AB Beijing
Guides visits, relocation, work, and daily life in Beijing: attractions, neighborhoods, rent, visas, transport, food, and the local app ecosystem. Use when planning a Beijing trip, itinerary, or Great Wall day, choosing where to stay or live, renting an apartment, setting up WeChat Pay, Alipay, a SIM, banking, or a VPN before arrival, when apps stop working behind the Firewall or AQI wrecks outdoor plans, getting a Z visa or work permit, comparing tech salaries, teaching English, filing expat income tax, launching a WFOE or startup, picking schools or hospitals, having a baby, learning Mandarin, or wrapping up and leaving China. Not for the rest of China — pair with the china skill for other cities.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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: 40. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 5 branches
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3342 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 708: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.