Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for anderskev/fastapi-code-review.
Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Fastapi Code Review" (anderskev/fastapi-code-review) from ClawHub.
Skill page: https://clawhub.ai/anderskev/fastapi-code-review
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.
Command Line
CLI Commands
Use the direct CLI path if you want to install manually and keep every step visible.
Name/description match the SKILL.md and reference files. The skill only asks the agent to inspect FastAPI code and follow review gates; there are no unrelated env vars, binaries, or installs requested.
ℹ
Instruction Scope
Runtime instructions explicitly tell the agent to open repository files, anchor findings to file:line, read handler bodies, and search the repo for Depends/Security/etc. That is appropriate for a code-review skill but means the agent must be allowed to read the project's source; also the SKILL.md references ../review-verification-protocol/SKILL.md which is not present in the provided manifest (missing reference).
✓
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes risk because nothing is written to disk or fetched at install time.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. It does not request secrets or external service tokens; this is proportional to a static code-review assistant.
✓
Persistence & Privilege
always:false (not forced into every agent run), user-invocable:true, and model-invocation allowed (normal). Note: because the skill reads repo files when run, allowing autonomous invocation increases the potential impact if combined with other risky skills, but by itself this is expected.
Assessment
This skill appears to do exactly what it says: guide a FastAPI code review by reading source files. It's low-risk because it has no install or secret requirements, but be aware it needs read access to your repository to operate. Before installing/run: (1) ensure you don't expose secrets in the repository (API keys, credentials, .env files), (2) confirm the missing referenced file (review-verification-protocol) if you rely on that gate, and (3) if you allow autonomous invocation, restrict agent permissions or run reviews on a sanitized copy of the codebase.
Like a lobster shell, security has layers — review code before you run it.
Correct HTTP methods (GET, POST, PUT, DELETE, PATCH)
Proper status codes (200, 201, 204, 404, etc.)
Dependencies use Depends() not manual calls
Yield dependencies have proper cleanup
Request/Response models use Pydantic
HTTPException with status code and detail
All route handlers are async def
No blocking I/O (requests, time.sleep, open())
Background tasks for non-blocking operations
No bare except in route handlers
Valid Patterns (Do NOT Flag)
These are idiomatic FastAPI patterns that may appear problematic but are correct:
Pydantic validates request body automatically - No manual validation needed when using typed Pydantic models as parameters
Dependency injection for database sessions - Sessions come from Depends(), not passed as function arguments
HTTPException for all HTTP errors - FastAPI handles conversion to proper HTTP responses
Async def endpoint without await - May be using sync dependencies or simple operations; FastAPI handles this
Type annotation on Depends() - This is documentation/IDE support, not a type assertion
Query/Path/Body defaults - FastAPI processes these at runtime, not traditional Python defaults
Returning dict from endpoint - Pydantic converts automatically if response_model is set
Context-Sensitive Rules
Only flag issues when the context warrants it:
Flag missing validation ONLY IF the field isn't already in a Pydantic model with validators
Flag missing auth ONLY IF the endpoint isn't using Depends() with an auth dependency
Flag missing error handling ONLY IF HTTPException isn't raised appropriately for error cases
Flag sync in async ONLY IF the operation is actually blocking (file I/O, network calls, CPU-bound), not just non-async
Gates (FastAPI-specific)
Run once per FastAPI-related finding, after you can anchor file:line for the handler (see review-verification-protocol) and before the finding text ships. If a step’s pass condition is not met, do not assert the finding as written—gather evidence, withdraw, downgrade severity, or rephrase as a question.
Gate 1 — Route decorator and response surface
Step
Action
Pass condition
1a
Open the handler’s route decorator in the repo (not from memory).
file:line for @router.* / @app.* (or the site that registers this handler).
1b
Record HTTP method, response_model=, and status_code= on that decorator (or note they are absent).
Snippet from that line or explicit absent with the same file:line.
Gate 2 — Blocking or “should be async”
Step
Action
Pass condition
2a
Read the full handler body.
file:line range covering the body.
2b
If claiming blocking I/O: name each blocking call (e.g. requests., open(, time.sleep, sync DB/ORM).
Each call has file:line, or withdraw the finding if none after the read.
Gate 3 — Depends, validation, auth
Step
Action
Pass condition
3a
List parameters: Depends / Annotated[..., Depends], Pydantic models, Body/Query/Path, Request/Response.
Names + mechanism tied to file:line on the signature.
3b
If claiming missing auth: search the handler file (and its APIRouter module if separate) for Depends, Security, HTTPBearer, or project auth dependencies.
Citation to an existing hook, or search result: paths searched + N matches (zero is allowed).
3c
If claiming missing validation: confirm the argument is not already a Pydantic model or constrained Query/Path/Body.
Type/source with file:line, or withdraw if validation already applies.
FastAPI Framework Behaviors
FastAPI + Pydantic handle many concerns automatically:
Request validation via Pydantic models
Response serialization via response_model
Dependency injection for cross-cutting concerns
Exception handling via exception handlers
Before flagging "missing" functionality, verify FastAPI isn't handling it.