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.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./config/.claude/skills/cloudbase-code-review/SKILL.md

The canonical home for this skill is cloudbase-code-review in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

A well-organized overview with excellent progressive disclosure and real bundle references, but the workflow leans on commented guidance rather than fully executable steps and lacks explicit validation/feedback checkpoints. Tightening the install/policy prose and adding a concrete review-then-fix loop would raise the weaker dimensions.

Suggestions

Replace the commented Quick start block with actual runnable commands (e.g., a concrete lint invocation and an explicit per-rule review sequence) to lift actionability toward copy-paste-ready.

Add an explicit validation/feedback checkpoint — e.g., 'If lint or LLM review flags an issue, apply the rule's 修复指引, then re-run lint before claiming done' — to give the workflow a real fix→re-review loop.

Trim the 'Standalone Install Note' and 'Rule boundary' sections to essentials so the body leans closer to a pure, token-efficient overview.

DimensionReasoningScore

Conciseness

Mostly efficient with no concept over-explanation, but the 'Standalone Install Note' and 'Rule boundary' meta sections add install-plumbing and policy prose that could be tightened; not quite 'every token earns its place'.

2 / 3

Actionability

Provides a concrete executable lint command ('node cloudbase-lint.mjs --project-dir <path>') and explicit rule file paths, but the primary Quick start is comment-style pseudocode and the core review action ('manually inspect your code') is somewhat vague, landing between concrete and incomplete.

2 / 3

Workflow Clarity

A clear two-layer sequence (read rules → optional lint → LLM review → claim done) is present, but validation checkpoints are only implicit ('before claiming done') with no fix→re-review feedback loop, which caps it below the explicit-checkpoint anchor.

2 / 3

Progressive Disclosure

SKILL.md is a concise overview with well-signaled one-level-deep references — 'See references/RULES_INDEX.md' plus a Reference index of markdown links — and all 10 referenced files exist in the bundle, matching the clear-overview anchor.

3 / 3

Total

9

/

12

Passed

Description

85%

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, well-scoped description that clearly states what it does and when to invoke it, with only minor room to broaden natural trigger phrasing. It uses third-person voice with no first/second-person penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'check for known pitfalls — auth guard misuse, missing database tables, RLS misconfiguration, storage domain setup, and SDK API misuse' plus 'automated lint scripts (regex-based) + LLM semantic review' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what ('Code review and validation for CloudBase projects... check for known pitfalls') and when ('After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill'), satisfying the explicit-trigger anchor.

3 / 3

Trigger Term Quality

'Code review and validation' are natural user terms, but the remaining triggers lean on technical jargon (RLS misconfiguration, auth guard misuse) rather than common user variations; missing broader natural phrasings, so it sits at 'some relevant keywords but missing common variations' rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

Scoped to 'CloudBase projects' with a distinct, domain-specific pitfall list and 'Web / miniprogram / CloudRun / cloud-function' qualifiers, giving it a clear niche unlikely to trigger for unrelated skills.

3 / 3

Total

11

/

12

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: 9 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 14 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.