AB simple-code
Plan and build small, readable coding projects in three reliable modes: start, continue, and review. Think first, make a short plan, then delegate implementation/review/testing/bug-fixing/documentation/step-tracking to a coding sub-agent. Prefer the model openai-codex/gpt-5.3-codex by default. Use when the user asks for simple code, a small project, a self-contained utility, straightforward feature work, or a practical code review that should stay easy to read and easy to manage.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 25 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 8 branches
- 85Steps. 112 steps, 3 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2177 tokens
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 484: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 112 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.