메뉴
Use when generating divergent concepts is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | generating-divergent-concepts |
| description | Use when generating divergent concepts is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent. |
| license | MIT |
| compatibility | ForgeOS-compatible Agent Skills hosts; no provider-specific model required. |
| metadata | {"author":"forgeos-community","version":"0.2.0","pack":"creativity","kind":"core","status":"stable"} |
This skill owns one bounded responsibility: generating divergent concepts. Its focus is produce mechanism-distinct concepts while delaying cross-agent anchoring and selection. It converts declared inputs into typed artifacts and reproducible evidence without silently changing product scope.
Activate only when the project is in one of these stages: divergence, synthesis, all contract preconditions pass, and the router identifies a missing output this skill can produce. Do not activate merely because the skill name resembles the user request.
creative-briefProduce or reference all applicable evidence:
idea genomeslens provenancesemantic clustersforbidden-pattern reportEvidence must identify the current artifact hash, command or method used, result, reviewer identity, timestamp, and limitations.
Produce:
candidate-ideasThe primary artifact must include schema version, provenance, consumed artifact IDs, decisions, evidence references, residual risks, validation state, and invalidation targets. Narrative explanation may accompany the artifact but cannot replace it.
Reviewer: independent-reviewer
Pass only when: All mandatory rules pass, evidence targets the current artifact hash, and no unresolved critical finding applies.
Stop and request a human decision when scope, risk acceptance, irreversible action, cost ceiling, privacy boundary, or product direction is materially ambiguous. When this artifact changes, invalidate only descendants named by the artifact graph; preserve unaffected verified branches.
candidate-ideas.contract-validation, independent-review, idea genomes, lens provenance, semantic clusters, forbidden-pattern report.artifactId, schemaVersion, sha256, producingSkill, producingAgent, consumedArtifacts, decisionIds, evidenceIds, residualRisks, validationState, invalidationTargets, stopCondition.Load at most 8 direct artifacts and reference depth 1. Use stable IDs, hashes, signatures, and deltas instead of repeating full history. Use established domain terminology, state each requirement once, and spend context on decisions, code, tests, or evidence rather than narration.
Load skills/references/core/creativity.md only when this skill needs pack-wide decision tables, evidence patterns, or cross-skill handoff rules.
See contract.json for the machine-readable contract.
Use when choosing system architecture is required during architecture work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
Use when decomposing bounded contexts is required during architecture work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
Use when defining domain model is required during architecture work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
Use when designing api contracts is required during architecture work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
Use when designing data migrations is required during architecture work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
Use when designing data model is required during architecture work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.