# AGENTS.md — Build guide for RelayThat

## Project scope
Place brand assets and reviewed copy into a constrained set of layouts, then generate size variants for selected channels. Flag overflow and let the user adjust crop/focal points before export.

Catalogue verdict: kinda. The visible brand design automation loop is buildable, but a credible replacement needs more than the first screen. RelayThat earns its keep through editor polish, assets, algorithms, so expect a weekend or multi-day build and a narrower personal scope.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- A supported Node release for development and a modern browser. Ship a static bundle that can work locally without an account.
- Implementation components: Vite, React and TypeScript with SVG for diagrams or a Canvas rendering adapter for raster assets. IndexedDB for projects and revisions; versioned JSON documents with stable object IDs.
- Scope boundary: color-management edge cases; cloud collaboration and mobile apps

## Stack and architecture
- Vite, React and TypeScript with SVG for diagrams or a Canvas rendering adapter for raster assets.
- IndexedDB for projects and revisions; versioned JSON documents with stable object IDs.
- Domain model: brand tokens, approved logos, reusable layout constraints, campaign variants and export profiles

## Security and data integrity
- Sanitize imported SVG, reject external scripts and oversized assets, and require user selection before reading local files. Keep document contents out of telemetry.
- Correctness boundary: Automated resizing cannot hide text overflow or stretch logos; each variant references the exact approved asset and copy revision.
- Represent edits as reversible commands, debounce autosave, and persist a complete project snapshot before destructive structural changes.
- Export editable JSON with assets and an SVG or PNG rendering. Reopen the editable export to retain layers, relationships and IDs; image exports alone are not backups.

## Agent implementation rules
- Project rule — data model: brand tokens, approved logos, reusable layout constraints, campaign variants and export profiles
- Project rule — preserve this invariant: Automated resizing cannot hide text overflow or stretch logos; each variant references the exact approved asset and copy revision.
- Project rule — acceptance evidence: Create square and landscape versions of one campaign and inspect both for overflow; changing a logo marks dependent exports stale.

## Optional agent skills and references
- Optional external skill: [vercel-composition-patterns](https://github.com/vercel-labs/agent-skills/blob/main/skills/composition-patterns/SKILL.md) — Design reusable React components with composition, context and explicit component variants. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate the actual RelayThat-inspired workflow with owned or clearly labeled sample data: Place brand assets and reviewed copy into a constrained set of layouts, then generate size variants for selected channels. Flag overflow and let the user adjust crop/focal points before export.
- Publish a reproducible walkthrough with this observable result: Create square and landscape versions of one campaign and inspect both for overflow; changing a logo marks dependent exports stale.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: color-management edge cases; cloud collaboration and mobile apps Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Place brand assets and reviewed copy into a constrained set of layouts, then generate size variants for selected channels. Flag overflow and let the user adjust crop/focal points before export. Record prerequisites, select representative user-owned fixtures and document the unsupported features: color-management edge cases; cloud collaboration and mobile apps
2. Phase 2 — Durable model. Model brand tokens, approved logos, reusable layout constraints, campaign variants and export profiles Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Automated resizing cannot hide text overflow or stretch logos; each variant references the exact approved asset and copy revision.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Represent edits as reversible commands, debounce autosave, and persist a complete project snapshot before destructive structural changes.
4. Phase 4 — Permissions and integration failure. Sanitize imported SVG, reject external scripts and oversized assets, and require user selection before reading local files. Keep document contents out of telemetry. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export editable JSON with assets and an SVG or PNG rendering. Reopen the editable export to retain layers, relationships and IDs; image exports alone are not backups. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Create square and landscape versions of one campaign and inspect both for overflow; changing a logo marks dependent exports stale. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

## Paid-product capabilities outside this build
- color-management edge cases
- cloud collaboration and mobile apps
- pixel-perfect professional tooling
- large template and asset libraries

## Implementation prompt
WORKING SLICE
Place brand assets and reviewed copy into a constrained set of layouts, then generate size variants for selected channels. Flag overflow and let the user adjust crop/focal points before export.

Build this scoped RelayThat-inspired workflow with a documented data model and visible failure states.

Architecture
- Vite, React and TypeScript with SVG for diagrams or a Canvas rendering adapter for raster assets.
- IndexedDB for projects and revisions; versioned JSON documents with stable object IDs.

Prerequisites and limits
A supported Node release for development and a modern browser. Ship a static bundle that can work locally without an account.
Outside this release: color-management edge cases; cloud collaboration and mobile apps

Data model and correctness
brand tokens, approved logos, reusable layout constraints, campaign variants and export profiles
Invariant: Automated resizing cannot hide text overflow or stretch logos; each variant references the exact approved asset and copy revision.
Represent edits as reversible commands, debounce autosave, and persist a complete project snapshot before destructive structural changes.

Security and privacy
Sanitize imported SVG, reject external scripts and oversized assets, and require user selection before reading local files. Keep document contents out of telemetry.

Recovery and export
Export editable JSON with assets and an SVG or PNG rendering. Reopen the editable export to retain layers, relationships and IDs; image exports alone are not backups.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Place brand assets and reviewed copy into a constrained set of layouts, then generate size variants for selected channels. Flag overflow and let the user adjust crop/focal points before export. Record prerequisites, select representative user-owned fixtures and document the unsupported features: color-management edge cases; cloud collaboration and mobile apps
2. Phase 2 — Durable model. Model brand tokens, approved logos, reusable layout constraints, campaign variants and export profiles Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Automated resizing cannot hide text overflow or stretch logos; each variant references the exact approved asset and copy revision.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Represent edits as reversible commands, debounce autosave, and persist a complete project snapshot before destructive structural changes.
4. Phase 4 — Permissions and integration failure. Sanitize imported SVG, reject external scripts and oversized assets, and require user selection before reading local files. Keep document contents out of telemetry. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export editable JSON with assets and an SVG or PNG rendering. Reopen the editable export to retain layers, relationships and IDs; image exports alone are not backups. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Create square and landscape versions of one campaign and inspect both for overflow; changing a logo marks dependent exports stale. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Create square and landscape versions of one campaign and inspect both for overflow; changing a logo marks dependent exports stale.
Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees.

Optional agent guidance
Optional external skill: [vercel-composition-patterns](https://github.com/vercel-labs/agent-skills/blob/main/skills/composition-patterns/SKILL.md) — Design reusable React components with composition, context and explicit component variants. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: brand tokens, approved logos, reusable layout constraints, campaign variants and export profiles
Project rule — preserve this invariant: Automated resizing cannot hide text overflow or stretch logos; each variant references the exact approved asset and copy revision.
Project rule — acceptance evidence: Create square and landscape versions of one campaign and inspect both for overflow; changing a logo marks dependent exports stale.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.