Agent skill
ecom-foundation-docs
Automate Research → Avatar → Offer Brief → Necessary Beliefs → Angle Matrix → ads.csv for DTC ecom creative. Use when starting a new product or when you need structured inputs for creative/copy/testing.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/skill-walkerhi11-mediabuy-plugins-5
SKILL.md
Ecom Foundation Docs (Research → Angles → Production Sheet)
This skill turns raw product info + competitor context into structured artifacts you can feed into:
- image ad prompt generation (UGC look + product-focused + proof-focused)
- copy packs (branded/trust + hard sell + long-form “chapter text”)
- Meta testing workflows (creative matrix, spend-gated guardrails, learning loop)
Required outputs (create these files)
Create a workspace folder (recommended): outputs/ecom/<brand_slug>/<run_id>/ containing:
foundation/research.mdfoundation/avatar.mdfoundation/offer_brief.mdfoundation/beliefs.md(3–6 “I believe…” statements)foundation/angles.mdads/ads.csv(angle → copy → image prompt build sheet)
Inputs to request (minimum viable)
- Brand + product name, price, AOV target
- Offer URL (PDP) + any advertorial/VSL URLs
- Margin + COGS + fulfillment constraints (inventory, ship times)
- Competitor list + 3–10 competitor URLs
- Existing creative winners (if any): images + copy + KPIs
Workflow (how to fill the docs)
Use voice-of-customer and competitor patterns instead of guessing:
-
Research (
foundation/research.md)- Pull customer language, objections, alternatives, and proof sources.
- If you don’t have VOC, write a “VOC needed” section instead of inventing quotes.
-
Avatar (
foundation/avatar.md)- Who buys, why now, what they tried, what they fear, what they want.
- Capture “phrases they actually use” (from reviews/comments/messages).
-
Offer Brief (
foundation/offer_brief.md)- Awareness + sophistication level
- Big idea + mechanism + proof points
- Objections + belief chain + funnel notes
-
Necessary Beliefs (
foundation/beliefs.md)- 3–6 max; each starts with
I believe… - Add 1–3 bullets of evidence/logic for each belief
- 3–6 max; each starts with
-
Angle Matrix (
foundation/angles.md)- For each belief: generate multiple angles across:
- branded/trust (education, empathy, credibility)
- hard sell (direct response, urgency, payoff)
- proof-first (UGC/reviews, demo, before/after only if truthful/allowed)
- Each angle should specify: hook, mechanism/proof, CTA, and competing alternative.
- For each belief: generate multiple angles across:
-
Production Sheet (
ads/ads.csv)- Convert angles into testable rows with IDs for:
angle_id,angle_name,hook,mechanism,proof,ctaprimary_textvariants andheadlinevariants (or pointers to copy packs)image_concept+image_prompt_base
- Convert angles into testable rows with IDs for:
Subagent pattern (recommended)
Assign in parallel:
- Researcher →
foundation/research.md - Angle strategist →
foundation/beliefs.md+foundation/angles.md - Copywriter → populate copy columns for each angle + long-text variants
- Creative director → populate image concepts + prompt bases
Guardrails
- Don’t fabricate proof or quotes; cite sources or mark as hypothesis.
- Avoid sensitive personal attribute inference (“you have X condition”).
- Keep belief count tight (≤6) and angles diverse (don’t spam the same hook).
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?