ad-copy
Write platform-native paid ad copy with multiple angles to test. Use when asked to write ad copy, Google/Facebook/LinkedIn/Instagram ads, PPC headlines, or paid social creative copy. Produces ready-to-ship variants per platform (headlines, primary text, descriptions, CTAs) across distinct angles, sized to each platform's limits, with a note on what each variant tests.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills /tmp/ad-copy && cp -r /tmp/ad-copy/exports/openclaw/ad-copy ~/.claude/skills/ad-copySKILL.md
# Ad Copy Skill
Paid ads live or die on the hook and the angle, and you never know which wins — so you test several.
This skill writes platform-native variants (right format, right character limits) across *distinct
angles* (pain, outcome, social proof, curiosity, objection), so you ship a real test, not one guess.
## Required Inputs
Ask for these only if they aren't already provided:
- **Platform(s)** — Google Search, Meta (FB/IG), LinkedIn, X, etc. (format and limits differ).
- **Product & offer** — what's advertised and the action (click, lead, install, buy).
- **Audience & their trigger** — who's targeted and the pain/desire that makes them click.
- **Differentiator & proof** — why you, and any metric/social proof to use.
- **Landing destination** — so the ad matches the page (message match lifts conversion).
## Output Format
### Ad Copy: [product] — [platform(s)]
For each platform, produce variants in its native fields and limits, e.g.:
**Google Search** — 3 sets of {Headlines (≤30 chars ×3), Descriptions (≤90 chars ×2)}.
**Meta / LinkedIn** — 4 ads of {Primary text (hook in first line, ~125 chars before "see more"), Headline, Description, CTA button}.
Each variant labelled with its **angle** and what it tests:
| # | Angle | Hook | What it tests |
|---|---|---|---|
| 1 | Pain | "Still doing X by hand?" | does the problem framing resonate |
| 2 | Outcome | "Ship Y in a day" | does the result pull harder |
| 3 | Social proof | "5,000 teams switched" | does credibility win |
**Notes** — the message-match line to keep consistent with the landing page, and which variable to hold constant so the test is clean.
## Quality Checks
- [ ] Variants span genuinely distinct angles (not reworded versions of one)
- [ ] Each fits the platform's exact fields and character limits
- [ ] The hook lands in the first line / before the fold
- [ ] Ad message matches the landing page it points to
- [ ] Each variant notes what it's testing, so results are interpretable
## Anti-Patterns
- [ ] Do not ship one ad — without variants you can't learn; give a real test set
- [ ] Do not write near-duplicate variants — vary the angle, not just the wording
- [ ] Do not exceed platform limits — copy that truncates mid-hook wastes spend
- [ ] Do not mismatch ad and landing page — broken message match tanks Quality Score and conversion
- [ ] Do not over-claim — ad platforms reject unsupported superlatives, and they erode trust
## Based On
Performance-creative practice — angle testing, platform-native formats, message match, hook-first structure.Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations.
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation framework, UX design, responsible AI checklist, and launch monitoring plan.
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context, success criteria, constraints, edge cases, and out-of-scope boundaries.
Design statistically rigorous A/B tests and interpret experiment results. Use when asked to design an experiment, run an A/B test, calculate sample size, interpret test results, or assess whether an experiment was successful. Produces a complete experiment design with hypothesis, sample size, run time, success criteria, and risk flags — or a results interpretation with ship/iterate/kill recommendation.
Synthesises user signals from multiple research sources into a unified, weighted insight brief. Use when you have data from interviews, support tickets, NPS verbatims, app reviews, or sales calls and need to reconcile contradictions, surface the underlying need behind requests, or answer 'what are users really telling us'. Produces ranked insights with confidence ratings, source weighting rationale, divergent signal analysis by user segment, and a research gap identification section.
Structure a product data analysis, metric deep-dive, funnel analysis, or cohort study. Use when asked to analyse product metrics, investigate a drop in conversion, explain a data change to stakeholders, or find the root cause of a metric movement. Produces a structured analysis with question, root cause, confidence level, and recommended action.
Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, root cause hypotheses, and prioritised actions.
Structure a retention analysis, churn investigation, or engagement deep-dive for any product team. Use when asked to analyse user retention, investigate churn, measure DAU/MAU, or build a retention improvement plan. Produces a retention snapshot with root cause hypotheses, aha-moment correlation, and prioritised interventions.