Testing & Agent Automation Skills

This skill should be used whenever work from an explicit checklist or plan is fanned out to multiple spawned agents (Workflow tool scripts or Task/Agent subagents). Trigger phrases include "run these through a workflow", "build from this atomic checklist", "spawn agents for these tasks", "make the agents follow the plan and not drift", "verify each item is actually done", and "use the harness". It binds every spawned agent to its EXACT checklist item verbatim (never from memory), forces a structured proof of completion, and runs an independent adversarial verifier that re-checks each item against its acceptance criteria with loop-back on failure. Use it to prevent agent drift, improvisation, and "done but not really done" outcomes.

Visible, supervised, human-mode browser co-working. PRIMARY browser = Playwright MCP run VISIBLY on your local machine (vision, keyboard, mouse, click, screenshot) for real-time round-trip work you watch: program → drive the browser → check → iterate. Logs in with your credentials when it can; on CAPTCHA/2FA it pauses and hands the keyboard to you in the same window, then continues. Use whenever a browser is involved — testing, verifying a deploy, a login/auth flow, admin tasks, automating a site, inspecting a page, or when you mention Playwright, browser automation, 'open a browser', 'click', 'login', 'check the page', 'verify the UI', 'visual test', or similar.

Compose and save a durable, wayback-grade session snapshot to UltraMemory. Use this whenever you are asked to write a session snapshot or rollup of the work just done — in particular when the UltraMemory capture hook nudges you to "Compose a session snapshot per the ultramemory-snapshot Skill rubric ... and save it with the UltraMemory memorywrite tool now". The snapshot is ONE rich card written with the UltraMemory memorywrite tool.