AB ekalavya-self-improvement
Enforce execution discipline for ongoing work after the user has already approved direction. Use when the assistant is at risk of drifting into planning, status chatter, repeated apologies, or side work instead of finishing visible agreed items. Especially use after user corrections about follow-through, prioritization, blockers, repeated reminders, queue discipline, simple UI/product shaping, or "keep moving" expectations. Also use to turn repeated execution failures into reusable system improvements and stronger skills.
As a process B 65/100 · Nearly there — weak spots: result and completion, when it triggers, inputs and preconditions
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: 3. 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 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Failures and branches. 8 branches
- 100Tools and files. No external tools needed
- 100Steps. 89 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1595 tokens
- 100Progress reporting. Reports progress
- low 12 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
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 527: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 89 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.