- Home
- Skills
- Marketing & SEO
- Audience Research: Creator and Brand Fit
More screenshots
Works with the AI Agents you already use
Audience Research: Creator and Brand Fit
Vet a creator before you pay them: define your buyer first, sample their comments like evidence, score six fit dimensions, and deliver a one-page brief with a verdict and a confidence grade.
$5
Audience Research: Creator and Brand Fit
Example session with this skill installed
We sell collapsible home-gym equipment, $200–400, to US homeowners aged 30–50 who are short on space. A YouTube creator, "GarageGains with Marcus" (210k subscribers, garage workout content), wants $3,000 for a sponsored video. Should we do it?
- Read your context and instructions
- Compiled the audience research
Target card (written before opening the channel): US homeowners 30–50, own their home, train 3+ times a week, buy equipment in the $200–400 band. Deal-breakers: majority audience under 25 or renters in apartments (no garage, no storage problem we solve), audience primarily outside the US. Nice-to-have: prior equipment-review content.
Scorecard, from the signal inventory:
- Geography: 3 — comments are dense with US references (Home Depot, HOA complaints, Fahrenheit); channel posts on US evening hours.
- Demographic match: 3 — commenters self-describe as dads and homeowners constantly; "my wife says it has to fold flat" is practically the channel motto — that is our exact buyer constraint.
- Niche fit: 3 — of the last 20 videos, 13 are garage/small-space training; equipment is the rotation, not an exception.
- Intent: 3 — comment sample (5 videos, ~140 comments): 16% buying-intent ("does the rack fold under 12 inches? my ceiling is low"), plus repeated questions about flooring and noise — storage-and-space intent, our category's core questions.
- Authenticity: 2 — engagement looks organic and commenters vary, but two videos show giveaway-driven spikes; sponsored posts average ~70% of organic views, acceptable, not great.
- Brand safety: 3 — prior sponsors are a flooring brand and a protein brand, no competitor conflicts, no controversies.
Total: 17/18 — strong fit. Confidence: High (bio, comments, shop, and sponsor history all agree; two platforms checked).
Recommendation: proceed at $3,000, and spend the leverage on terms, not price: require the demo to show the fold-flat storage moment on camera, because that is the exact question his comment section asks. One flag for the gaps section: his audience skews male; if a women-focused line launches later, this brief does not transfer.
Connects securely to your tools. The creator never sees your data.
About this skill
Follower count is the most expensive number in influencer marketing — it looks like an answer and isn't one. This skill replaces it with an evidence method. It starts by writing the target before any profile is opened: who the buyer is, the deal-breakers stated precisely, and the nice-to-haves, so a charismatic creator can't drag the target toward themselves mid-scroll.
Then it builds a signal inventory from public data only: profile and cadence signals, geography and language signals (comment language usually tells the truth the bio doesn't), content rotation, engagement authenticity — like-to-view ratios, commenter overlap, growth patterns — and commercial signals like past sponsors and what their shop actually sells. Comments get sampled, not eyeballed: five recent posts, 20–30 comments each, tallied into buying-intent, experience-sharing, compliment, and spam buckets with a worksheet, because buying questions are the strongest intent signal a comment section holds.
The verdict comes from a six-dimension scorecard (geography, demographic match, niche fit, intent, authenticity, brand safety), each scored 1–3 with logged evidence, with thresholds for strong fit, conditional, and pass. A Step-0 deal-breaker fails a creator regardless of total. Every brief ends with a confidence grade — high, medium, or low — and a gaps section naming what couldn't be verified, plus early-exit red flags that end an evaluation fast and an edge-case section for disabled comments, small accounts, brand accounts, and creators mid-pivot.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Marketing & SEO.
Public signals only, by design: the method cannot see a creator's private analytics, so demographic conclusions are evidence-based estimates with a stated confidence grade, not certainties. Thin public data (disabled comments, very small accounts) caps confidence at low — the skill says so rather than guessing. It evaluates one creator, or several against one shared target; it is not a market-sizing or pricing-negotiation tool.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
Permissions
No special permissions declared or detected