AC learned-from-ai
Turn chat interactions with AI into durable learning materials for humans. Use when the user provides a chat/share link, pasted AI conversation, or rough AI-generated draft and wants it converted into structured, long-lived notes for review and memory. Especially use when the user wants the fixed structure: (1) definition, (2) essential ideas or engineering practice, (3) worked examples and calculations, (4) important derivations, (5) Q&A, (6) further reading/viewing, plus a separate cheat sheet. For tasks under this skill, always use a subagent with model openai-codex/gpt-5.4 and thinking medium by default so the main session stays responsive, unless the user explicitly asks otherwise. Always save outputs in notes/ unless the user explicitly asks otherwise.
As a process C 61/100 · Has gaps — weak spots: result and completion, 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: 2. 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 2, column 14: description: Turn chat interactions with AI into durable learning materials for… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 5 branches
- 85Steps. 89 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1600 tokens
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 768: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 89 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.