AC vibe-learn
A micro-learning knowledge feed for developers waiting on AI coding agents. Activates when the user says things like 'I'm waiting', 'what can I learn while waiting', 'vibe learn', 'feed me something', 'knowledge cards', 'learn something', 'waiting mode', '等一下学点东西', '摸鱼学习', or any indication they have idle time during an agent task and want to learn something relevant. Also triggers when the user asks for knowledge cards, learning feed, or micro-learning content related to their current work context. Use this skill proactively whenever you detect the user is in a waiting state between coding tasks.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 51/100
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (vibe-learn) differs from the folder (checkai)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 45 steps
- 100Execution cost. Instruction body is 1454 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
- +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 604: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.