AF expert2skill
专家方法沉淀器（meta-skill）— 通过引导式访谈，把一个"具备专业技术/知识但不懂 AI" 的专家（如营养师、验房师、投资顾问、设备工程师）的隐性方法，蒸馏成结构化规则库 （rule_library JSON）+ 可运行 skill 包。 仅在用户明确要求"把我的 XX 方法/经验做成 skill"、"帮我把我的专业判断沉淀成工具"、 "我想让别人能按我的标准做评估"、"expert2skill"、"方法蒸馏"时激活。 普通对话中提及"skill/方法"等词不自动触发。 核心能力： 1. 适配性判断（P0）— 5 问内判断方法是否适合规则引擎，不适合诚实告知转咨询型。 2. 引导式访谈（P1-P5）— 领域定义 → 维度拆解 → 逐项蒸馏 → 条件/开放/自问题 → 权重汇总。 3. 生成（P6-P7）— 产出 rule_library JSON（v2 schema）+ 纯本地 skill 包，含合规自检与免责声明。 关键原则：专家只说业务语言，AI 负责翻译到 schema；AI 永不替专家做判断； 开放题永不自动判分；不可规则化部分诚实标记。 locale: zh-CN
专家方法沉淀器（meta-skill）— 通过引导式访谈，把一个"具备专业技术/知识但不懂 AI" 的专家（如营养师、验房师、投资顾问、设备工程师）的隐性方法，蒸馏成结构化规则库 （rulelibrary JSON）+ 可运行 skill 包。 仅在用户明确要求"把我的 XX 方法/经验做成…
As a process F 33/100 · Will not run — References files that are not bundled: scripts/{slug}.py
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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: 11. 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
missing-refreference to a missing file: scripts/{slug}.py - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 33/100
- 0Tools and files. 1 referenced file(s) missing: scripts/{slug}.py
- 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
- 30Running it twice. 2 mutating operations with no state check
- 100Steps. 37 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1083 tokens
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 501: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.