CtrlK
BlogDocsLog inGet started
Tessl Logo

postgresql-development-cloudbase

Use when building, debugging, or evaluating CloudBase PostgreSQL / CloudBase PG / PG mode apps, including Postgres schema setup, queryPgDatabase/managePgDatabase, JS SDK v3 app.rdb() CRUD/RPC, PG HTTP API fallback, RLS-style permissions, username-password auth, and Web CMS/admin CRUD flows backed by CloudBase PG.

74

Quality

92%

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

The canonical home for this skill is postgresql-development-cloudbase in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is highly actionable with a clear validated workflow and well-structured one-level-deep references. The main weakness is conciseness: a duplicated comparison table and some restated guidance add redundant tokens.

Suggestions

Remove the duplicate NoSQL-vs-PG comparison table (it appears both near the top of 'Required Flow' and again under 'JS SDK v3 PostgreSQL Patterns'); keep a single canonical table and cross-reference it.

Translate or drop the inline Chinese phrases (e.g. '或', '通过 select 的 count 参数获取总数') in the second comparison table so the skill reads consistently in one language.

Trim the 'Golden rule' paragraph, which restates the preceding table's guidance, to reduce token cost without losing the rule.

DimensionReasoningScore

Conciseness

Mostly efficient and avoids explaining concepts Claude already knows, but the NoSQL-vs-PG comparison table is duplicated (lines ~50 and ~198, the latter mixing in untranslated Chinese) and the 'Golden rule' restates prior guidance, so it could be tightened; not the lean level-3 anchor and not the padded level-1 anchor.

2 / 3

Actionability

Provides copy-paste-ready TS/SQL code, specific MCP action signatures with parameters, exact base URLs, and concrete error codes with fixes — fully executable guidance matching the level-3 anchor.

3 / 3

Workflow Clarity

The 'Required Flow' is a clear numbered sequence with explicit validation checkpoints (verify migration history, verify RLS via real session, verify both layers before done) and feedback loops, matching the level-3 anchor and exceeding the checkpoint-missing level-2 anchor.

3 / 3

Progressive Disclosure

SKILL.md is an overview with well-signaled one-level-deep references into references/, all referenced files exist, and a 'Reference index' enumerates them; matches the clear-overview level-3 anchor.

3 / 3

Total

11

/

12

Passed

Description

100%

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

The description is specific, trigger-rich, complete, and clearly scoped to CloudBase PG with explicit 'Use when' guidance and named APIs. It is a strong, low-conflict description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and named APIs (schema setup, queryPgDatabase/managePgDatabase, JS SDK v3 app.rdb() CRUD/RPC, PG HTTP API fallback, RLS, username-password auth, CMS/admin CRUD) — matches the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Opens with an explicit 'Use when building, debugging, or evaluating ...' trigger clause and details what the skill does, clearly answering both what and when; the level-2 anchor lacks an explicit when, which this is not.

3 / 3

Trigger Term Quality

Covers natural terms a user would say ('CloudBase PostgreSQL', 'CloudBase PG', 'PG mode', 'Postgres') plus trigger method names like app.rdb(); matches the good-coverage anchor and is not the level below, which only has some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply scoped to CloudBase PG / PG mode with distinct trigger terms, making it unlikely to fire for NoSQL or MySQL skills; not the level-2 anchor, which could still overlap with similar skills.

3 / 3

Total

12

/

12

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.

Validation15 / 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
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.