菜单
Queries DNA truth artifacts before modifying a specific file or component. Use before any code change to verify it does not conflict with established intents, contracts, or constraints. Lighter-weight than full plan validation -- operates at the individual change level.
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
| name | checking-truth |
| description | Queries DNA truth artifacts before modifying a specific file or component. Use before any code change to verify it does not conflict with established intents, contracts, or constraints. Lighter-weight than full plan validation -- operates at the individual change level. |
Before modifying code, check what truth governs this area.
dna search "<what you are about to change>" --limit 5
Review the results. If any artifact has a similarity score above 0.6, read it carefully. It likely governs what you are about to do.
If the change modifies an interface or API:
dna search "<the interface>" --kind contract
If the change modifies business logic or computations:
dna search "<the computation>" --kind algorithm
If the change touches a constrained area (security, performance, compliance):
dna search "<the area>" --kind constraint
dna search "<the area>" --kind compliance
| Score | Meaning | Action |
|---|---|---|
| > 0.8 | Directly relevant | Read and comply |
| 0.6 - 0.8 | Likely relevant | Read and assess |
| 0.4 - 0.6 | Possibly related | Skim for applicability |
| < 0.4 | Probably noise | Ignore |
Do not silently proceed. State the conflict:
If you are making a significant decision and no truth covers it, note this. After the change, consider capturing the decision. See capturing-artifacts.
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.