AB py
Writes, debugs, and reviews Python code — runtime traps, packaging, typing, async, tests, performance. Use when Python raises or misbehaves: ModuleNotFoundError, circular imports, AttributeError on None, UnboundLocalError, UnicodeDecodeError, mutable default arguments, `is` vs `==`, float rounding, naive vs aware datetimes, or a wrong answer with no exception; when pip, uv, poetry, venv, pyproject or a lockfile fight over dependencies, or a package installs but will not import; when threads, asyncio, multiprocessing or the GIL hang, deadlock, or leak memory; when pytest passes but should not, mocks patch the wrong module, or async tests never run; when mypy or pyright errors need clearing; when a script is slow, eats RAM, or gets OOM-killed; when subprocess calls hang or logs never appear; or when upgrading Python breaks the build. Not for library-specific problems — pandas, numpy, django, fastapi and flask have their own skills.
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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 28. 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. 11 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4137 tokens
- 100Steps. 42 steps
- 100Failures and branches. 2 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 10 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 943: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 10 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.