2.6k
GitHub Stars
3
Bundled Files
2 months ago
Catalog Refreshed
3 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill openclaw/skills --skill audience-segmentation-analyst- _meta.json319 B
- metadata.json90 B
- SKILL.md4.5 KB
Overview
This skill builds audience segmentation and targeting plans ready for ad setup across Meta, Google Ads, TikTok Ads, YouTube Ads, and DSP/programmatic channels. It converts business goals and account context into an execution-ready audience strategy with clear labels, exclusions, and prioritized tests. The output includes an intent summary, findings, action plan, risks, and a structured handoff payload for campaign build.
How this skill works
I ingest the business_goal, scope, and context (URL, account notes, historical performance) and validate missing critical inputs. I analyze ICP segments, define audience labels, propose exclusion strategies, and produce prioritized actions tied to KPI impact and platform-specific notes. The result separates facts from assumptions, flags data risks, and emits a compact payload formatted for downstream ad setup and measurement.
When to use it
- When preparing ads, advertising, or campaign builds with clear operational next steps
- When you need to grow revenue, improve ROAS, reduce CPA, or optimize budget and bidding
- When analyzing traffic, conversion funnel, or campaign performance signals for targeting changes
- When requesting ICP segmentation, audience labels, and exclusion strategy
- When setting up cross-channel plans across Meta, Google Ads, TikTok Ads, YouTube Ads, or DSP
Best practices
- Always supply business_goal, scope, and context; if KPI targets are missing, I will infer and flag assumptions
- Provide baseline_metrics where available; low data quality leads to conservative recommendations
- Use clear naming conventions for audiences and exclusions to simplify reporting and iteration
- Prioritize reversible low-risk tests first when urgency or uncertainty is high
- Tie each audience action to an explicit KPI and monitoring window (e.g., 7–14 days)
Example use cases
- Meta ecommerce optimization: reduce CPA by proposing audience pruning, lookalike thresholds, and week-1 tests
- Google Ads lead gen: restructure intent segments, negative keyword/exclusion audiences, and bidding adjustments
- TikTok + YouTube scale test: cross-channel test matrix with budget split, guardrails, and rollback triggers
- DSP programmatic targeting: contextual + audience combined plan with frequency caps and exclusion lists
- Retention campaigns: audience labels for high-LTV customers and exclusion rules to avoid overlap
FAQ
Required: business_goal, scope, and context (URL/account notes/historical data). Optional but helpful: kpi_targets, constraints, platform_preference, baseline_metrics.
Can you recommend platform-specific audiences without account data?
Yes — I provide a platform-agnostic baseline plus channel variants, but platform-specific recommendations will be conservative and flagged as assumptions if account evidence is missing.