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
Negative Keyword Review
Simulate supplied literal negative-match rules against actual search queries and flag protected-query conflicts before review.
What it helps with
Simulate supplied literal negative-match rules against actual search queries and flag protected-query conflicts before review.
Say it like this
Check these proposed negatives against converting queries before I review them.
Keep campaign and ad-group scope separate and show exact and phrase conflicts.
What you receive
Confirm Search scope, whitespace tokenization and the explicit protection facts. Keep rule IDs, campaign/ad-group scope and query IDs. Compare literal rules, return each actual match and protect conversions only when supplied. Ask about unknown conversions rather than inventing a bad-keyword classification.
Give the assistant your actual files or records and confirmed rules. It asks for missing facts rather than inventing records; you do not need to hand-fill JSON. Receive a traceable report and detailed review rows for download.
Scope
Literal whitespace-token simulation only; platform spelling correction, close variants, language segmentation and final serving eligibility are not reproduced. No automatic exclusions or advertising changes.
The script reads supplied local files and creates reports without network or model calls. Your assistant still uses its configured services; this does not promise absolute privacy for a conversation. The Skill is free and needs Python3.10+. Optional AI interpretation follows your existing model service charges.
Demand and technical basis