CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloudbase-document-database-web-sdk

Use CloudBase document database Web SDK only for confirmed NoSQL collection work. Query, create, update, and delete document data; if the task mentions PostgreSQL / CloudBase PG / app.rdb(), route to postgresql-development instead.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/cloudbase/skills/cloudbase-document-database-web-sdk/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is highly actionable with executable CloudBase-specific code and unusually strong operational gotchas (rule propagation delay, result._id shape, CUSTOM rule semantics). Its weaknesses are redundancy — the same key patterns are restated across the Activation Contract, gotchas, and Working rules — and quick-routing targets that are not present in the bundle being evaluated.

Suggestions

Deduplicate: state the `result._id` return shape and the CMS CUSTOM-rule pattern once (working rules) and reference them from gotchas rather than repeating the full detail twice.

Ensure the seven quick-routing files (crud-operations.md, security-rules.md, etc.) ship in the bundle alongside SKILL.md, or note their expected location as explicitly as the sibling-skill fallback is handled.

Consolidate the write-verification and rule-propagation retry guidance into a single sequenced validate-fix-retry workflow so the checkpoints are integrated rather than scattered.

DimensionReasoningScore

Conciseness

The body is mostly efficient and CloudBase-specific, but key facts are repeated at length: the `result._id` return shape appears three times (gotchas, working rule 5, quick example), the CMS CUSTOM-rule pattern is fully spelled out twice (gotchas and working rule 3), and the PG routing boundary appears twice — fitting 'mostly efficient but could be tightened'.

3 / 5

Actionability

Copy-paste-ready executable code covers the common cases (init, where/get, add with result._id capture, orderBy/skip/limit pagination, field selection, try/catch), plus verbatim security-rule expressions and exact return-shape specifics ("the created document ID is exposed at top-level result._id") — fully executable with no pseudocode.

5 / 5

Workflow Clarity

Ordered working rules (auth model first, browser-native code, respect rules, check errors, persist IDs) plus a minimal checklist and real validation guidance (check result.updated/deleted, get() round-trip on the written _id, retry after the 2–5 minute rule-propagation window) give a clear sequence with most checkpoints present; they fall short of level 5 because the checkpoints are scattered across sections rather than one integrated validate-fix-retry workflow.

4 / 5

Progressive Disclosure

The "Quick routing" section is a clean, clearly signaled map to one-level-deep files (CRUD -> ./crud-operations.md, Security rules -> ./security-rules.md, etc.), matching good structure — but none of the seven referenced files (nor the ../ sibling skills) actually exist in this bundle, so the references cannot be followed as shipped.

4 / 5

Total

16

/

20

Passed

Description

71%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.

The description is concrete, honest about scope, and excellently disambiguated against its closest sibling skill. Its main weakness is trigger-term coverage: users would naturally mention specific SDK surfaces (db.collection(), watch(), pagination) that the description omits in favor of a CRUD summary plus routing terms.

Suggestions

Add natural trigger phrases users would actually say, e.g. "Use when the request mentions db.collection(), .where(), .watch(), pagination, or aggregation in a Web frontend".

Briefly enumerate the fuller capability set (realtime listeners, aggregation, geolocation queries) alongside CRUD to close the coverage gap.

Keep the PG routing sentence — it is the description's strongest distinctiveness asset — but consider trimming "only for confirmed" phrasing that reads as a constraint rather than a trigger.

DimensionReasoningScore

Specificity

"Query, create, update, and delete document data" lists four concrete CRUD actions on a named domain (CloudBase document database Web SDK, NoSQL collections), matching the 'several specific actions with minor gaps' anchor — coverage gaps exist (realtime watch(), aggregation, geolocation) so it is not the comprehensive level 5.

4 / 5

Completeness

The 'what' is clear (query/create/update/delete document data via the Web SDK) and a 'when' is present via "only for confirmed NoSQL collection work" plus the explicit PG routing boundary, but the when-guidance is a scope restriction rather than explicit natural trigger phrases, fitting 'both present; when could be more explicit or specific'.

4 / 5

Trigger Term Quality

Relevant keywords are present ("CloudBase", "document database", "NoSQL collection", "PostgreSQL / CloudBase PG / app.rdb()"), but common natural trigger phrases a user would actually say — "db.collection()", ".where()", ".watch()", pagination, collection permissions — are missing, matching 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

"Use CloudBase document database Web SDK only for confirmed NoSQL collection work" carves out a clear niche and explicitly routes the nearest competitor ("if the task mentions PostgreSQL / CloudBase PG / app.rdb(), route to postgresql-development instead"), giving distinct triggers with minimal conflict risk.

5 / 5

Total

16

/

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

plugin/cloudbase/skills/cloudbase-document-database-web-sdk/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.