Menu

Individual skill

brand-mention-monitor

0upvotes

Use this skill when you need to know what people are saying about a brand across the web and social — "monitor brand mentions", "what are people saying about [brand] this week", "run a brand sweep", "social listening", "find high-risk mentions", or "how does [brand] compare to [competitor] in the conversation". Sweeps social platforms, news, forums, and review sites; scores every mention on reach, velocity, sentiment, and risk-topic match; and produces a triage report bucketed into Crisis / Watch / Engage / Log with a suggested owner and response window for each mention, so the team responds before one spirals.

skills/uri-knorovich/brand-mention-monitor/SKILL.md

Read pinned source

Source commit 5d786aad0c7b2ca59b1abf1f601f9407ca261996

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
237
Repository last updated
Oct 20, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

Run this when anyone needs eyes on the brand conversation — a routine weekly sweep, a launch-week watch, or a "something feels off" check. It produces a triage report: every mention scored on four dimensions, deduped against what previous runs already found, and bucketed into Crisis / Watch / Engage / Log with an owner and a response window.

## Before the sweep — resolve, profile, confirm

Do two research steps before asking the user anything:

1. **Resolve brand variants.** Search the live web for the brand's alternate spellings, hashtags, handles, product names, and sub-brands that get mentioned independently. For common-word brand names, find the disambiguating terms (industry, founder, domain) so the sweep doesn't pull unrelated noise. Fold every confirmed variant into the query list silently — never ask the user to supply this.
2. **Profile the brand.** Establish B2B vs B2C, industry, primary geography and language, and rough audience size. This picks the source profile and calibrates scoring — "high reach" means something different for a niche B2B tool than for a consumer app with millions of users.

Replace before enabling: {{CRISIS_OWNER}} (who gets flagged on a Crisis hit) and {{ALERTS_CHANNEL}} (the team channel, if any, for Crisis/Watch pushes).

Then confirm scope in a single message: the brand as you understood it plus any competitors to track alongside, the date window (default: last 7 days), depth (quick scan vs deep sweep; default deep), and who gets flagged on a Crisis-tier hit ({{CRISIS_OWNER}} — a PR lead, legal, founder, or the marketing team by default). Skip the questions entirely when the user already provided the answers or a prior run in this workspace configured them. If the brand name is still ambiguous after research, confirm which entity is meant before running anything.

## Pick the source profile
Back to top