stitch-react-vite-dashboard

Stitch Data Dashboard Implementation

Quick Start

1. "Implement the store operations draft as an appointment volume dashboard; first provide a locally reviewable result."
2. "Add query and empty/error/loading states to the orders table; preserve the existing scope and source."
3. "Display on-chain read-only data under an explicit requirement; mark missing inputs and verification status."

For designers, frontend developers, and teams maintaining this workflow. Designers provide intent and assets, developers provide engineering/tools, and the team preserves source and acceptance status during handoff.

Capability Boundary Description

✅ Good At

• Implementing the store operations draft as an appointment volume dashboard.
• Adding query and empty/error/loading states to the orders table.
• Displaying on-chain read-only data under an explicit requirement.

⚠️ Requires Assets

• Target React/Vite project and locked versions.
• Stitch HTML/screenshots and DESIGN.md.
• API contracts, pagination rules, and demo data.

❌ Not Applicable and Handoff

• Ordinary single-card conversion → stitch-react-components.
• shadcn primitive migration → stitch-shadcn-ui.
• Signed transactions or financial advice → hand off to an explicitly authorized business process, first deliver the read-only data requirements.

Workflow

1. Read the actual project versions and screen assets; do not upgrade React/Vite by default.
2. Map DESIGN.md colors, fonts, and spacing to project CSS variables, and record the source.
3. Split pages/presentational components/hooks, and preserve semantic table, label, focus, and routing.
4. Set queryKey, query functions, pagination, and loading/empty/error/retry states per the API contract; use a clearly marked demo adapter when there is no API.
5. Run project type/lint/build and interaction verification; use a local token consistency check, and do not use an unverified external linter as a gate.

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, first output a draft of assumptions, then precisely list what is missing and its purpose; do not use vague prompts like "please provide more context".

Security and Result Verification

Do not read unrelated account configurations, do not collect user passwords; credentials are provided only by the environment or authorized connectors. Use demo data only in examples; before uploading, replace customer names, phone numbers, and order numbers with demo values, and check HTML, screenshots, and file metadata. Do not write keys, session cookies, full base64, or signed download URLs into reports/repositories. Do not fabricate unverified parameters, visual effects, or business numbers; note sources, decision basis, actual execution, and unverified parts in the output.

• Filtering/pagination changes queryKey, and mocks are not used to impersonate a backend.
• Semantic tables and keyboard focus are usable.
• VITE_* contains only public configuration.

Customizable: API adapters, queryKey, pagination strategy, breakpoints, currency/units. Value-added checks: async state matrix; data source annotations; public configuration boundaries.

FAQ

Q1: What is the main deliverable? Appointment filter = pending confirmation, API demo returns [] → table title and filter are retained, "No appointments" is displayed, and no fabricated statistics are shown.

Q2: When should a different entry point be used instead? Ordinary single-card conversion → stitch-react-components; shadcn primitive migration → stitch-shadcn-ui; signed transactions or financial advice → hand off to an explicitly authorized business process, and first deliver read-only data requirements.

Q3: What happens when inputs are missing? First provide a clearly marked draft based on local assumptions, and list "Needed additions: target React/Vite project and locked versions; Stitch HTML/screenshots and DESIGN.md; API contract, pagination rules, and demo data." Write operations that depend on these inputs are not executed.

Q4: How is completion determined? Filters/pagination change the queryKey, and mocks are not used to impersonate the backend; semantic tables and keyboard focus are usable; VITE_* contains only public configuration.

Q5: How is it customized? API adapter, queryKey, pagination strategy, breakpoints, currency/units; when not provided, follow 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; without a remote receipt, do not claim upload success, and without runtime verification, do not claim it is live. Additional installation or scope expansion requires explaining the specific impact first.

Reference as needed

• When performing detailed mapping, API, or template work, 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 input/output and verification scenarios are needed, read Local application examples。
• The local implementation basis is the source code accompanying the current skill and pinned 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 that online behavior has been verified.

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: implement a Stitch design as a React/Vite data dashboard; trigger when TanStack Query, tables, filtering, async state, and design token consistency are needed. Use stitch-react-components only for ordinary presentational components; add on-chain reads only when explicitly requested..

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 output are missing, clearly mark them as NOT_VERIFIED。
• Idempotency first: retain request identifiers and stage status; when results are unclear, query first and do not blindly retry.
• 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 preflight

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

Step 3: Form a plan

List the tools to be invoked, 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, unfinished items, risks, and clear next steps, and state facts, inferences, and unverified items separately.

Validation checklist

• The skill trigger conditions are consistent with the user's 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, paid, publish, or irreversible actions are within the scope authorized by the user.
• The results have been verified with independent checks; "the command succeeded" or "the 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 is not equal to 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, publish, overwrite, and paid operations are not a natural extension 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, paid, publish, and irreversible actions require explicit authorization. If the request requires another skill, do not copy its body text; hand off by skill name and preserve the current task context.

Progressive disclosure

• When inputs/outputs, states, and authorization points need to be determined, read references/workflow-contract.md。
• When a pre-delivery self-check is needed, read references/validation-checklist.md。
• When encountering timeouts, partial success, or recovery scenarios, read references/error-recovery.md。
• For first runs, refusal of privilege escalation, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。