Ready to supercharge your AI agents?

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

Get Started Free →

Kragen Knowledge Graph — measured AI agent skill | DecimalAI

Kragen Knowledge Graph

SkillScore86Maintained

kragen-knowledge-graph

Graph-RAG Solver

AI/MLby FreedomIntelligence

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

Automatic

AI Engineer pack

decimalai skills pull kragen-knowledge-graph

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/kragen-knowledge-graph/SKILL.md

Raw file: /s/kragen-knowledge-graph/SKILL.md ↗ · machine-readable summary at /s/kragen-knowledge-graph.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 7d ago

—-22% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-42%	0%
case-05	✗→✓	▲ Improved	19%	0%
case-06	✗→✓	▲ Improved	37%	0%
case-07	✗→✓	▲ Improved	-30%	0%
case-08	✗→✓	▲ Improved	-60%	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

FreedomIntelligence / OpenClaw-Medical-Skills

skills/kragen-knowledge-graph/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v2

Skill contents

SKILL.md

<!--

COPYRIGHT NOTICE

This file is part of the "Universal Biomedical Skills" project.

Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>

All Rights Reserved.

#

This code is proprietary and confidential.

Unauthorized copying of this file, via any medium is strictly prohibited.

#

Provenance: Authenticated by MD BABU MIA

-->

KRAGEN (Knowledge Graph Enhanced RAG)

A knowledge graph-enhanced Retrieval-Augmented Generation system for biomedical problem solving, using Graph-of-Thoughts (GoT) reasoning.

When to Use

Complex Reasoning: Questions requiring multi-hop deduction (e.g., "How does gene A influence disease B via protein C?").
Hypothesis Verification: Checking if a proposed mechanism is supported by existing knowledge graphs.
Literature Synthesis: Combining facts from structured DBs and unstructured text.

Core Capabilities

Graph Retrieval: Query biomedical knowledge graphs (e.g., PrimeKG, SPOKE).
Graph-of-Thoughts: structured reasoning over retrieved nodes.
Vector DB Integration: Combines graph data with vector embeddings for hybrid search.

Workflow

Input: Natural language question.
Retrieval: Fetch relevant sub-graph and similar text chunks.
Reasoning: LLM traverses the graph to find connecting paths.
Answer: Generate response with citation of graph nodes.

Example Usage

User: "Explain the mechanism connecting BRCA1 mutations to ovarian cancer."

Agent Action:

bash
python -m kragen.solve --question "BRCA1 mutations to ovarian cancer mechanism"

Want to see if kragen-knowledge-graph 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.