Explore in MochiBot. Install in chat.Hosted workspaces and MochiBot lightweight setups include the Skills assistant. Choose a Skill and ask for installation in chat. Other OpenClaw setups can follow the first-install guide.
How to use Skills →
MOCHILAB / AI SKILL
Topic Coverage Momentum
Compare equal-length windows by distinct events, with new-baseline and source-count diagnostics.
What it does
Compare equal-length windows by distinct events, with new-baseline and source-count diagnostics.
Try saying
Compare equal-length windows by distinct events, with new-baseline and source-count diagnostics. Use current original sources, explicit dates and a cited synthesis.
Execution and scope
Includes a distinct executable evidence tool, fictional samples, schema, offline tests and CSV/JSON reports. Optional single-feed public RSS/Atom collection requires no API key. Other websites and social platforms require available permitted browsing/API access or supplied exports; this is not a universal social scraper. Identity, event/fact alignment and stage labels require source review before calculation.
Public figures are limited to public content and announced events, never private whereabouts. Preserve citations, time windows, uncertainty and failed-source coverage. The package creates reports, not scheduled jobs, push messages or speech. Those require a separately verified scheduler/reminder capability.
Method and limits
The window is divided at its exact UTC midpoint: previous [start,midpoint), recent [midpoint,cutoff]. Event counts reflect selected sources only. Growth is null when baseline is zero; topic coverage is not popularity, sentiment or truth.
References