원클릭으로
designing-cybernetic-solutions
Use when an existing v1 control chain requires design.control.json; v2 strategies remain agent-owned.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when an existing v1 control chain requires design.control.json; v2 strategies remain agent-owned.
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
Use when a formed task needs durable human-approved meaning, completion obligations, evidence claims, non-goals, or live/destructive authority boundaries.
Use when maintaining or resuming an existing v1 requirements.control.json run; new runs use forming-cybernetic-commitments.
Use when an existing v1 run must compile its reviewed control chain into runtime.control.json.
Use when optional local workflow guidance or legacy v1 workflow compatibility needs diagnosis.
Use when cybernetic routing is requested but user input is pre-task intent or role-ambiguous context: confusion, dissatisfaction, risk sense, observed symptoms, failed attempts, method preference, process distrust, source material, declared current state, or unclear requested transformation.
Use when resuming an existing v1 run that already requires pre-goal control-chain compilation.
| name | designing-cybernetic-solutions |
| description | Use when an existing v1 control chain requires design.control.json; v2 strategies remain agent-owned. |
Legacy v1 control-artifact compatibility only. V2 may design internally without turning design into an approved artifact.
Create the solution model needed between approved requirements and goal writing.
This skill owns design strategy, not requirement meaning, execution policy, review, runtime compilation, or target execution.
Official persistent control facts are JSON only. Historical Markdown may be read as background, but must not become official control input.
Detailed rules live in references/solution-design-detailed-rules.md.
Use references/design-check.md for the design trigger rubric.
requirements.control.json.What the User Approved is Approved when controlled_run work is
involved.controlled_run with schema 1.1.0+, confirm
approved_control.information_sufficiency_check is satisfied or reviewed
not_required, has run-local evidence_ref values, and has approved
independent counterexample_review; otherwise route to
RunInformationSufficiencyCheck.design.control.json only for the model needed downstream.The design artifact should include:
If requirements say how the task must be answered, design must preserve that answer path. It must not replace required implementation, measurement, repair, or diagnosis with a framework, readiness, compatibility, or classification-only answer because that is easier.
Output the design path and status:
Created or updated design:
`docs/cybernetics/runs/<slug>/design.control.json`
Design status:
- `approved` / `candidate` / `blocked`
Key design decisions:
- ...
Open questions:
- ...
Response-only next step:
- return to `$orchestrating-cybernetic-pregoal`; include `允许使用 subagent 执行 review。`, or
- if manual fallback is being used, continue to `$writing-cybernetic-goals`.
Do not write runtime /goal prompts or target-work commands into the design
artifact.