BC low-visibility-fix
Audit existing mobile UI (WeChat mini-program / H5 / app) for FIELD low-visibility conditions — low light, glare, gloves, wet hands, vibration — and emit a structured, implementer-ready handoff DOCUMENT SET (findings by severity + prioritized fix recommendations). Runs a deterministic analyzer plus a bounded visual/browser pass; scopes to specific page(s)/component(s) for cheap multi-round re-runs. NEVER edits the target — it hands documents to another agent to apply. Use when someone has an existing field/industrial UI and wants it checked for contrast, tap-target size, color-only state, or icon-only buttons, and wants a fix plan. Triggers: "审计这个界面在低光/眩光/戴手套下是否清晰可点， 给我修改建议文档", "audit this field UI and hand me a fix plan", "check only <page/component> for low-visibility issues", "$low-visibility-fix". Not for: editing/fixing the files directly (this skill produces docs, an implementer applies them); designing a new UI from scratch; disability/screen-reader a11y (colorblind, low-vision); generic CSS review with no low-visibility angle.
Audit existing mobile UI (WeChat mini-program / H5 / app) for FIELD low-visibility conditions — low light, glare, gloves, wet hands, vibration — and emit a…
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Shorten the description to 1024 characters.
- 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: 26. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1051 chars, limit 1024
Process rating: all ten parameters 50/100
- 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
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 877 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- +3Description length 1050: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -33 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 3 headings
- +3Step-by-step instructions: 6 items
- +4Reference files are cited in the instructions (4 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.