Ready to supercharge your AI agents?

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

Get Started Free →

template-advanced-literature-review — measured AI agent skill | DecimalAI

docxology/template-advanced-literature-review

SkillScore100Maintained

Multi-phase literature-review exemplar with phase-aware retrieval, filtering, provenance, and cross-phase 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-advanced-literature-review

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/docxology-template-advanced-literature-review/SKILL.md

Raw file: /s/docxology-template-advanced-literature-review/SKILL.md ↗ · machine-readable summary at /s/docxology-template-advanced-literature-review.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 6d ago

Yes — +64% lift-37% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-53%	0%
case-02	✗→✓	▲ Improved	-42%	0%
case-03	✗→✓	▲ Improved	-47%	0%
case-04	✗→✓	▲ Improved	-39%	0%
case-05	✗→✓	▲ Improved	-54%	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_advanced_literature_review/.agents/skills/template-advanced-literature-review/SKILL.md

View on GitHub ↗

License CC-BY-4.0Imported 8/1/2026Version v1

Skill contents

SKILL.md

template-advanced-literature-review

Load this project-scoped skill when working inside projects/templates/template_advanced_literature_review/ or forking it into a new phased literature-review pipeline.

When to Use

A review requires distinct query phases or methodological eras.
Papers must retain discovery-phase and cross-phase provenance.
Phase-specific deterministic or optional LLM filters need validation.

Quick Reference

bash
uv run python scripts/pipeline/stage_01_test.py --project templates/template_advanced_literature_review --project-only
uv run python scripts/pipeline/stage_02_analysis.py --project templates/template_advanced_literature_review
uv run python scripts/pipeline/stage_03_render.py --project templates/template_advanced_literature_review
uv run python scripts/pipeline/stage_04_validate.py --project templates/template_advanced_literature_review

Pitfalls

Stage 01 retrieval is live network work; the tracked corpus is an evidence snapshot.
Keep phase logic in src/multi_phase/ and numbered scripts thin.
Use real local HTTP servers in tests; never introduce mock frameworks.
Run stage 11 before stage 10 when adding full-text reproducibility evidence.

Want to see if docxology/template-advanced-literature-review 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.