CloudBase AI Toolkit is an integration layer that lets AI coding tools use Tencent CloudBase as an application backend, including databases, authentication, functions, storage, and deployments. Developers use it to have coding agents build and operate CloudBase-backed applications through skills, plugins, commands, and chat-accessible tools. The catalogue entries are the toolkit’s own skills, agents, hooks, plugins, rules, instructions, and MCP tools.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill minimal-web-baas-demogit clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-ToolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tencentcloudbase/cloudbase-ai-toolkit/minimal-web-baas-demo)<a href="https://agentmods.dev/skills/tencentcloudbase/cloudbase-ai-toolkit/minimal-web-baas-demo"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/cloudbase-ai-toolkit/minimal-web-baas-demo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tencentcloudbase/cloudbase-ai-toolkit/minimal-web-baas-demo"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/cloudbase-ai-toolkit/minimal-web-baas-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 36 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00144 | $0.02244 |
| Opus 5.5 | $0.00058 | $0.00898 |
| Sonnet 5.5 | $0.00029 | $0.00449 |
| Haiku 4.5 | $0.00014 | $0.00224 |
Grade A, and why
minimal-web-baas-demo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
3 near-identical copies found in the catalogue:
- minimal-web-baas-demo — 100% identical, 0 lines differ
- minimal-web-baas-demo — 98% identical, 14 lines differ
- minimal-web-baas-demo — 97% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sibling skills (local only)
Sibling CloudBase skills ship beside this skill. Use local relative paths such as ../web-development/SKILL.md.
If a referenced sibling skill file is missing from this environment, ask the user to install the full CloudBase plugin (or the missing skill). Do not HTTP-fetch remote skill or protocol markdown into the agent context.
Minimal Web BaaS Demo (fast path)
Goal: minutes to an interactive Web + database preview, not a cloud-function middleware stack.
This skill is the product equivalent of CloudBase Sites SessionStart Rule 5 (BaaS-first data persistence).
Activation Contract
Use this first when
- The user asks for a minimal fullstack / 前后端 demo, message board, Todo, Notes, Kanban, or Lovable/Supabase-like quick app on CloudBase Web.
- The user says "带云函数+云数据库" but the real need is CRUD + preview (reinterpret as Web SDK → database).
Do NOT use for
- WeChat Mini Programs (
wx.cloud) — use../miniprogram-development/SKILL.md. - True server workloads: payments callbacks, SMS providers, secret third-party keys, cron/ETL, WebSockets — use
../cloud-functions/SKILL.mdor../cloudrun-development/SKILL.md. - Large multi-module products that need
../spec-workflow/SKILL.md.
Hard rules (align with Sites SessionStart Rule 5)
- BaaS-first data path
- Schema / admin: Prefer MCP management tools. Do not ask the user to create collections/tables in the console. If MCP tools are missing in this session, configure MCP for next time and use
tcbCLI (../cloudbase-cli/SKILL.md) for equivalent schema/admin ops.- NoSQL:
writeNoSqlDatabaseStructure(create collection / indexes) + permission tools as needed; CLI: NoSQL commands incloudbase-cli. - PostgreSQL: follow
../postgresql-development-cloudbase/SKILL.md(queryPgDatabase/managePgDatabase/ migrations); CLI parity viatcb db pg …when MCP is unavailable.
- NoSQL:
- Reads / writes:
@cloudbase/js-sdkin the browser.- NoSQL:
app.database()→db.collection(...).get()/add()/update()/watch(...). - PG:
app.rdb().from(...).
- NoSQL:
- Prefer the template helper (often
src/utils/cloudbase.ts). Do not invent a second SDK wrapper.
- Schema / admin: Prefer MCP management tools. Do not ask the user to create collections/tables in the console. If MCP tools are missing in this session, configure MCP for next time and use
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed f257d9a13814
- 6d ago Changed 0795cf0ecf6f
- 8d ago Changed 7d2984a31bf4
- 14d ago Changed 293ef4916727
- 17d ago Changed · +1 lines 138d0e20e3d1
- 18d ago Changed · +1 lines a8aed5a140ef
- 27d ago Changed ee5e015a8d61
- 1mo ago Changed a6f701b38739
- 1mo ago Changed 08ed231d51f5
- 1mo ago First seen · 139 lines · 144 tokens per session scan A 9f8442945283
minimal-web-baas-demo is a skill published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,152 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 2,244 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
todolist-skill
A simple to-do list workflow backed by a cloud database, for viewing, adding, completing, and deleting tasks.
kolo
Kolo is a text-based Python debugger that captures every executed function, return value, local variable, HTTP request, and SQL query into greppable trace files. Use this skill for tricky debugging challenges, to verify that code behaves as expected at runtime, and to see the real data and values passing through the…
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
atlas-mssql
SQL Server specifics for Atlas (also Azure SQL and MSSQL): login, dev database and URL scope (mode=schema vs mode=database, the database query parameter), compatibility level and collation, system-generated constraint names, clustered index defaults and datetime2 precision in HCL, GO batches and the delimiter…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…