tiktest 
automated tiktok-style video review of every pr.
the more i shipped stuff with claude the more i realised; in the long term the most value i can add as a human is testing - finding the stuff other humans would struggle with...
...but testing is boring. so i tried to make it less boring - or at least take way less of my time.
play with sound to hear narration and watch normal speed
get it running in a few mins
two paths. both are paste-and-go — claude code does the wiring.
1. claude code plugin — record a walkthrough of whatever you just shipped, locally. type these slash commands yourself (claude can't invoke them from inside a prompt), one at a time:
/plugin marketplace add marcushyett/tik-test
/plugin install tiktest@tiktest
/reload-plugins
then paste this prompt so claude finishes the wiring:
The tik-test Claude Code plugin is now installed. Finish setting it up for this project:
1. Verify the plugin's runtime prereqs are present and fix what's missing for my OS:
- `ffmpeg` on PATH (`brew install ffmpeg` on macOS, `sudo apt install ffmpeg` on Linux)
- Playwright Chromium (`npx playwright install chromium`)
- `tik-test` CLI globally (`npm i -g tik-test`)
2. If a `tiktest.md` already exists at repo root, summarise it and ask me whether to keep, expand, or replace it before doing anything destructive. Otherwise run `/tiktest:setup` and ask me for anything you can't infer (project name, dev-server start command, login/auth flow, key user paths to record).
3. Tell me how to invoke `/tiktest:run` (full video, MP4 to Desktop) and `/tiktest:quick` (checklist only, no video) when I ship a feature, including the optional URL / focus-hint argument forms.
2. github action — cd into your repo, open claude code, paste:
Set up tik-test (https://github.com/marcushyett/tik-test — 45s video reviews on every PR) on this repo. Goal: working tik-test.yml + drafted tiktest.md + secret instructions, then test on a real PR.
1. Pick a template (local-dev / vercel-preview / staging-with-services) from inspecting package.json, framework configs, and deploy setup; ask if ambiguous. Create .github/workflows/tik-test.yml from it, adapted (build cmd, dev port, working-directory).
2. Draft tiktest.md at repo root: read README + package.json + 5-10 representative source files to infer flows; detect login (ask me for creds if there's a wall); list 3-5 highest-risk user-facing surfaces. Format: one-paragraph app description → login → "Risky surfaces" bullets → optional "Hints" with test-IDs. Show me the draft and wait for confirmation before committing. Warn if CLAUDE.md / AGENTS.md sit alongside it (silent-fallback footgun).
3. List the secrets I need to add: CLAUDE_CODE_OAUTH_TOKEN (`claude setup-token`, required) plus optionals you detect apply (OPENAI_API_KEY for narration; VERCEL_AUTOMATION_BYPASS_SECRET if Vercel Deployment Protection is on). One line each on where to get them. Mention that TIKTEST_OWNERS in repo Variables can restrict who triggers runs (default = any collaborator).
4. Open the PR. Heads-up: tik-test's plan generator looks at the diff and will skip cleanly with a "no testable change" comment when the only edits are workflow + tiktest.md (no impact on the UI). That's expected, not a failure — the action itself is wired up correctly.
5. After I merge it, propose a small visible UI change (one-screen nit from open issues or your own suggestion) to be the real first test PR. Wait for my okay, then ship on a separate branch.
prerequisites
| what | why |
|---|
| a web app with a public preview url | tik-test drives a real browser. vercel, netlify, render, ngrok-tunneled localhost — anything reachable. |
a tiktest.md at repo root (or ## TikTest in README.md) | tells the agent the url, login, and what's risky. |
| a claude code max subscription, OR an anthropic api key | tik-test invokes the claude cli directly so cost comes out of your subscription. oauth is what i use; api key works too. |
| ci permissions | contents: write, pull-requests: write, id-token: write. |
optional: OPENAI_API_KEY for voice narration, VERCEL_AUTOMATION_BYPASS_SECRET for protected previews.
telling tik-test how to test your app
drop a tiktest.md at your repo root. free-form prose, no schema:
# acme
acme is a project tracker for engineering teams.
