AC meeting-minutes-qa-tts
Read meeting minutes, produce a short summary with the current conversation model, save the meeting text and summary into local memory, answer follow-up questions about that same meeting in the current conversation model, and generate spoken audio for both the initial summary and later answers with the SenseAudio TTS API. Use when the user wants to ask detailed follow-up questions about one meeting note after it has been read and remembered, and wants both a text answer and an mp3 answer. If no meeting source is available, ask for a local file path or URL first. Before asking the user for a SenseAudio API key, first check whether `SENSEAUDIO_API_KEY` is already configured in the environment and use it directly when present. Before any audio generation, ask the user where the mp3 should be saved.
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: 15. 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 (python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 38 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 872 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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)
- +3Description length 806: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -33 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 5 headings
- +3Step-by-step instructions: 38 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.