cloudbase-code-review skill
✓ VerifiedValidates CloudBase implementations by checking for security misconfigurations, database errors, and SDK API misuse using linting and semantic review.
- GitHub stars
- 1,164
- Files
- 13
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the cloudbase-code-review skill do?
cloudbase-code-review validates CloudBase implementations by checking for security misconfigurations, database errors, and SDK API misuse using linting and semantic review.
Summary generated from the skill's SKILL.md.
About the cloudbase-code-review skill
Validating CloudBase implementations for security and correctness is the primary function of this skill. Developers working on Web, miniprogram, CloudRun, or cloud-function projects use it to catch common mistakes like auth guard misuse, missing database tables, or RLS misconfigurations before deployment. It serves as a final check after implementing features such as authentication, database CRUD operations, or storage setups.
The tool operates through two distinct layers. First, it offers an optional linting layer where users can run a local node command using a temporary cloudbase-lint.mjs script to perform deterministic regex checks for pattern mismatches and wrong API calls. Second, it provides an LLM semantic review layer that inspects code logic for architectural problems and completeness. It relies on a structured set of reference files, including a rules index and specific markdown files for modules like postgresql and storage, to guide the inspection process.
What an agent can do with it
- 1Verify authentication securityCheck if login, registration, or route guard implementations follow security best practices.
- 2Detect SDK API misuseRun automated regex-based linting to find incorrect API calls or missing configurations.
- 3Prevent credential leaksInspect Cloud Function or CloudRun handlers to ensure they do not leak headers or credentials.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the cloudbase-code-review skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the cloudbase-code-review skill in Claude Code
~/.claude/skills/cloudbase-code-review/SKILL.md
$ npx degit TencentCloudBase/CloudBase-AI-Toolkit/config/.claude/skills/cloudbase-code-review ~/.claude/skills/cloudbase-code-reviewInstall the cloudbase-code-review skill in Claude Code (project)
.claude/skills/cloudbase-code-review/SKILL.md
$ npx degit TencentCloudBase/CloudBase-AI-Toolkit/config/.claude/skills/cloudbase-code-review .claude/skills/cloudbase-code-reviewInstall the cloudbase-code-review skill in Codex
~/.agents/skills/cloudbase-code-review/SKILL.md
$ npx degit TencentCloudBase/CloudBase-AI-Toolkit/config/.claude/skills/cloudbase-code-review ~/.agents/skills/cloudbase-code-reviewInstall the cloudbase-code-review skill in Gemini CLI
~/.gemini/skills/cloudbase-code-review/SKILL.md
$ npx degit TencentCloudBase/CloudBase-AI-Toolkit/config/.claude/skills/cloudbase-code-review ~/.gemini/skills/cloudbase-code-reviewInstall the cloudbase-code-review skill in Claude.ai
npx degit TencentCloudBase/CloudBase-AI-Toolkit/config/.claude/skills/cloudbase-code-review cloudbase-code-review && zip -r cloudbase-code-review.zip cloudbase-code-review # claude.ai → Customize → Skills → + → Create skill → Upload a skill → cloudbase-code-review.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachabletencentcloudbase/cloudbase-ai-toolkit/config/.claude/skills/cloudbase-code-review is public and reachablegithub.com/tencentcloudbase/cloudbase-ai-toolkit/tree/HEAD/c ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/tencentcloudbase/cloudbase-ai-toolkit/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/tencentcloudbase/cloudbase-ai-toolkit/blob/HEAD/c ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/tencentcloudbase/cloudbase-ai-toolkit/blob/HEAD/c ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/tencentcloudbase/cloudbase-ai-toolkit/blob/HEAD/c ↗Finding
SKILL.md
View on GitHubSibling skills (local only)
Sibling CloudBase skills ship beside this skill. Use local relative paths such as ../auth-tool-cloudbase/SKILL.md.
If a referenced sibling skill file is missing from this environment, ask the user to install the full CloudBase plugin (or the missing skill). Do not HTTP-fetch remote skill or protocol markdown into the agent context.
CloudBase Code Review
One-liner: After implementing CloudBase features, call this skill to catch common mistakes before users do.
When to use
Call this skill after completing a CloudBase implementation task, before declaring done:
- You implemented auth (login / register / route guard)
- You created database tables or wrote CRUD (NoSQL / PostgreSQL / MySQL)
- You set up CloudBase Storage (file upload, hosting)
- You configured security rules or RLS policies
- You wrote MCP-dependent code
- You wrote Cloud Function or CloudRun HTTP handlers (check for credential / header echo leaks)
How it works
The skill runs in two layers:
| Layer | Method | Speed | What it catches |
|---|---|---|---|
| Lint (optional) | No executable script is shipped. If the user approves running lint, review the code block in references/lint-rules/README.md, copy it to a temporary local cloudbase-lint.mjs, then run node cloudbase-lint.mjs --project-dir <path> |
Seconds | Deterministic regex checks — wrong API calls, missing configs, pattern mismatches |
| LLM review | Read each rule's "LLM 检查" section, inspect code semantically | Variable | Semantic issues — route guard logic, RLS completeness, architecture-level problems |
Rule index
See references/RULES_INDEX.md for the full matrix (module × frontend type → applicable rules).
Rule boundary
Do not promote a single failed run or case-specific workaround into a hard rule. A rule should be backed by stable SDK/API documentation, repeated failures, or deterministic runtime behavior. Case-specific observations belong in attribution reports; only broadly applicable constraints should enter RULES_INDEX.md or the optional lint checklist.
Quick start
# Step 1: Read relevant rules for identified modules
# references/rules/cross-cutting/AUTH001.md
# references/rules/cross-cutting/SEC001.md
# references/rules/postgresql/PG-CR001.md
# ...
# Optional: if the user approves running lint, review the script code block in
# references/lint-rules/README.md, copy it to a temporary cloudbase-lint.mjs,
# then run: node cloudbase-lint.mjs --project-dir .
# Step 2: For each applicable rule, read the "LLM 检查" section
# and manually inspect your code before claiming done.
Rule format
Each rule .md file follows this structure:
# RULE-ID Rule Name
- **Module**: which module (auth / postgresql / storage / ...)
- **Severity**: error | warning
- **Stage**: code-generation | deployment | config
## 正则检查 (Lint)
The condition checked by the optional script code block in `references/lint-rules/README.md`.
## LLM 检查
Semantic review prompt for human or LLM to evaluate.
## 修复指引
How to fix the issue.
Reference index
All packaged reference files (required for skill lint reachability):
- RULES_INDEX.md
- lint-rules/README.md
- rules/cross-cutting/AUTH001.md
- rules/cross-cutting/SEC001.md
- rules/cross-cutting/SKILL001.md
- rules/postgresql/PG-CR001.md
- rules/postgresql/PG-CR002.md
- rules/postgresql/PG-CR003.md
- rules/postgresql/PG-CR004.md
- rules/postgresql/PG-CR005.md
- rules/storage/STORAGE001.md
Files in this skill
13cloudbase-code-review skill questions
How do I install the cloudbase-code-review skill in Claude Code?
Run npx degit TencentCloudBase/CloudBase-AI-Toolkit/config/.claude/skills/cloudbase-code-review ~/.claude/skills/cloudbase-code-review. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the cloudbase-code-review skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What kind of issues does this skill detect?
It identifies auth guard misuse, missing database tables, RLS misconfigurations, storage domain setup errors, and SDK API misuse.
Can I run automated linting with this skill?
Yes, if the user approves, you can run a local lint script by copying the code block from the lint-rules README to a temporary file and running it with Node.js.