stitch-ui-design-variants

Stitch Design Variants

This skill acts as a Variant Generator. It takes a base design and produces alternative prompts to explore different creative directions.

Input

• Base Spec: The original Design Spec or Prompt.
• Variant Type:
  • LAYOUT: Keep style, change structure.
  • STYLE: Keep structure, change theme/colors.
  • CONTENT: Keep design, change text/data.

Output Format (List of Strings)

A list of 3 distinct prompts.

Logic Rules

1. Layout Variants

• Variant A: Standard layout.
• Variant B: Split screen or asymmetrical layout.
• Variant C: Minimalist/Hidden navigation layout.

2. Style Variants

• Variant A: Original Theme.
• Variant B: Inverted Theme (Light <-> Dark).
• Variant C: High Contrast / Monochromatic.

Usage Example

User: "Give me 3 style options for this dashboard." Output:

1. "Desktop Dashboard... Dark Mode... Blue accents..."
2. "Desktop Dashboard... Light Mode... Clean white/grey..."
3. "Desktop Dashboard... High Contrast... Black and White..."

References

• Examples

When to use

Load this skill when the user needs to select and execute a verifiable, recoverable professional workflow for the current request . First extract the goal, inputs, constraints, delivery format, and acceptance criteria from the request; the description summary is: Logic skill that generates prompts for alternative design variants e.g. A B testing options.

Rules

• Read before write: first confirm the current state and real capabilities, then perform actions that change external state.
• Least privilege: use only the files, tools, accounts, and network scope required to complete the current step.
• Evidence first: when run results, resource IDs, versions, hashes, or test outputs are missing, explicitly mark them as NOT_VERIFIED。
• Idempotency first: retain request identifiers and phase state; when results are unclear, query first and do not retry blindly.
• Privacy and security: logs, examples, receipts, and error messages must not contain tokens, cookies, keys, or personally sensitive data.

Workflow

Step 1: Clarify intent

Confirm whether this skill matches the goal; if it is only an adjacent need, hand it off to a more precise skill.

Step 2: Perform precheck

Confirm the goal, inputs, constraints, available tools, success criteria, and failure boundaries; if any critical condition is unknown, stop at the read-only stage.

Step 3: Form a plan

List the tools to be called, the objects that will be changed, the success criteria, and the safe exit method after failure.

Step 4: Execute actions

Execute in minimally sufficient steps and record evidence at key state changes; retain an associable state or receipt for every external call.

Step 5: Verify delivery

Output the results, verification evidence, incomplete items, risks, and clear next steps, and state facts, inferences, and unverified items separately.

Validation checklist

• The skill trigger conditions match the user's intent, and adjacent tasks have not been misrouted to this skill.
• The inputs, target objects, versions, and output locations are all clear, and no guessed values have been used to replace required values.
• All writes, payments, publications, or irreversible actions are within the scope authorized by the user.
• The results have been verified with independent checks; "command succeeded" or "file exists" alone does not count as complete acceptance.
• The output includes actual evidence, failed/skipped items, remaining risks, and executable next steps.

Gotchas

1. Mistaking the plan for the result: A document or prompt is not equal to actual execution; the actual execution level must be indicated.
2. Incorrect retry: A timeout or lost response may already have produced remote state; query first, then decide whether to retry.
3. Implicit scope expansion: Batch, full-scale, publication, overwrite, and payment are not natural extensions of ordinary reads and writes.
4. Version drift: When referencing external resources, record the version, tag, or commit; do not treat a mutable branch as release evidence.
5. Stale evidence: Caches, old screenshots, and historical tests cannot prove the current environment; refresh key evidence before delivery.

Non-applicability and boundaries

Do not go beyond the scope given by the user; writes, payments, publications, and irreversible actions require explicit authorization. If the request requires another skill, do not copy its body; hand off by skill name and preserve the current task context.

Progressive disclosure

• When it is necessary to determine inputs/outputs, state, and authorization points, read references/workflow-contract.md。
• When pre-delivery self-check is needed, read references/validation-checklist.md。
• When encountering timeout, partial success, or recovery scenarios, read references/error-recovery.md。
• For first run, privilege escalation denial, and failure recovery, refer to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。