BD prompt-optimization
Applies prompt repetition to improve accuracy for non-reasoning LLMs. Use when a Haiku or other non-reasoning agent misses details in a long prompt.
Promises to repeat prompts so weak models like Haiku don't lose details in long instructions. Files contain 543 tokens of code, no scripts, one folder. Checks show B grade, quality score 75/100, but process score only 41 with broken references. Not tested on models. The idea works—repetition does help weak models—but the skill doesn't show how much or when. Supports many platforms, which looks optimistic.
Install if you feed Haiku huge prompts regularly and accept token bloat. If your model handles them fine already, you won't save anything.
Applies prompt repetition to improve accuracy for non-reasoning LLMs.
As a process D 41/100 · Unfinished process — References files that are not bundled: references/prompt-repetition.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/prompt-repetition.md - note
frontmatter-keyunknown frontmatter key "agent_types" - note
frontmatter-keyunknown frontmatter key "research_source" - note
frontmatter-keyunknown frontmatter key "activation"
Process rating: all ten parameters 41/100
- 0Tools and files. 1 referenced file(s) missing: references/prompt-repetition.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 543 tokens
- 100Running it twice. No mutating operations
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
- +1No license
- +2Single-language instructions
- +3Description length 148: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.