菜单
Registers and organizes label keys in DNA. Use when adding new metadata dimensions for filtering artifacts, or when setting up a new project with custom label keys.
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 | managing-labels |
| description | Registers and organizes label keys in DNA. Use when adding new metadata dimensions for filtering artifacts, or when setting up a new project with custom label keys. |
Labels are key-value pairs attached to artifacts for filtering and organization. Unlike free-form tags, label keys must be registered before use. This ensures consistency across a project and prevents typos from fragmenting your label space.
dna label list
To see the full project context -- all registered kinds and labels together:
dna context
dna label add <key> "<description>"
The key must be:
The description should explain what this label represents and give example values.
dna label add domain \
"Domain or bounded context the artifact belongs to. Ex: auth, billing, orders, onboarding"
dna label add regulation \
"Regulatory framework that requires this artifact. Ex: gdpr, hipaa, pci-dss, soc2"
dna label add priority \
"Relative importance of the artifact. Values: high, medium, low"
dna label add provider \
"External service provider name. Ex: stripe, sendgrid, google-maps"
dna label show <key>
dna label remove <key>
Removing a label key does not strip the label from existing artifacts. Those labels remain on the artifacts but are no longer part of the registered set.
Create a new label when:
--label key=value in dna list or dna search queriesDo NOT create a new label when:
--context (free-form semantic content)Labels are for exact-match filtering: dna list --label domain=auth.
Context is for semantic similarity: --context "Part of the auth system, relates to GDPR".
Use both together for best results. Labels narrow the search space; context improves relevance ranking.