BC llm-calibration-logprobs
Reads model uncertainty from token log-probabilities. Covers collecting logprobs and aggregating multi-token labels, confidence tiers and margins for triage, calibration assessment with ECE, Brier scores, and reliability diagrams, responsible downstream use of confidence, and reproducibility archives. Use when the user asks classifier confidence by item, logprobs, top-k tokens, calibration, ECE, Brier, reliability diagrams, or routing low-confidence cases to human review. This is within-model confidence. Independent-model agreement goes to model-council-voting, and codebook and validation design to text-classification.
Reads model uncertainty from token log-probabilities.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 1. 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 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4701 tokens
- 100Steps. 58 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +1No license
- +2Single-language instructions
- +3Description length 626: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 58 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.