AI公司 Skill维护工作流(CTO 版本治理 + CISO 安全运营标准版)。在对已发布的 Skill 进行版本更新、bug 修复、功能增强、依赖升级、安全补丁或废弃管理时触发...
Micro-tier (XS) LLM agent governance skill for organizations of 1-3 agents: 18 enterprise function blocks consolidated into 2 departments, backed by shared harness templates, a full error-code catalog, and propose-only self-scaling.
Source files are authored in English; runtime output follows the user's language (see
language_policyin the frontmatter). Slugs, error codes, field names, enum values, file paths, and function names are never translated.
SlugPrefixScopeReferencegovernance-and-delivery``CEO_Strategy, governance, deliverygovernance-and-delivery.mdengineering-and-safety``CTO_Architecture, engineering, safetyengineering-and-safety.md
ResourceContentsmethod-patterns.mdSingle source of truth for the ten shared code templates and the CRISPE / 3WEH / Five-Element prompt frameworkserror-codes.mdFull four-element error-code catalog (code, message, trigger, resolution) for all prefixesscaling.mdTier thresholds, upgrade gating, and alias mapping for self-scaling
PrefixMeaningCEO_Governance-and-delivery department codesCTO_Engineering-and-safety department codesSCL_Self-scaling infrastructure codes (fixed across tiers)
FileModePurpose01-implement-method.mdhuman-pastePaste into any AI chat window to have that AI implement one method to this standard02-robustness-checks.mdhuman-pastePaste into any AI chat window to have that AI run robustness checks on a method
task (required) and optionally department ( auto routes automatically); set output_language to override the runtime output language.<placeholders>, and paste the prompt into any AI chat window.