beifeng724/personal-workbench-skills / skills/personal-workbench-builder
personal-workbench-builder
VerifiedBuild a durable personal or professional workbench as a runnable application, or produce a six-stage generic prompt pack for building it. Use when the user wants to turn a recurring workflow into a dashboard, management system, workspace, personal operating system, or long-lived website with multiple connected modules and persistent state. Trigger for project, CRM, creator, learning, family, finance, travel, teaching, legal, or team workbenches. Do not trigger for marketing sites, one-off scripts, ordinary coding tasks, or informational questions.
references/delivery-deployment.md
View on GitHub# Delivery And Deployment
Read [deployment-options.md](deployment-options.md) before selecting a runtime. Use this file for handoff and operational verification.
## Direct-mode package
Deliver:
1. Runnable source with exact start/build commands.
2. Current `workbench-spec.md` and `workbench-manifest.json`.
3. Test commands, control inventory, actual results, and evidence.
4. Everyday use instructions.
5. Export, backup, restore, and last-known-good recovery instructions.
6. Update, schema migration, compatibility, and rollback steps.
7. Deployment instructions, data location, synchronization boundary, and recurring-cost estimate.
8. Known limitations and owners for accounts, data, backups, and ongoing services.
Do not call a static mockup a complete system when persistence, sync, permissions, or integrations were confirmed. Do not call a hosted static URL, PWA, or mobile-local package synchronized unless a real synchronization backend was implemented and tested.
## Responsibility split
Before setup that touches accounts, paid services, physical devices, or private credentials, state:
- Agent responsibilities: code, configuration templates, migrations, tests, packaging, troubleshooting, and reproducible instructions.
- User responsibilities: identity-bound registration, payment, account terms, private credential entry, physical-device permission, domain/store ownership, and final authorization for external changes.
Do not ask the user to perform a technical step that can be completed safely in the active workspace. Do not place credentials into generated files or logs.
## Communication by level
### plain
Use numbered actions and visible outcomes. Explain where data lives and what happens if the device, browser, app, or host computer is unavailable.
### guided
Give the consequence first, then the technical label. Example: "To keep phone and computer in sync, this version uses a cloud database, which stores the records online."
### technical
Include runtime versions, environment variables, migrations, auth boundaries, data residency, observability, RPO/RTO, rollback, and cost assumptions.
## Verification before handoff
- Fresh install/start succeeds from documented commands.
- Production build succeeds when a build step exists.
- The selected vertical slice works with empty data and realistic fictional sample data.
- Every required control has an actual functional result; page load, syntax, or selector checks alone are insufficient.
- Layout works at representative desktop and phone widths.
- Persistence location and synchronization boundaries are accurately described.
- Export is created and restore is rehearsed when data risk warrants it.
- Import merge/overwrite and migration preserve current data on failure.
- Secrets are absent from client bundles and repository history available in scope.
- A failed integration shows an actionable error and preserves user input.
- For a selected local-service profile, startup, alternate-port handling, shutdown consequences, backup creation, and restore are tested.
- For Xiao Ma He, record platform and package type; mark it `candidate` until the required real-device checks pass.
Run `scripts/workflow_guard.py` for `verification-passed` after recording this evidence. Handoff as incomplete when a required result is failed, blocked, or not run.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |