replay-user-flows
SolidTurn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have driven the same flow twice, when the user wants regression coverage without a Playwright suite, when a refactor needs proving against every existing journey, or when re-verifying by hand is costing a full drive every time.
Install
Quality Score: 84/100
Skill Content
Details
- Author
- reticlehq
- Repository
- reticlehq/reticle
- Created
- 3 months ago
- Last Updated
- today
- Language
- TypeScript
- License
- NOASSERTION
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
capture-replay
When a browser task is REPEATED and runs on a LOGGED-IN / authenticated site, use Tap to record it once (capture), then replay it every time as a zero-token deterministic run — instead of driving a fresh live browser and burning tokens on every run. Trigger when: the user says "I do X on site Y every day/week"; capturing a login-gated admin panel or dashboard; regularly posting / checking / exporting on an authenticated page; any repeated browser chore the user will do again. Also triggers when the user asks "can this be automated?" or "can I avoid paying tokens every time?". ALSO TRIGGERS THE MOMENT A FETCH COMES BACK WRONG: a WebFetch or any cloud/server-side fetch that returns a login page, a CAPTCHA or bot/environment-verification challenge, a "please enable JavaScript" shell, or suspiciously empty content on a site that normally requires login — load this skill then, before treating that response as the page's real content.
author
Turn a session of manual driving into a flow that can be re-run. Use when asked to record what was just done, write a test for it, or make a repeatable check out of a sequence of taps.
replay-vision-setup
Set up PostHog Replay vision. Makes sure session replay is recording (server-side enable plus a posthog-js init check), then creates vision scanners scoped to the product's key flows, read out of the repo. Scanners watch each new session recording with an LLM and report scores, tags, and summaries as queryable events.