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.

68

Quality

85%

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 cloudbase-code-review in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

78%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, lean review skill that delegates detail to a real, well-organized reference bundle with clear navigation. The main weakness is that the LLM-review execution layer leans on 'manually inspect' and lacks an explicit review feedback loop.

Suggestions

Deduplicate the lint script copy-and-run instructions so they appear in only one place (either the 'How it works' table or 'Quick start').

Replace the vague 'manually inspect your code' step with a concrete per-rule checklist or a 'for each rule, verify X / Y / Z' procedure so the LLM-review layer is executable rather than descriptive.

Add an explicit validation checkpoint such as 'only declare done after every applicable rule passes; if a rule fails, fix and re-check before claiming completion'.

DimensionReasoningScore

Conciseness

Lean overview that assumes Claude's competence and avoids explaining known concepts, but the lint copy-to-temp workflow is described twice (in the 'How it works' table and again in 'Quick start'), a minor redundancy that could be trimmed.

4 / 5

Actionability

Provides concrete file paths and an executable command ('node cloudbase-lint.mjs --project-dir <path>'), but the core LLM-review layer reduces to 'manually inspect your code', leaving a small gap in concrete inspection steps.

4 / 5

Workflow Clarity

A clear two-step sequence (read applicable rules, then inspect code per rule before declaring done) is present, though explicit validation checkpoints or a fail→fix→re-review feedback loop are only implicit rather than spelled out.

4 / 5

Progressive Disclosure

The body is a concise overview with well-signaled, one-level-deep markdown links to a verified bundle (RULES_INDEX.md, lint-rules/README.md, and per-rule files all exist), making navigation easy and content appropriately split.

5 / 5

Total

17

/

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, specific, third-person description that clearly states both what it does and when to invoke it, with a well-scoped CloudBase niche. Minor room to add synonym-style trigger phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete review actions and a comprehensive set of specific pitfalls — 'auth guard misuse, missing database tables, RLS misconfiguration, storage domain setup, and SDK API misuse' — plus two methods ('lint scripts (regex-based) + LLM semantic review').

5 / 5

Completeness

Explicitly answers what ('Code review and validation ... check for known pitfalls') and when ('After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill') with concrete trigger phrases, satisfying the 'Use when...' equivalent requirement.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('code review', 'CloudBase', 'auth guard', 'RLS', 'storage', 'SDK'), but lacks common synonym variations and an explicit 'when the user mentions X' phrasing, so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

Clearly scoped to CloudBase projects with niche-specific triggers (CloudRun, cloud-function, RLS, CloudBase Storage), giving it a distinct niche with minimal overlap risk against generic code-review 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.