AC guide-generator
Generates practical lifestyle guides (攻略) by researching recommendations on social media. Covers travel guides (weekend trips, long trips, road trips 自驾游, hiking 徒步, mountaineering 登山, city walks), sports guides (venues 场地, equipment 装备, beginner training), food guides (探店, local cuisine), shopping guides (malls, souvenirs, duty-free), and more. Searches Xiaohongshu, Zhihu, Mafengwo, Dianping, Bilibili plus official sources in parallel, cross-validates recommendations to filter out ads, and integrates findings into one medium-length concrete ready-to-use guide. Use when the user asks for 攻略 / 旅行攻略 / 美食攻略 / 购物攻略 / 运动攻略 / 自驾 / 徒步 / 登山 / 探店 / 装备推荐 / 行程规划 or similar requests.
Generates practical lifestyle guides (攻略) by researching recommendations on social media.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 52/100
- 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
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 753 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 680: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 47 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.