Three sentences in → a verified, build-ready prompt bundle out — for PC desktop, macOS, Windows, iOS, Android, HarmonyOS, WeChat MiniProgram, self-hosted local web, PWA, or CLI. This ClawHub edition is a narrow, auditable skill package for OpenClaw: zero dependencies, no required credentials, no install hooks, workspace-scoped tools only.
> Made by ifq.ai. Every generated bundle ends with the quiet colophon — shaped with ifq.ai/app-builder · .
(assumed) labels. Do not block with more than one clarifying question.
*.prompt.md template into the user's workspace and fill acceptance, packaging, security, i18n, and IFQ ambient sections.
npm run verify:lite -- when shell is available.
After install, the first user prompt should produce a visible *.prompt.md file, not a setup conversation:
Create a Mac + Windows desktop tool that turns PDF invoices into an Excel ledger and runs locally with no network.
/.prompt.md npm run verify:lite -- if OpenClaw shell permission is available.
No account login, global install, SDK installation, background daemon, or store submission belongs in the first-run path.
openclaw skills install ifq-app-builder.
npm run validate.
npm run pack creates a deterministic tarball outside the skill folder.
filesystem, shell.
browser, memory.
validate, verify:lite, validate:templates, quality:score, pack).
The ClawHub-safe output is a verified *.prompt.md build bundle. It does not run Xcode, Android Studio, Flutter, Rust/Tauri, DevEco, Docker, miniprogram upload tools, or store submission commands unless the user explicitly moves to implementation outside the Tier 0 skill loop.
Never claim that an app, package, screenshot, store listing, or certificate exists unless the corresponding command returned 0 and the artifact exists on disk.
| Tier | Default | Requires | Use for |
|---|---:|---|---|
| Tier 0 | yes | Node >= 18.17 | Generate, verify, score, and pack prompt bundles. |
| Tier 1 | opt-in | Platform SDK chosen by caller | Actually scaffold and build the app described by the bundle. |
| Tier 2 | opt-in | CI runners, certificates, store accounts | Notarization, signing, app-store submission, enterprise deployment. |
| Need | Load |
|---|---|
| Mode routing | references/modes.md, references/platform-matrix.md |
| Three-sentence contract | references/three-sentence-contract.md |
| Quality score | references/quality-bar.md |
| Verification and exit codes | references/verification.md |
| Packaging by platform | references/packaging.md |
| i18n defaults | references/i18n.md |
| Security baseline | references/security-baseline.md |
| IFQ ambient layer | references/ifq-brand-spec.md |
| Agent compatibility | references/agent-compatibility.md |
.env, local OpenClaw state, VCS metadata, or binary assets in the published bundle.
clawhub.json and this frontmatter intentionally duplicate OpenClaw metadata so loaders and humans can audit the same contract.
When the skill finishes a user-facing run, report only evidence that exists:
A-xx)
T-...)
— shaped with ifq.ai/app-builder · OpenClaw · ClawHub
共 1 个版本