Agent Skills: CloudBase Code Review

Sibling 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