel ``
- Dataset found: continue.
- No dataset found: inform the user and suggest
/datalad-initor plaingit status.
- Run
datalad status— optionally scoped to paths from$ARGUMENTS:
``bash datalad status [paths...] `` Present the full output to the user. Additional flags to mention if relevant:
--annex— shows verbose annex content state (number of copies, remote presence)
for each annexed file; useful for understanding data availability
--untracked=no— suppresses untracked files from output (useful in large repos
with many untracked directories that would otherwise clutter the output)
- Interpret the status symbols — explain each symbol present in the output:
| Symbol | Meaning | |--------|---------| | modified | Content changed since last save | | untracked | File exists on disk but is not recorded in the dataset | | deleted | File was tracked but is now missing from disk | | added | New file staged but not yet saved | | clean | No changes — working tree matches the last commit |
For annexed files, also explain:
- content present: file pointer exists and content is available locally
- content missing: file pointer exists but content was dropped (pointer only)
- Suggest next actions — based on what was found:
- Modified or untracked files → suggest
/datalad-save - Missing annex content → suggest
datalad getto retrieve it - Output files that should have been produced by a command → suggest
/datalad-run - Clean working tree → confirm no action needed
Constraints
- Read-only — never run any command that modifies the dataset, stages files, or commits.
- Always explain every status symbol that appears in the output — never show raw output
without interpretation.
- If the user asks about a specific path, scope the status command to that path.
- Do not confuse
datalad status(dataset state) withgit status— they overlap but
DataLad status correctly handles annexed files that git would misreport.
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.