Ready to supercharge your AI agents?

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

Get Started Free →

Knowledge Graph Management — measured AI agent skill | DecimalAI

a5c-ai/knowledge-graph-management

SkillScore36Maintained

Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph

by a5c-ai

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

Automatic

Knowledge Management pack

decimalai skills pull a5c-ai-knowledge-graph-management

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-knowledge-graph-management/SKILL.md

Raw file: /s/a5c-ai-knowledge-graph-management/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-knowledge-graph-management.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 9d ago

—-35% tokens0% turns36% of whole cases pass with skill (8/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-57%	0%
case-13	✗→✓	▲ Improved	-73%	0%
case-14	✗→✓	▲ Improved	-40%	0%
case-15	✗→✓	▲ Improved	-54%	0%
case-16	✗→✓	▲ Improved	-73%	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 — 7/31/2026

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

a5c-ai / babysitter

library/methodologies/maestro/skills/knowledge-graph-management/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

Knowledge Graph Management

Capabilities

Manages the .maestro/knowledge.dot knowledge graph. Captures architectural patterns and design decisions. Validates graph consistency. Queries for relevant patterns. Syncs graph with codebase reality. Exports to DOT format.

Tool Use Instructions

Use Read to load the knowledge graph file
Use Grep/Glob to find patterns referenced in the graph within the codebase
Use Write to export the updated knowledge graph
Use Edit to make targeted graph updates
Use Bash to generate DOT visualizations

Process Integration

Used in maestro-knowledge-graph.js (All operations)
Used in maestro-orchestrator.js (Post-merge update)
Used in maestro-development.js (Story completion capture)
Used in maestro-hotfix.js (Postmortem recording)
Used in maestro-maintenance.js (Knowledge sync)
Agent: Knowledge Curator
Operations: capture, validate, query, sync, full-cycle

Want to see if a5c-ai/knowledge-graph-management 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.