AB session-feedback-analyzer
Parse Claude Code session JSONL to extract implicit user feedback signals. Detects skill invocations (tool_use blocks with name="Skill" or /slash-commands), classifies user responses as correction/acceptance/partial within a 3-turn influence window, and computes per-skill correction_rate metrics. Not for synthetic evaluation (use improvement-evaluator) or structural scoring (use improvement-learner). Use this when you need to find which skills users correct most often, or generate feedback.jsonl for the improvement-generator.
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 75/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 100Steps. 23 steps
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3993 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 531: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.