AB fastapi
Builds, debugs, and hardens FastAPI services: async endpoints, Pydantic models, dependency injection, auth, and deployment. Use when writing or reviewing a FastAPI app, router, or schema; when the API hangs or every route slows because a sync driver or CPU work blocks the event loop; when a request returns an unexpected 422, a POST becomes a 307, or a 500 arrives with no CORS headers; when migrating pydantic v1 to v2 (`model_dump`, `from_attributes`, `field_validator`); when `Depends` runs too often, `yield` cleanup misfires, or dependency overrides do not take; when SQLAlchemy raises `QueuePool limit` or `MissingGreenlet`, or connections leak across workers; when TestClient, httpx `AsyncClient`, or pytest-asyncio fail with a closed event loop; when uvicorn or gunicorn workers, graceful shutdown, `root_path`, or proxy headers need deciding; or when background tasks, WebSockets, SSE, uploads, or the OpenAPI docs misbehave. Not for Django, Flask, or general Python — `django`, `flask`, `py`.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "changelog" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4630 tokens
- 100Steps. 45 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1003: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 45 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.