一键导入
wiki-maintenance
Use when source-backed project knowledge needs to be created, refreshed, or corrected.
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。
菜单
Use when source-backed project knowledge needs to be created, refreshed, or corrected.
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 | wiki-maintenance |
| description | Use when source-backed project knowledge needs to be created, refreshed, or corrected. |
Lifecycle stage: LEARN
Use when ingesting sources, resolving contradictions, or preserving synthesis.
Do not use when this trigger is absent; choose the command or skill that owns the requested state, artifact, and verification gate.
| Shortcut | Rebuttal |
|---|---|
| "This is obvious." | Write the assumption and evidence. If you cannot, it is not obvious. |
| "We can do this later." | If the missing step changes the decision, do it now or state the risk. |
| "The user wants speed." | Reduce scope; do not skip the quality bar. |
| "This does not need verification." | Every important claim or behavior needs proof. |
Wiki Update
Use templates/wiki-update.md. The artifact should be concise, auditable, and include evidence, blockers, and next action so another agent can resume.
Trigger: source-backed project knowledge needs a durable update. Action: preserve provenance, confidence, freshness, and recheck triggers while updating only the relevant wiki section. Output artifact: templates/wiki-update.md with blockers and next action. Verification: cite changed paths, sources checked, stale claims rejected, and validation evidence.
A new source contradicts an existing project note. The skill should preserve both claims with provenance, mark freshness and confidence, update only the relevant wiki section, and record a recheck trigger instead of overwriting durable knowledge with unverified synthesis.
Agent Brain /brain-brief: after intake, research, and grill have enough signal.
Agent Brain /brain-build: an implementation plan has a selected task and validation method.
Agent Brain /brain-design: a product brief needs ux or interaction design before planning.
Agent Brain /brain-eval: changing Agent Brain behavior or checking quality.
Agent Brain /brain-grill: the idea, brief, design, or plan has unresolved assumptions.
Agent Brain /brain-learn: after repeated success/failure, a tricky fix, or a shipped workflow.