CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

minimal-web-baas-demo

Fast path for a minimal CloudBase Web + database demo (最小前后端 / 最小可用 fullstack / Lovable-like BaaS). Defaults to @cloudbase/js-sdk client CRUD (NoSQL app.database / PG app.rdb), MCP-only schema, preview-first, and forbids cloud functions unless secrets, cron/background jobs, or logic that security rules/RLS cannot express. Use for 搭一套 demo、留言板、Todo、Notes、Kanban, or when users say 带云函数+云数据库 but only need CRUD. NOT for production multi-service backends, CloudRun, WeChat Mini Programs, or tasks that truly need server secrets.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable fast-path brief with concrete code, exact tool calls, a rigid sniff order, and strong error anticipation (the anonymous-session-before-CRUD 401 rule). Its main weaknesses are redundancy — the pipeline order and the zero-cloud-function rule are each stated multiple times — and inlined partner-packaging material that would fit better in a separate reference file.

Suggestions

State the pipeline order once (the sniff-order block) and have the Standard playbook and partner paste reference it instead of restating it, cutting the triple duplication and the ~5x repetition of the zero-cloud-function rule.

Add an explicit validation checkpoint to the sequence, e.g. step 6 becomes "Verify list + add roundtrip in the preview, then ask before deploy", so the workflow has a concrete feedback loop for the database path.

Move the WorkBuddy/partner packaging notes (~40 lines) into a separate reference file (e.g. references/partner-packaging.md) and keep a one-line pointer in the main body, keeping the fast-path brief lean.

DimensionReasoningScore

Conciseness

Mostly efficient and directive, but the same pipeline order appears three times (Capability sniff order, Standard playbook, One-screen partner paste) and the zero-cloud-function rule is restated roughly five times across sections. This is noticeably tighter-able rather than only minor trimming, matching level 3; not level 4 because the duplication is more than incidental.

3 / 5

Actionability

Concrete, executable guidance throughout: a runnable signInAnonymously() code block, exact tool calls (queryEnv(action="info"), writeNoSqlDatabaseStructure), SDK methods (app.database().collection(...), app.rdb().from(...)), and specific file paths. Minor gaps keep it at level 4 — the full list+create wiring is deferred to on-demand sibling skills rather than shown, and the template helper is referenced but not exemplified.

4 / 5

Workflow Clarity

Clear, explicitly-ordered sequence ("Use this order for every minimal Web + DB demo. Do not reorder.") with error anticipation and recovery (401 → signInAnonymously before any database call) and an ask-before-deploy checkpoint. Not level 5 because there is no explicit validation step verifying the add/list roundtrip works before reporting the preview URL; the 401 note is preventive, not a checkpoint in the sequence.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the body is well-structured with a clearly-signaled "On-demand skills (fetch only when needed)" table of one-level-deep sibling SKILL.md references plus a conditional pgdoc.md reference gated on a specific scenario. Minor gap: the ~40 lines of WorkBuddy/partner packaging notes are inlined in the main body where a separate reference file would keep the fast-path brief leaner, matching level 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: it states concrete capabilities with named SDKs and APIs, gives explicit use-when triggers in both English and Chinese (including a reinterpretation trigger for users who ask for cloud functions but only need CRUD), and delimits the niche with clear NOT-for exclusions. Dense but every clause carries information — no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions with named APIs and precise conditions: "Defaults to @cloudbase/js-sdk client CRUD (NoSQL app.database / PG app.rdb), MCP-only schema, preview-first, and forbids cloud functions unless secrets, cron/background jobs, or logic that security rules/RLS cannot express". Coverage is comprehensive rather than having minor gaps, so it matches the level-5 anchor, not level 4.

5 / 5

Completeness

Explicitly answers both questions: what ("Fast path for a minimal CloudBase Web + database demo... Defaults to @cloudbase/js-sdk client CRUD... MCP-only schema, preview-first") and when ("Use for 搭一套 demo、留言板、Todo、Notes、Kanban, or when users say 带云函数+云数据库 but only need CRUD"), plus explicit negative boundaries. Not level 4, because the when-clause is already fully explicit with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say in both English and Chinese — "搭一套 demo、留言板、Todo、Notes、Kanban", "Lovable-like BaaS", "最小前后端", and the reinterpretation trigger "带云函数+云数据库 but only need CRUD" — covering synonyms and concrete app types. This matches the comprehensive-synonyms anchor at level 5; level 4 would require noticeably missing natural terms.

5 / 5

Distinctiveness Conflict Risk

Clear niche (minimal CloudBase Web BaaS fast path) with distinct triggers and explicit routing of adjacent cases away ("NOT for production multi-service backends, CloudRun, WeChat Mini Programs, or tasks that truly need server secrets"), minimizing conflict with sibling skills. Minimal conflict risk matches the level-5 anchor.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

TencentCloudBase/CloudBase-AI-Toolkit

Path

config/source/skills/minimal-web-baas-demo/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.