AB make-knowledge-cards
Convert pasted articles, local Markdown/TXT files, or PDF documents into 5-8 concise knowledge cards. Each card captures one key concept with a title, core knowledge summary, brief explanation, and an example or self-test question. Trigger when the user asks to make knowledge cards, create study cards, summarize into cards, or provides an article or PDF for card-based learning. Do NOT use for web scraping, Anki export, or graphical interfaces.
Convert pasted articles, local Markdown/TXT files, or PDF documents into 5-8 concise knowledge cards.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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
- note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (read, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 5 branches
- 85Steps. 42 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1926 tokens
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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 447: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.