✨ Smooth agent visual workflows - #348
Merged
Merged
Conversation
Keep the Vizzly skill portable across Agent Skills-compatible harnesses and make explicit setup reruns refresh managed guidance safely. Close the dogfood gaps around repeated diff suggestions and missing hotspot analysis in human output.
The portable skill is better protected by its real installation and CLI workflow coverage than by assertions over static frontmatter and file names.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
The beta dogfood pass proved that an agent can get useful baseline, current, diff, and history evidence from the CLI. It also exposed a few rough edges before stable: human screenshot history could crash when hotspot analysis was unavailable, comparison drill-downs did not suggest raw diagnostics, and upgrading the CLI left previously installed skills stale.
Approach
The bundled Vizzly skill now follows the vendor-neutral Agent Skills format from top to bottom. The core instructions stay short, detailed workflows load through focused references, and the package no longer carries an OpenAI-specific descriptor.
Explicit agent setup reruns now refresh the packaged skill and Vizzly-owned AGENTS.md block while preserving unrelated project guidance and extra skill files. Incomplete managed markers are reported without rewriting user content. Build and comparison suggestions also stop recommending raw diffs after those details are already present, and human screenshot output treats missing hotspot analysis as unavailable.
Evidence
The complete CLI test suite passes, including boundary coverage for managed refresh behavior, source-pinned drill-downs, and the null hotspot response observed during dogfooding. Repository-wide lint and the production build pass. A clean-project run through the built binary installs and then refreshes the skill without replacing the existing config, and the package dry run contains the core skill plus all four references with no vendor-specific metadata.