AB loop-engineering
Run an adaptive, bounded, evidence-backed work loop when the user explicitly invokes it, asks it to remain active for the current task or thread, or when active personal, workspace, or project instructions declare it the default. Once active, use it for substantive follow-ups without requiring the tag again. Apply it across coding, product, UI, UX, accessibility, research, strategy, public writing, and reusable prompts that need task-specific checks, measured self-correction, honest evidence, and clean stopping. Keep narrow tasks light and do not trigger from incidental mentions of for-loops, event loops, or feedback loops.
Run an adaptive, bounded, evidence-backed work loop when the user explicitly invokes it, asks it to remain active for the current task or thread, or when…
As a process B 71/100 · Nearly there — weak spots: result and completion, 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: 30. 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 71/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 38 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3160 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -32 of 7 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 631: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (17 of 17)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.