BC Bangkok
Plans Bangkok trips, relocations, and nomad stays: neighborhoods, visas, costs, transport, street food, and Thai law. Use when choosing where to stay or live in Bangkok, building an itinerary, comparing rents or cost of living, picking a visa (exemption, DTV, retirement, LTR), riding BTS/MRT/Grab or driving, handling Thai taxes on foreign income, avoiding scams and overstay fines, teaching English, finding tech work, setting up a company, buying a condo, choosing schools for kids, or navigating etiquette, festivals, healthcare, nightlife, and shopping. Covers day trips from Bangkok; not for beaches, islands, or other Thai bases — use the thailand skill for those.
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 1
-
high Concealment
en-hide-from-usernightlife.md:42Instruction to hide actions from the user- **Fill times**: bars 9-10 PM, clubs 11 PM-midnight. Official close 2 AM in entertainment zones, earlier elsewhere — some venues quietly run later.
Files scanned: 42. 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 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 4280 tokens
- 100Steps. 69 steps
- 100Consistency. Name and required fields are in place
- 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 671: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 69 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.