BD 12306-android-adb
Book train tickets on the 12306 Android app via USB ADB. Battle-tested 2026-08-30 (two successful bookings: G3314 上海→苏州 and D203 上海松江→杭州南). Primary method: direct uiautomator2 + RapidOCR via ocr_bridge.py (see appium-android-adb skill). Covers the UC WebView virtual-list traps, the card-expand UI, departure-station filter (一车多站 time disorder), scroll-unsticking, clipboard Chinese input, and 车票信息已过期 (M0013) recovery.
Book train tickets on the 12306 Android app via USB ADB.
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Book train tickets on the 12306 Android app via USB ADB. Battle-te… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 47/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 46 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2520 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 419: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 46 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.