BD ai-building-ai-governance
AI 造 AI 治理与安全实操手册——面向"AI 自主开发与自我改进"前沿的治理框架：AI 造 AI 形态谱系（AI 编码智能体写代码、AI 训练 AI 之合成数据与蒸馏、AI 研究自动化、AI 自我改进与递归提升）、自主开发风险（能力获取、递归自我改进失控、目标错位、突然能力跃升）、开发门禁与边界治理（能力门槛、可逆性、监督红线）、合成数据与蒸馏的合规治理（质量验证、内容标识衔接、版权与训练数据溯源）、AI 产物验证（AI 生成代码/研究/模型的验证与红队衔接）、组织落地（AI 造 AI 工程治理、供应商评估、审计报告）。附零依赖本地工具一键判定形态、识别风险、生成治理检查清单与合成数据合规要点。面向 AI 工程、治理、安全与战略负责人，与 AI 治理/智能体治理/红队测试形成前沿延伸。
AI 造 AI 治理与安全实操手册——面向"AI 自主开发与自我改进"前沿的治理框架：AI 造 AI 形态谱系（AI 编码智能体写代码、AI 训练 AI 之合成数据与蒸馏、AI 研究自动化、AI…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 349 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "title" - note
frontmatter-keyunknown frontmatter key "description_en"
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 599 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 349: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.