skills/ontology/SKILL.md
Use when you need to query, manage, or visualize the project-level ontology.
npx skillsauth add seokan-jeong/team-shinchan ontologyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Query, manage, and visualize the project's ontology.
/team-shinchan:ontology [subcommand] [args]
Display ontology summary with key metrics.
node ${CLAUDE_PLUGIN_ROOT}/src/ontology-engine.js summarySearch for entities by name or type.
/team-shinchan:ontology query Payment/team-shinchan:ontology query --type Componentnode ${CLAUDE_PLUGIN_ROOT}/src/ontology-engine.js query --name <term> or --type <type>Manually add an entity (for domain concepts, decisions, patterns).
/team-shinchan:ontology add DomainConcept "User Authentication"/team-shinchan:ontology add Decision "Use REST over GraphQL" --rationale "Simpler for our team size"Remove an entity and its relations.
/team-shinchan:ontology remove comp-a3f2Trigger a full re-scan of the project.
/team-shinchan:ontology scan/team-shinchan:ontology scan --module src/servicesLLM 구동 온톨로지 자동 스캔 — 코드베이스를 분석하여 새 엔티티를 제안.
/team-shinchan:ontology auto-scan --check — 발견된 엔티티 후보 리포트 (수정 없음)/team-shinchan:ontology auto-scan --write — 검토 후 ontology.json에 병합node ${CLAUDE_PLUGIN_ROOT}/src/ontology-engine.js auto-scan --check|--writebash ${CLAUDE_PLUGIN_ROOT}/scripts/ontology-check.sh — --check 모드로 차이 보고Regenerate kb-summary.md from ontology.
/team-shinchan:ontology gen-kbnode ${CLAUDE_PLUGIN_ROOT}/src/ontology-engine.js gen-kbGenerate a Mermaid diagram.
/team-shinchan:ontology diagram modules — Module dependency graph/team-shinchan:ontology diagram domain — Domain concept map/team-shinchan:ontology diagram entity <id> — Entity neighborhoodIf no ontology exists:
/team-shinchan:ontology scan or wait for next session start to auto-build."development
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, a completeness critic, and a schema-validated rubric judge. Opt-in main-loop Workflow tier.
data-ai
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
testing
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
development
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.