Ready to supercharge your AI agents?

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

Get Started Free →

Instructions — measured AI agent skill | DecimalAI

docxology/Advanced Multi-Phase Literature Retrieval

SkillScore55Maintained

Operations for phase-aware federated retrieval across nine literature engines, preserving provenance from broad discovery through focused synthesis.

by docxology

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

Automatic

Research pack

decimalai skills pull docxology-advanced-multi-phase-literature-retrieval

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/docxology-advanced-multi-phase-literature-retrieval/SKILL.md

Raw file: /s/docxology-advanced-multi-phase-literature-retrieval/SKILL.md ↗ · machine-readable summary at /s/docxology-advanced-multi-phase-literature-retrieval.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

—-22% tokens0% turns55% of whole cases pass with skill (12/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-23%	0%
case-08	✗→✓	▲ Improved	-12%	0%
case-09	✗→✓	▲ Improved	-62%	0%
case-10	✗→✓	▲ Improved	-38%	0%
case-12	✗→✓	▲ Improved	-39%	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/src/literature/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v1

Skill contents

SKILL.md

Instructions

You are interacting with the src/literature/ module. This coordinates multi-source API harvesting across nine independently toggled engines, canonical-identifier deduplication, full-text resolution/extraction, unified bibliography export, and phase-aware synthesis.

Agentic Interface (MCP Strategy)

Federated Politeness: Ensure rigorous rate-limiting across provider networks. If writing tests for this package, absolutely enforce the "Zero-Mock" policy by orchestrating local pytest-httpserver fixtures rather than blinding the agent via mocker.patch.
Canonical Deduplication: The ecosystem is messy; always prioritize cross-referencing DOIs, arXiv IDs, and fuzzy-hashed title matches.
Taxonomy Enforcement: Categorization logic into the A (Theory), B (Tools), C (Application) tiers relies heavily on specific mathematical token matching. Update the keyword heuristics with precision.

Want to see if docxology/Advanced Multi-Phase Literature Retrieval 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.