AB things-plus
Personal task manager powered by Things 3. Trigger when the user asks to add, capture, review, organize, reprioritize, search, or manage tasks in Things. Also trigger when the user expresses a concrete personal future action or commitment, including natural planning phrases like "tomorrow I need to…", "I still need to…", "I should…", "remind me to…", "I've got to…", "don't let me forget…", or "help me note this down" — even when Things is not mentioned explicitly. Also trigger when the user asks for an end-of-day summary, work log, daily report, or asks to summarize what was done today and put it into Things.
As a process B 65/100 · Nearly there — 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "Do NOT trigger for" - note
frontmatter-keyunknown frontmatter key "Execution default"
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 82 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2297 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- -5TODO / placeholder text left in the skill
- -42 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 616: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 82 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.