stitch-taste-design

Stitch Visual Style Proposal

Quick Start

1. "Write a restrained Chinese visual proposal for a store appointment brand; provide locally reviewable results first."
2. "Turn the operations dashboard's density/motion preferences into specifications; preserve the existing scope and sources."
3. "Propose typography and layout variants under the brand's existing colors; mark missing inputs and verification status."

For designers, front-end developers, and teams maintaining this workflow. Designers provide intent and assets, developers provide engineering/tooling, and the team preserves sources and acceptance status during handoff.

Capability Boundaries

✅ Good At

• Writing a restrained Chinese visual proposal for a store appointment brand.
• Turning the operations dashboard's density/motion preferences into specifications.
• Proposing typography and layout variants under the brand's existing colors.

⚠️ Requires Materials

• Brand assets and page purpose.
• Target audience, viewport, and existing constraints.
• Density, degree of variation, motion preferences.

❌ Inapplicable Scenarios and Handoff

• Extract real tokens from an existing implementation → stitch-extract-design-md.
• Generate actual Stitch screens → stitch-ui-designer.
• Arbitrarily changing the brand or fabricating product results → preserve brand inputs; when data is missing, provide structural illustrations rather than factual claims.

Workflow

1. Read the brand and goals, prioritize user-approved values, and distinguish observed facts from design recommendations.
2. Provide three adjustable directions: density/layout variation/motion; by default these are recommendations, not hard brand rules.
3. Form color names/values/roles and a type hierarchy with Chinese fallbacks, and check readability and content density.
4. Write specific constraints for components, layout, breakpoints, and motion; disable non-essential motion under prefers-reduced-motion and do not force infinite loops.
5. Output a seven-section DESIGN.md proposal and mark the basis for decisions, pending items, and verification methods; if upload is needed, use the management skill separately.

Order by dependency: source verification → local artifacts → authorized external operations → verification handoff. For multiple tasks, do the current main path first; when information is missing, output a draft with assumptions first, then precisely list what is missing and its purpose, without using vague prompts like "please provide more context."

Security and Result Verification

Do not read unrelated account configurations or collect user passwords; credentials are provided only by the environment or authorized connectors. Use only demo data in examples; before uploading, replace customer names, phone numbers, and order numbers with demo values, and check HTML, screenshots, and file metadata. It is forbidden to write keys, session cookies, full base64 content, or signed download URLs into reports/repositories. Unverified parameters, visual effects, and business figures must not be fabricated; outputs must note sources, decision basis, what was actually executed, and what has not yet been verified.

• Brand takes precedence over example style prohibitions.
• There are clear paths for Chinese fonts and low motion.
• Statistics, customer counts, and performance data are not fabricated.

Customizable: density, variation, motion intensity, brand lock-in items, devices, and Chinese fonts. Value-added checks: adjustable style axes; brand difference notes; low-motion solutions.

FAQ

Q1: What are the main deliverables? Store reservation proposal: retain brand #2563eb; density 5/10; Chinese system sans-serif; button press feedback; low-motion mode disables displacement; all are suggestions and not uploaded.

Q2: When should a different entry point be used instead? Extract real tokens from an existing implementation → stitch-extract-design-md; generate actual Stitch screens → stitch-ui-designer; arbitrarily change the brand or fabricate product results → retain the brand input; when data is missing, provide a structural mockup rather than factual claims.

Q3: What happens when inputs are missing? First provide a clearly marked local draft of assumptions, and list "Needs to be provided: brand assets and page purpose; target audience, viewport, and existing constraints; density, degree of variation, motion preferences." Write operations that depend on these inputs are not executed.

Q4: How is completion determined? Brand takes precedence over example style prohibitions; there is a clear path for Chinese fonts and low motion; statistics, customer counts, and performance data are not fabricated.

Q5: How is it customized? Density, variation, motion intensity, brand lock-in items, device, and Chinese fonts; when not provided, use existing project values and mark assumptions.

Q6: Does it automatically upload, install, or go live? Only perform actions covered by the current request and existing authorization; do not claim upload success without a remote receipt, and do not claim go-live without runtime verification. Additional installation or scope expansion requires explaining the specific impact first.

Reference as needed

• When executing detailed mappings, APIs, or templates, read Extended Workflow。
• When encountering failures/abnormal inputs, read Anti-patterns and Gotchas。
• When edge cases, compatibility, customization, and authorization are involved, read In-depth FAQ。
• When complete inputs, outputs, and verification scenarios are needed, read Local Application Examples。
• The local implementation basis is the current skill's accompanying source code and fixed upstream snapshot; the structure follows the Agent Skills specification. The tool's current behavior is subject to the actual schema; when not connected, do not claim to have verified online behavior.

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: write a DESIGN.md proposal for Stitch with a clear visual direction; trigger it when the user asks for a more distinctive typography, color, layout, and motion plan. Use stitch-design-md to audit existing design facts; it will not automatically override approved brand guidelines or generate remote screens.

Rules

• Read before write: first confirm the current state and actual 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, clearly mark them as NOT_VERIFIED。
• Idempotency first: preserve request identifiers and stage state; when results are unclear, query first rather than blindly retrying.
• 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 to a more precise skill.

Step 2: Perform pre-checks

Confirm the goal, inputs, constraints, available tools, success criteria, and failure boundaries; if any key 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 minimal 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 are consistent with user intent, and adjacent tasks were not misrouted to this skill.
• The inputs, target objects, versions, and output locations are all clear, and no guessed values were used in place of required values.
• All write, payment, publication, 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. Treating a plan as a result: A document or prompt does not equal actual execution; the actual execution level must be indicated.
2. Retrying on error: A timeout or lost response may already have produced a remote state; query first before deciding 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 exceed the scope given by the user; write, payment, publication, 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 input/output, state, and authorization points need to be determined, read references/workflow-contract.md。
• When self-checking before delivery is needed, read references/validation-checklist.md。
• When encountering timeouts, partial success, or recovery scenarios, read references/error-recovery.md。
• For first run, privilege escalation refusal, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。