framework_eng/skills/tool-usage/browser-ui/visual-check/SKILL.md
MUST use WHEN a 1C form is created or modified and requires acceptance by the UI checklist. Provides a screenshot via the web client, checks JS errors in the console, and analyzes against form-visual-requirements.
npx skillsauth add steelmorgan/1c-agent-based-dev-framework visual-checkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A 1C web client URL (published infobase) and credentials are required.
Prefer Deep Linking - it is faster than navigating through the interface.
<base_url>/e1cib/list/<MetadataType>.<Name><base_url>/e1cib/data/<MetadataType>.<Name>?ref=00000000-0000-0000-0000-000000000000<base_url>/e1cib/data/<MetadataType>.<Name>?ref=<UUID>browser_snapshot → browser_fill (login/password from ref) → browser_click (Log in).
After loading (wait for the indicator to disappear):
browser_take_screenshotbrowser_console_messages — look for "Error", "Exception", "Uncaught"form-visual-requirementsReport: screenshot analysis result + presence/absence of JS errors.
| Capability | Purpose |
|------------|---------|
| browser_navigate | Open the form URL |
| browser_snapshot | Page structure and element refs |
| browser_fill | Fill in fields |
| browser_click | Click elements |
| browser_take_screenshot | Capture the form |
| browser_console_messages | Check for JS errors |
| browser_wait_for | Wait for loading |
| Error | Workaround |
|--------|------------|
| Blank screenshot | browser_wait_for before the screenshot |
| Deep Link does not work for a new object | List → "Create" via browser_click |
| browser_fill cannot find the field | browser_snapshot for current refs |
| JS errors on a normal form | Record it - they will surface on save |
depends_on:
testing
MUST use BEFORE making a judgment about the cause of a conflict, a test failure, or an artifact dispute. Defines the end-to-end verification method L1→L6 and the classification of the first broken link.
development
MUST use AFTER a work cycle with ≥2 iterations (wrote → error → fixed → success). Provides the retrospective procedure and the format for recording practice/anti-patterns in references/learned-patterns.md or {project}/.context/learned-patterns.md.
tools
MUST use WHEN you are writing reusable knowledge into RLM (pattern / architectural decision / stable domain fact) OR reading it before a non-trivial task/solution in the domain. Provides the breakdown of native-push vs RLM-pull, tools for writing and reading RLM, H-MEM levels, and hygiene.
testing
MUST use WHEN the task is classified as simple (< 20 lines, 1 file, no new metadata objects, no architectural decisions). Provides a short cycle of 3 steps with a guard on the self path and mandatory verify.