AB comment-voc-miner
Turn public comments into a usable brief. Give a post link, a category to search, or comments you already copied, and get the objections, verbatim lines, purchase worries, FAQ answers, live-commerce replies, and spoken hooks that come from what viewers actually wrote. This comment analysis workflow reads public comments on Douyin, TikTok, Xiaohongshu, Instagram, YouTube, and X, and reply threads on Douyin, TikTok, Xiaohongshu, Instagram, and YouTube, or works from comments you paste, then groups the real audience language into a same-day brief. Use it for comment analysis, comment-section analysis, comment mining, VOC insight, audience insight, user voice research, FAQ writing, and live-commerce answers that sound like the audience.
Turn public comments into a usable brief.
As a process B 66/100 · Nearly there — weak spots: result and completion, 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: 16. 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 66/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 14 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 1962 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
- -32 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 742: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.