ai-answer-gap
When the user wants to find the prompts where their brand should be cited in AI answers but isn't — and who owns the answer…
When the user wants a full-funnel influencer marketing campaign workflow: campaign setup, creator matching, budget and pricing forecast, outreach/confirmation pack, content review checklist, launch tracking, or post-campaign report. Also use on "plan an influencer campaign,"
$ npx -y skills add unifapi-agent/agents --skill creator-campaign-ops --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/creator-campaign-opsContext preview
The summary Claude sees to decide when to auto-load this skill.
When the user wants a full-funnel influencer marketing campaign workflow: campaign setup, creator matching, budget and pricing forecast, outreach/confirmation pack, content review checklist, launch tracking, or post-campaign report. Also use on "plan an influencer campaign,"
name: creator-campaign-ops description: 'When the user wants a full-funnel influencer marketing campaign workflow: campaign setup, creator matching, budget and pricing forecast, outreach/confirmation pack, content review checklist, launch tracking, or post-campaign report. Also use on "plan an influencer campaign," "run creator campaign ops," "compare predicted vs actual," "track influencer results," "review creator content," or "creator campaign workflow agent." Reads public data and user-provided campaign data only; read-only research, not outreach or campaign management.' license: MIT metadata: author: UnifAPI version: "1.0.0"
You are an influencer-marketing campaign operator who turns a campaign goal into an evidence-backed operating pack: brief, matching plan, pricing forecast, confirmation decisions, content review criteria, launch watchlist, and post-campaign readout.
This is an **enhanced** skill: it reads live public data through UnifAPI.
Campaign plans fail when the brief, creator match, price, and reporting live in separate spreadsheets. Use live public data to keep every decision tied to the creator's actual audience and recent content. Use the `unifapi` skill to connect (OAuth MCP), then call:
UnifAPI reads public data only — it never creates campaigns, sends outreach, negotiates, schedules posts, requests revisions, signs usage rights, or reads private conversion dashboards. Keep any `billing` metadata so the output can state record cost.
1. **Lock the campaign brief.** (Read `.agents/product-marketing.md` / `.claude/product-marketing.md` first if it exists.) Confirm product, target customer, market/country/language, campaign goal, desired action, budget range, platform mix, creator volume, deliverable formats, timeline, usage rights, exclusivity, must-have traits, and exclusion list. If the brief is thin, ask before searching. 2. **Build the matching and budget model.** Translate the brief into platform-specific search queries, creator tiers, expected creator count, target CPM/CPC or cost-per-signup assumptions, and a reserve budget. Mark which assumptions are from public data vs. operator input. 3. **Discover and rank creators.** Run the recall operations above or hand off to `creator-shortlist`. Score niche relevance, audience fit, momentum, platform fit, safety, budget fit, and reach-for-budget. Keep a rejected-candidate log with reasons. 4. **Price and confirm the shortlist.** Hand X/Twitter-heavy candidates to `kol-pricing`; deep-vet borderline creators with `audience-fit-check`. For each finalist, produce a confirm / negotiate / pass decision with public evidence, estimated price band, predicted reach, predicted CPM/CPC, confidence, and the exact unresolved questions for outreach. 5. **Prepare the trust-safe outreach and production pack.** Draft outreach angles, sender identity requirements, authorized sending domain checks, one-click opt-out / do-not-contact handling, the creator brief, deliverable checklist, FTC/disclosure requirements, approval criteria, revision policy, usage-rights and exclusivity questions, promo-link/UTM naming plan, and handoff fields the operator must collect. Review user-provided scripts, captions, or storyboards against the brief; do not invent approval for content you have not seen. 6. **Create the launch watchlist.** Before launch, define the required public post URL/ID fields, the sampling windows (for example T+24h, T+72h, T+7d), the exact operations to re-run, and the predicted metrics to compare against actual public engagement. If the user provides private analytics exports, keep them separate from public UnifAPI evidence. 7. **Read results and optimize.** After launch, fetch the public post records, compare predicted vs. actual reach/engagement/cost efficiency, identify top performers and under-delivery, and recommend the next cycle: scale, renegotiate, retarget, revise creative, or stop.
# Creator Campaign Ops — {Product} — {date}
## Campaign Spec
- Goal / desired action:
- Target audience:
- Markets / languages:
- Platform mix:
- Budget range and reserve:
- Deliverables:
- Timeline:
- Hard constraints:
- Assumptions needing operator confirmation:
## Matching And Budget Model
| Platform | Query / source | Target creator tier | Why this source | Expected role in campaign |
| -------- | ------------------------------- | ------------------- | ----------------- | ------------------------- |
| X | x/communities/search: "{topic}" | niche builders | high buyer signal | shortlist + pricing |
## Creator FOpen-source marketing agents for Claude, ChatGPT, Codex, OpenClaw, Hermes, and any MCP client.
When the user wants to find the prompts where their brand should be cited in AI answers but isn't — and who owns the answer…
When the user wants to know whether their brand or domain is cited in AI answers — AI Overviews, ChatGPT, or AI search — for the…
When the user has AI visibility, GEO, AI answer gap, or AI citation evidence and wants a prioritized plan to improve where the…
When the user wants to track how often their brand or domain gets mentioned across ChatGPT and AI search engines over a set of…
When the user wants to track a named competitor's launch or announcement and the public reaction to it across X, LinkedIn,…
When the user wants to research, profile, or analyze a competitor from its public footprint — site, search/SEO, backlinks,…