AC concept-rediscovery-walk
Guides a learner to invent a math or ML concept themselves through a Socratic walk — a sequence of small guessable questions that ends with the learner stating the formal definition unprompted. The 3Blue1Brown signature move. Use when the learner is meeting a foundational concept (eigenvectors, gradient, attention, softmax, KL divergence) for the first time, when prior exposure produced memorization without understanding, or when the user says "explain it from scratch", "I want to really get it", "build it up for me", or "where does this come from".
Guides a learner to invent a math or ML concept themselves through a Socratic walk — a sequence of small guessable questions that ends with the learner…
As a process C 64/100 · Has gaps — weak spots: result and completion, 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 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 100Steps. 29 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 2428 tokens
- 100Running it twice. No mutating operations
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 555: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.