Ready to supercharge your AI agents?

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

Knowledge Graph Builder — measured AI agent skill | DecimalAI

stijnman/knowledge-graph-builder

SkillScore91Maintained

Builds structured knowledge graphs from text and sessions. Use when organizi ngentities and relations or user says knowledge graph, map entities. Trigger s:knowledge graph, map entities, build graph, entity map.

by stijnman

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

Automatic

Knowledge Management pack

decimalai skills pull stijnman-knowledge-graph-builder

Get this skill — curl · raw file

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

Raw file: /s/stijnman-knowledge-graph-builder/SKILL.md ↗ · machine-readable summary at /s/stijnman-knowledge-graph-builder.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

Yes — +50% lift-34% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-52%	0%
case-05	✗→✓	▲ Improved	-61%	0%
case-08	✗→✓	▲ Improved	-52%	0%
case-09	✗→✓	▲ Improved	-38%	0%
case-11	✗→✓	▲ Improved	106%	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

stijnman / grok-custom-skills

.grok/skills/knowledge-graph-builder/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Knowledge Graph Builder

When to Use

User says knowledge graph or task matches this capability
User says map entities or task matches this capability
User says build graph or task matches this capability
User says entity map or task matches this capability

Workflow

Extract entities: people, tools, projects, concepts.
Define relations: uses, depends_on, blocks, produces.
Output JSON graph or mermaid diagram.
Store index in semantic-memory-manager.

Integrations

semantic-memory-manager
insight-synthesizer
self-healing-error-recovery

Error Handling

| Failure | Response | |---------|----------| | Too many entities | Cluster; show top 20 with expand option. |

Gotchas

Graphs are hypotheses; mark unverified edges.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/knowledge-graph-builder 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.