Repository navigation
docs(starter): streamline authoring and browser workflows - #29
Merged
lukasoppermann merged 1 commit intoOct 19, 2026
Merged
Conversation
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 1b58255f-30de-4528-8072-7441ea94f202
lukasoppermann
deleted the
lukasoppermann-upstream-workflow-improvements
branch
October 19, 2026 12:37
There was a problem hiding this comment.
🔵 Needs a closer look
The revised context and validation requirements need reconciliation with existing guidance and final human review.
5 open issues
Include measurement and evidence limits in section-scoped reads · New Align recovery guidance with the schema-reuse contract · New Include shared packages, data, and exceptions guidance · New Explicitly terminate the normal workflow in the narrow branch · New Preserve applicable repository constraints in narrow reads · New
What changed in this PR
Streamlines the copied starter’s agent workflows to reduce repeated setup and unnecessary research.
Changes:
- Adds focused paths for test-only work and narrow edits.
- Scopes authoring context and package API research.
- Reuses browser schemas within a session while retaining validation safeguards.
| File | Description |
|---|---|
starter/README.md |
Updates preview and canvas preflight guidance. |
starter/AGENTS.md |
Defines task scope and narrow-edit requirements. |
starter/.agents/skills/create-prototype/workflows/iterate.md |
Adds early narrow-edit classification. |
starter/.agents/skills/create-prototype/SKILL.md |
Updates task dispatch and authoring dependencies. |
starter/.agents/skills/create-prototype/references/authoring.md |
Scopes context reads and API discovery. |
starter/.agents/skills/browser-canvas-validation/WORKFLOW.md |
Updates schema reuse and timeout recovery. |
starter/.agents/skills/browser-canvas-validation/SKILL.md |
Makes context selection task-specific. |
starter/.agents/context-templates/DESIGN-SYSTEM.md |
Clarifies standalone-link research scope. |
starter/.agents/context-templates/BROWSER-VALIDATION.md |
Aligns schema reuse and recovery guidance. |
Review effort: Max
| Read `PRODUCT-DESIGN.md`, `REPOSITORY.md` and `BROWSER-VALIDATION.md` | ||
| directly there. Read `DESIGN-SYSTEM.md` for component-specific assertions. | ||
| No manifest or canvas-specific pack file is required. Never mix roots. | ||
| Read the applicable `BROWSER-VALIDATION.md` sections and owner topics for target/readiness, canvas identifiers, safe state and recovery. In the shared template, these are `Target and readiness`, `Canvas host and identifiers`, `Sessions, safe state and artifacts`, and `Recovery and cleanup`. Read `Configured Playwright MCP fallback` or `Existing CLI adapter` only when that fallback is needed. |
| A read timeout can be retried once after checking the declared readiness signal. | ||
| Refocus the same owned panel, rediscover capabilities and retry inspection only | ||
| with valid required identifiers. Do not loop or create duplicate panels. | ||
| A read timeout can be retried once after checking the declared readiness signal. Refocus the same owned panel and retry inspection only with valid required identifiers and the existing schema. Rediscover only if the runtime contract's invalidation condition applies, not because a read timed out. Do not loop or create duplicate panels. |
| responsive decisions and `ACCESSIBILITY.md` for product accessibility environments. | ||
| For application work, read the applicable sections of these owners and follow relevant topic links: | ||
|
|
||
| - `REPOSITORY.md`: `Where UI lives`, `Commands` and `Constraints`. |
| be edited, read [clarify](./clarify.md), then return here. Do not silently | ||
| create a duplicate route, fork, branch or session. | ||
| 2. Read the shared [authoring reference](../references/authoring.md) before | ||
| 2. Read the target's directly affected implementation and nearest focused test. If the change might qualify for the root instructions' narrow-edit path, classify it now. For an eligible change, follow that path and skip the remaining authoring and context reads. If eligibility is uncertain or scope grows, continue with the normal workflow. |
| For a narrow edit: | ||
|
|
||
| - Read the directly affected implementation and nearest focused test, then make only the requested change. | ||
| - Skip component preflight, product/design/repository context reads, Replica canvas preflight and the preview-before-edit requirement. |
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.


Why
Agent workflows currently repeat repository and browser setup for small, fully specified changes, and they can inspect unchanged design-system evidence more broadly than needed. This slows focused work without improving confidence, while the normal safety and quality checks remain essential for substantive UI changes.
What changes
The starter now distinguishes behavior-preserving test-only work and tightly bounded narrow edits from full prototype iterations. It scopes context reads to the task, resolves JavaScript package APIs through installed package metadata, reuses an established composition before optional recipe research, and avoids repeating design decisions or launching unrelated reviews.
Browser guidance now reuses same-provider schemas within a session, avoids capability discovery for source-only work, and selects repository and product context by the validation task. It keeps authorization, readiness, fresh rendered state, bounded recovery and fallback requirements intact. The design-system context template also explains when standalone links do not need research into unrelated composite navigation patterns.