AB measure-okr-grader
Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum (committed | aspirational | learning | operational_health | compliance_or_safety), committed-vs-aspirational interpretation, evidence quality assessment, learning synthesis, and next-cycle recommendations. Refuses to retroactively change targets or shrink committed scope, average away guardrail KRs, treat 0.7 as success for committed or compliance_or_safety KRs, equate effort with impact, or use scores for individual performance. Hands off to iterate-lessons-log, iterate-retrospective, define-hypothesis, measure-dashboard-requirements, measure-instrumentation-spec, and foundation-okr-writer.
Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum (committed | aspirational | learning | operationalhealth |…
As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
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: 4. 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 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 28 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 100Tools and files. No external tools needed
- 100Steps. 79 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3779 tokens
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +3Description length 693: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 79 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.