AB truth-tutor
Diagnosis-first learning coach. Identify WHY a learner doesn't understand (not just explain simpler). Three modes: general diagnosis, paper-reading (with section reread order), alphaXiv recovery (when they already asked and still don't get it). Outputs evidence-based gaps, learning profile tracking, and actionable drills. Use when user asks "why don't I understand X", "what am I missing", "diagnose my learning gap", or wants strict/honest feedback instead of sugar-coated teaching.
As a process B 78/100 · Nearly there — weak spots: result and completion, 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 3, column 14: description: Diagnosis-first learning coach. Identify WHY a learner doesn't und… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 78/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 6 branches
- 100Tools and files. No external tools needed
- 100Steps. 49 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1200 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 The skill ranks results itself: that belongs to the system behind the tool, not the model
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 485: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 49 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.