Use when the user wants to vibe-code a full-stack web app inside DeepSeek Harness — scaffold from CloudBase templates, local Vite preview, PostgreSQL tables, and one-click static hosting deploy with a real domain.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add TencentCloudBase/CloudBase-AI-Toolkit --skill sites --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Sites?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/tencentcloudbase-sites)More formats (shields.io, HTML) on the badges page.
---
name: cloudbase-sites
description: Use when the user wants to vibe-code a full-stack web app inside DeepSeek Harness — scaffold from CloudBase templates, local Vite preview, PostgreSQL tables, and one-click static hosting deploy with a real domain.
---
# CloudBase Sites (DSH)
Closed loop for "build me a web app" inside DeepSeek Harness.
## Mandatory sequence
1. Call `mcp__cloudbase__auth` `action=status`. If not signed in, `action=start_auth` `authMode=device`. Never pass an API Key.
2. Call `mcp__cloudbase__downloadTemplate` with `template="react"` (or `vue`) into the workspace. Do not scaffold files by hand.
3. Start the Vite dev server locally and tell the user the preview URL.
4. Create PostgreSQL tables with `mcp__cloudbase__managePgDatabase` (`action=execute`, `confirm=true`). Verify with `mcp__cloudbase__queryPgDatabase`.
5. Build the frontend (`pnpm build` / `npm run build`).
6. Deploy with `mcp__cloudbase__manageHosting` `action=upload` pointing at `dist/`. Return the **real domain** from the tool result. There is no hosting rollback API — do not offer a rollback button.
7. Mini Program publish is P2 and not available. Say so explicitly; do not fail silently.
## Product language
Never say FLEXDB / SCF / TDSQL / EnvId / Region in user-facing text. Say 文档型数据库 / 云函数 / 数据库 / 环境 ID / 地域.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
