BC ai-pm-workbench
【AI产品经理超级工作台 / AI PM Super Workbench】—— 面向AI产品经理的全栈智能工作台，覆盖12阶段、60+AI方法论框架、20+AI专业交付物。从模型选型到RAG架构、从Agent设计到安全护栏、从Prompt工程到商业化变现，一个Skill全覆盖。■ 12阶段：AI战略与机会识别→数据策略→模型选型→Prompt与上下文工程→RAG设计→Agent与多智能体→模型微调→AI UX→评测体系→安全护栏→AI可观测性→AI商业化→AI治理合规 ■ AI PM 3大角色谱系：AI Builder PM / AI Experience PM / AI-Enhanced PM ■ 技术全栈：LLM选型 | RAG 7大模式 | Agent 6大架构 | Prompt Engineering | Fine-tuning(SFT/RLHF/DPO) | AI评测 | AI安全 | LLMOps | AI UX 7大模式 | GenUI | AI数据飞轮 ■ 商业化：Token经济学 | 推理成本建模 | Build vs Buy vs Fine-tune | 基于结果的定价 ■ 治理合规：EU AI Act | 中国生成式AI管理办法 | 模型卡/系统卡 | 红队测试 ■ 触发词：AI产品经理、AI PM、大模型产品、LLM产品、RAG设计、Agent设计、Prompt工程、模型选型、AI评测、AI安全、AI商业化、AI治理、AI PRD、AI product manager、GenAI PM、agent architecture、model selection、AI evaluation、AI governance
【AI产品经理超级工作台 / AI PM Super Workbench】—— 面向AI产品经理的全栈智能工作台，覆盖12阶段、60+AI方法论框架、20+AI专业交付物。从模型选型到RAG架构、从Agent设计到安全护栏、从Prompt工程到商业化变现，一个Skill全覆盖。■…
As a process C 50/100 · Has gaps — 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 13321 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "contact" - note
frontmatter-keyunknown frontmatter key "language"
Process rating: all ten parameters 50/100
- 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
- 40Execution cost. Instruction body is 13321 tokens: crowds the task out of the window
- 100Tools and files. No external tools needed
- 100Steps. 83 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 39 top-level sections: this looks like several domains in one skill
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
- -2101 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 728: enough signal without eating the budget
- +4Structure: 196 headings
- +3Step-by-step instructions: 83 items
- +4Has examples (69 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.