菜单
Validates a proposed implementation plan against DNA truth artifacts to catch conflicts before any code is written. Use after forming an approach but before beginning implementation. Checks contracts, constraints, and evaluations against each planned step.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Interactive conversation for deliberate truth changes. Acts as a truth guardian that searches DNA, surfaces conflicts, debates proposals, and only applies changes with explicit human reasoning. Use via text or voice mode in Claude Code.
Assembles DNA truth artifacts into a self-contained specification that an autonomous agent can execute against without further human guidance. Use when handing off a well-defined deliverable to an agent for extended autonomous execution.
Consults DNA truth artifacts during task planning to understand system identity before designing an implementation approach. Use at the start of any non-trivial task before choosing an architecture or decomposing work into steps. Searches for intents, contracts, and constraints that shape the solution space.
Creates escalation artifacts that define when an agent should stop autonomous work and involve a human. Use when encoding decision boundaries for agent autonomy -- the guard rails on what agents can decide alone.
Creates tradeoff artifacts that encode which concern wins when competing concerns clash. Use when two valid goals, constraints, or intents conflict and agents need to know which to prioritize.
Stores truth artifacts in DNA with correct kind, format, metadata, and semantic context. Use when codifying decisions, contracts, intents, or constraints that should persist across code changes, team transitions, and framework evolutions.
| name | validating-approach |
| description | Validates a proposed implementation plan against DNA truth artifacts to catch conflicts before any code is written. Use after forming an approach but before beginning implementation. Checks contracts, constraints, and evaluations against each planned step. |
You have a plan. Before executing it, verify each step against stored truth.
dna search "<component or interface this step touches>" --kind contract
If a contract governs the component, verify:
dna search "<the technique or pattern this step uses>" --kind constraint
If a constraint applies, verify:
dna search "<what this step is building>" --kind evaluation
If evaluations exist, they define what "correct" means. Your implementation must satisfy them.
dna search "<any computation this step involves>" --kind algorithm
If an algorithm artifact exists, the implementation must match its logic. Do not invent alternative formulas.
dna search "<competing concerns in this step>" --kind tradeoff
If two concerns in the plan conflict (e.g., latency vs correctness), verify a tradeoff artifact resolves the conflict. If no tradeoff exists, surface the conflict before proceeding.
dna search "<what this step changes>" --kind escalation
If an escalation applies to this step, the plan must include a human checkpoint. Do not proceed autonomously past an escalation boundary.
If a step conflicts with stored truth:
Before proceeding to implementation, state: