✨ Add Vizzly agent project guidance#281
Merged
Merged
Conversation
Install the packaged Vizzly skill from init and optionally add project AGENTS.md guidance for agents using Vizzly visual context.
Vizzly - Visual Test ResultsCLI Reporter - Waiting for buildNo builds received yet for this pull request.
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR packages the Vizzly agent skill with the CLI and adds an opt-in
vizzly init --agent-guidancepath that sets up project-local agent context.The core idea is simple: agents cannot use what they do not know exists. Vizzly already has the good stuff agents need for UI work: approved baselines, screenshot history, diffs, review state, comments, dynamic regions, public screenshot URLs, and local TDD context. But unless that context is installed and named in the repo, models tend to reach for generic browser tooling or write tests at the wrong layer.
--agent-guidancemakes that setup explicit and project-scoped. It installs.agents/skills/vizzlyand adds a small marked section to the repoAGENTS.mdthat points agents toward Vizzly context and local visual TDD when they are working on user-facing UI.What Changed
skills/vizzlyskill to the npm artifact.vizzly init --agent-skillfor installing only the repo-local skill.vizzly init --agent-guidancefor installing the skill and updating projectAGENTS.md.Why This Matters
This should make Vizzly feel much more native to coding agents. Instead of treating visual testing as something the human has to remember to invoke, the project can teach the agent: check screenshot memory first, use existing user workflows, and capture visual evidence through Vizzly.
That is a big unlock for customers using Codex, OpenCode, Pi, or any harness that honors repo-local agent context. The CLI becomes the delivery mechanism for the right instructions, not just the screenshot runner.
Verification
Covered with focused init tests, relevant command tests, Biome, skill validation, a production build, a temp-project
init --agent-guidancesmoke test, and an npm pack check to confirm the skill ships in the artifact.