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.

65

Quality

80%

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 ./plugin/cloudbase/skills/cloudbase-code-review/SKILL.md
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.

The skill body is well-structured as an overview with clean progressive disclosure and mostly actionable, token-efficient guidance. Its main gap is workflow clarity: the review process lacks explicit validation checkpoints and a fix→re-validate feedback loop, capping that dimension at 3.

Suggestions

Add an explicit validation/feedback loop to the Quick start (e.g., 'If lint or LLM review finds issues, fix them and re-run before claiming done') to lift workflow_clarity above 3.

De-duplicate the optional-lint instructions so they appear in one place (either the layer table or Quick start), referencing the other, to tighten conciseness toward 5.

Inline one or two concrete example checks (e.g., a sample regex or an LLM 检查 prompt) so the core review steps are actionable without opening every reference file.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence without explaining CloudBase fundamentals, though the optional-lint instructions are repeated in both the layer table and the Quick start block, a minor bit of redundancy that keeps it just below 5.

4 / 5

Actionability

Provides concrete, executable guidance such as "copy it to a temporary local cloudbase-lint.mjs, then run `node cloudbase-lint.mjs --project-dir <path>`" and a clear per-rule review procedure, with the minor gap that the bulk of the review logic lives in referenced files rather than inline.

4 / 5

Workflow Clarity

A rough sequence exists (identify modules → read rules → optional lint → LLM review → claim done), but there are no explicit validation checkpoints or fix-and-retry feedback loops, which the rubric caps at 3 for a review/batch workflow lacking validation.

3 / 5

Progressive Disclosure

The body is a concise overview with a full Reference index linking to one-level-deep bundle files (RULES_INDEX.md, lint-rules/README.md, and individual rule .md files, all verified present), giving clear navigation and appropriate content splitting.

5 / 5

Total

16

/

20

Passed

Description

87%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 strong, explicitly pairing a concrete what with a clear when and listing specific review pitfalls. Its only weakness is the second-person "call this skill" phrasing, which breaks the third-person-voice convention and caps specificity at 4.

DimensionReasoningScore

Specificity

Lists multiple concrete review actions ("auth guard misuse, missing database tables, RLS misconfiguration, storage domain setup, and SDK API misuse") giving comprehensive coverage, but the second-person imperative "call this skill" violates the third-person-voice rule, reducing the score by 1 from 5.

4 / 5

Completeness

Explicitly answers both what ("Code review and validation... to check for known pitfalls") and when ("After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage of natural CloudBase terms a user would say ("Web / miniprogram / CloudRun / cloud-function", "auth guard", "RLS", "storage", "SDK API"), but it lacks common synonyms and file extensions, so it does not reach the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear CloudBase niche with distinct triggers (Web/miniprogram/CloudRun/cloud-function and specific pitfall types), minimizing conflict with other skills.

5 / 5

Total

18

/

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.