AC llm-workflow-diagnoser
Use this skill whenever a user wants to evaluate whether an existing offline / reusable workflow is worth converting into an LLM-driven workflow. Triggers on phrases like "这个流程要不要交给大模型做", "我有个跑得很熟的脚本流程, 能不能用 LLM 改造", "我想把这套离线流程升级成 LLM 工作流", "判断一下现在流程合不合适交给大模型", "LLM 改造 ROI 诊断", "评估一下大模型介入的成本收益". Always trigger when the user describes a reusable workflow and wants a go / partial / no-go decision plus ROI reasoning, even if they don't ask for the words "diagnose" or "ROI" explicitly. Do not trigger for one-off prompts that are not a reusable workflow, and do not trigger for general writing / coding tasks.
Triggers on phrases like "这个流程要不要交给大模型做", "我有个跑得很熟的脚本流程, 能不能用 LLM 改造", "我想把这套离线流程升级成 LLM 工作流", "判断一下现在流程合不合适交给大模型", "LLM 改造 ROI 诊断", "评估一下大模型介入的成本收益".
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 59/100
- 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
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 45 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 977 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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
- +4No input/output examples
- -222 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 610: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 45 items
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.