CtrlK
BlogDocsLog inGet started
Tessl Logo

cloudbase-code-review

Code review and validation for CloudBase projects. After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill to check for known pitfalls — auth guard misuse, missing database tables, RLS misconfiguration, storage domain setup, and SDK API misuse. Supports automated lint scripts (regex-based) + LLM semantic review.

67

Quality

82%

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

72%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.

Well-structured, lean overview that delegates detail to a verified one-level-deep reference bundle. Its main weakness is workflow clarity: the review sequence lacks an explicit validation/feedback loop, leaving checkpoints implicit.

Suggestions

Add an explicit validation checkpoint to the Quick start, e.g. 'If lint or LLM review finds issues → fix → re-run lint / re-inspect until clean before declaring done', to lift workflow_clarity above 3.

De-duplicate the lint copy-and-run instructions (present in both the How-it-works table and Quick start) into one location to tighten conciseness.

Tighten or relocate the Rule-boundary prose so the overview stays a pure navigation/trigger surface.

DimensionReasoningScore

Conciseness

Lean and mostly efficient — it does not explain what CloudBase/RLS is and uses a compact table for the two-layer method — but the lint 'copy to a temporary local file' instructions are duplicated in both the table and Quick start, and the Rule-boundary prose could be trimmed.

4 / 5

Actionability

Provides concrete file paths and a runnable command ('node cloudbase-lint.mjs --project-dir <path>') with a full reference index; minor gap is that the actual review heuristics live in referenced files and 'inspect code semantically' is somewhat abstract, which is appropriate for an instruction-only skill.

4 / 5

Workflow Clarity

A sequence is present (read rules → optional lint → inspect before done), but there is no explicit validate→fix→retry checkpoint or feedback loop for the review process; checkpoints are implicit, matching the 3 anchor rather than the explicit-checkpoint 4.

3 / 5

Progressive Disclosure

Clear overview with a well-signaled Reference index pointing one level deep to 11 verified-real rule files plus RULES_INDEX.md and lint README; content is appropriately split out of the body and easy to navigate.

5 / 5

Total

16

/

20

Passed

Description

92%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.

A strong, concrete description that names a specific niche and lists actionable pitfalls with an explicit after-implementation trigger. Trigger phrasing leans on 'call this skill' rather than a broad 'Use when…' synonym set, slightly limiting trigger-term breadth.

DimensionReasoningScore

Specificity

Names the domain and enumerates multiple concrete actions/pitfalls — 'auth guard misuse, missing database tables, RLS misconfiguration, storage domain setup, and SDK API misuse' — plus the two-layer lint+LLM method, giving comprehensive coverage rather than the minor gaps of a 4.

5 / 5

Completeness

Explicitly answers both 'what' (code review/validation checking known pitfalls via lint+LLM) and 'when' ('After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill…') with concrete trigger phrases; not the 4 anchor since 'when' is explicit, not merely improvable.

5 / 5

Trigger Term Quality

Good keyword coverage across natural terms ('code review', 'CloudBase', 'Web / miniprogram / CloudRun / cloud-function', 'auth guard', 'RLS', 'SDK API'), but lacks a few natural user phrasings and synonyms that would push it to a 5.

4 / 5

Distinctiveness Conflict Risk

Targets a clearly niche platform (CloudBase / CloudRun / cloud-function / miniprogram) with distinct, platform-specific triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 10 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 16 deeper-than-1-level

Warning

Total

13

/

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.