AC python-hardener
Hardens Python scripts by applying a complete security review, clean-code refactoring, robust error handling, proper logging, and full docstring coverage — then produces a companion Markdown documentation file. Use this skill whenever the user uploads or references Python files and asks for any of the following (even if they only mention one): - security review, SQL injection check, shell injection, path traversal - error handling, try/except fixes, bare except removal - logging, RotatingFileHandler, proper log setup - clean code, refactoring, meaningful variable names - docstrings, type hints, parameter documentation - code review, code hardening, production-ready script - "fix this script", "improve this code", "make this safe" Also trigger when the user says things like "review and fix", "make this production-ready", "add proper error handling and logging", or uploads .py files alongside a review request. If multiple Python files are uploaded together, harden all of them.
Hardens Python scripts by applying a complete security review, clean-code refactoring, robust error handling, proper logging, and full docstring coverage —…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (python-hardener) differs from the folder (skill-python-hardener)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 41 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1528 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 989: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.