بنقرة واحدة
screenshots
Test a page in the browser against accessibility standards.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Test a page in the browser against accessibility standards.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Fetch a Jira ticket's details (summary, description, acceptance criteria, testing notes) by ticket ID. Use whenever another skill or task needs to read a Jira ticket.
Create a new page and associated files by parsing a prototype page
Test a page in the browser against accessibility standards.
Conventions and file structure for quote journey pages in nrf-frontend. Read before creating or modifying any page under frontend/src/server/quote/. Covers the standard file structure (routes, get-view-model, form-validation, get-next-page), quoteController / quotePostController wiring, PRG validation flow, Nunjucks template conventions, Joi rules per input type, session cache helpers, and page/accessibility test patterns.
Fetch a Confluence page's details (title, space, version, labels, body HTML) by page ID or URL. Use whenever another skill or task needs to read a Confluence page.
Reviews changed code against team coding standards. Use after writing code in a nrf-* repository
| name | screenshots |
| description | Test a page in the browser against accessibility standards. |
| tools | Bash, Read, mcp__playwright__browser_navigate, mcp__playwright__browser_navigate_back, mcp__playwright__browser_snapshot, mcp__playwright__browser_evaluate, mcp__playwright__browser_run_code_unsafe, mcp__playwright__browser_click, mcp__playwright__browser_type, mcp__playwright__browser_fill_form, mcp__playwright__browser_press_key, mcp__playwright__browser_wait_for, mcp__playwright__browser_close, mcp__playwright__browser_console_messages, mcp__playwright__browser_network_requests |
This skill captures screenshots of all pages in a user journey by automatically walking through the user flow and taking screenshots of each page.
args is a path to a journeys markdown file (by default look in docs/user-journeys folder), or a single URL to a page to test.
Each numbered step within a journey is a separate page.
For each page, if there are specified sub-steps then execute each step. After the last step, continue to the next page. If a page has "- skip" then just click through it and don't take a screenshot.
Setup: when testing deployed environments (e.g.
*.cdp-int.defra.cloud), add a real-browser--user-agentto your Playwright MCP server args in~/.claude.json— otherwise the bot filter serves blank pages to Playwright's headless UA. Seetest-in-browser/SKILL.mdfor the exact value.
args.mcp__playwright__browser_navigate.mcp__playwright__browser_snapshot.mcp__playwright__browser_close.If a sub-step can't be performed or a page doesn't load, record the failure and stop that journey — do not retry silently. Report the exact error. Continue with the next journey.
Use keyboard-based drawing, not mouse clicks on the canvas (mouse events don't reliably register with the MapLibre GL draw library).
To draw a triangle:
aria-disabled removed. If not, add extra points (alternating ArrowLeft/ArrowUp, 20 presses each) until it enables.Session integrity: Always navigate through the full form flow from the start page in one continuous session. Never clear cookies mid-session — this invalidates the CSRF token and causes the boundary validation endpoint (/quote/draw-boundary/check) to return 403.
Use mcp__playwright__browser_run_code_unsafe for map interactions so the full Playwright API (keyboard, waitFor, etc.) is available in a single session context.
.png screenshots should be saved to 'docs/user-journeys/screenshots/'. For a given run of this skill, create a new subfolder named yyyy-mm-dd-. The screenshots should be named 01-page-name.png, and the number incremented for each page.