Run a Meticulous test run after implementing a frontend change, then hand off to the `meticulous-review` skill to classify each visual change as intended or…
To test a frontend change using Meticulous, follow the workflow below step by step, using the CLI commands as described.
Before starting, run the meticulous-cli-update skill to ensure the Meticulous CLI is up to date — unless it has already run earlier in this conversation, in which case skip it.
If you are already given a test run id, skip to Step 4.
Step 1 -- Build the frontend
Find out what build artefact Meticulous expects by checking .github/workflows/ for one of the following steps:
uses: alwaysmeticulous/report-diffs-action/upload-assets@v1 — build assets
uses: alwaysmeticulous/report-diffs-action/upload-container@v1 — docker image
Build the frontend following the same instructions as used in the GitHub workflow.
Step 2 -- Upload the build
Register the build as a reusable deployment with agent upload-build. This uploads the artefact and prints a deploymentId to stdout — it does not trigger a run yet.
related skills
semantically similar in the cross-vendor index
don't have the plugin yet? install it then click "run inline in claude" again.
+procedure includes explicit conditionals (meticulous-cli-update skip logic, test run id shortcut) showing awareness of state
+references actual cli commands (agent upload-build, agent test-run) grounded in real tooling
+step sequence is logical: build, upload, trigger, handoff
weaknesses
~vague artifact discovery step (check .github/workflows, find one of two patterns) lacks fallback or error handling if neither is found
~skips steps 3 and 4 entirely in the provided text, leaving procedure incomplete and handoff to meticulous-review unexplained
~no edge cases documented: upload failures, build failures, network timeouts, cli version incompatibility all absent