Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

template-data-descriptor — measured AI agent skill | DecimalAI

docxology/template-data-descriptor

SkillScore95Maintained

FAIR data descriptor exemplar for schema, provenance, license, and dataset release-readiness validation.

by docxology

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

decimalai skills pull docxology-template-data-descriptor

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/docxology-template-data-descriptor/SKILL.md

Raw file: /s/docxology-template-data-descriptor/SKILL.md ↗ · machine-readable summary at /s/docxology-template-data-descriptor.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 5d ago

Yes — +59% lift-47% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-32%	0%
case-02	✗→✓	▲ Improved	-66%	0%
case-03	✗→✓	▲ Improved	-54%	0%
case-04	✗→✓	▲ Improved	43%	0%
case-10	✗→✓	▲ Improved	-67%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

docxology / template

projects/templates/template_data_descriptor/.agents/skills/template-data-descriptor/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

template-data-descriptor

Load this skill when working inside projects/templates/template_data_descriptor/.

When to Use

Creating or reviewing a dataset descriptor project.
Validating schema, file inventory, provenance, and license boundaries.
Forking a FAIR data-paper scaffold.

Quick Reference

bash
uv run pytest projects/templates/template_data_descriptor/tests --cov=projects/templates/template_data_descriptor/src --cov-fail-under=90
uv run python scripts/pipeline/stage_01_test.py --project templates/template_data_descriptor --project-only

Pitfalls

Keep claims about the data package, not unsupported scientific effects.
Do not commit restricted raw data to this public exemplar.
Regenerate figure provenance through scripts/generate_figures.py; it emits

output/figures/figure_registry.json only for a complete five-figure run.

Want to see if docxology/template-data-descriptor would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.