Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/squadcodercom/squadcoder/ad-copywritingnpx skills add squadcodercom/squadcoder --skill ad-copywritinggit clone --depth 1 https://github.com/squadcodercom/squadcoderWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00103 | $0.00836 |
| Opus 5 | $0.00051 | $0.00418 |
| Sonnet 5 | $0.00021 | $0.00167 |
| Haiku 4.5 | $0.00010 | $0.00084 |
Grade A, and why
sc:ad-copywriting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Copywriting
Write ad and marketing copy that converts. Always start from the audience, offer, and one desired action — never from a clever line.
Step 0 — gather the brief (ask if missing)
- Product/offer and the single most valuable benefit.
- Audience: who, their pain, their desire, their objection.
- Platform (sets length + tone — see specs below).
- Goal/CTA: one action (buy, sign up, book, download, learn more).
- Language/market: Hebrew/Israeli? See the localization section.
Frameworks (pick one per piece)
- PAS — Problem → Agitate → Solution. Best for pain-driven offers.
- AIDA — Attention → Interest → Desire → Action. General-purpose.
- BAB — Before → After → Bridge. Great for transformation/results.
- 4U headline test — Useful, Urgent, Unique, Ultra-specific (hit ≥3).
Structure of one ad
- Hook / headline — earn the next line. Lead with the benefit or the pain, not the brand.
- Body — proof + specifics (numbers, outcomes, social proof). Cut adjectives, keep nouns/verbs.
- CTA — one verb, low friction, present tense ("Start free", "Book a demo", "התחילו עכשיו").
Rules
- One idea per ad. One CTA per ad.
- Specific beats vague: "cut invoicing time 60%" > "save time".
- Write at a 6th-grade reading level; short sentences; active voice.
- Show, don't claim: testimonials, metrics, guarantees, scarcity (only if true).
- Always produce 3–5 distinct variants (different angle/hook), not reworded twins, for A/B testing.
Platform specs (current-ish; verify before shipping)
| Platform | Primary text | Headline | Notes |
|---|---|---|---|
| Google Search RSA | — | 15 headlines ≤30 chars, 4 descriptions ≤90 | Pin sparingly; include keyword + benefit |
| Meta (FB/IG) feed | ~125 chars before "See more" | 27–40 chars | Hook in first line; emoji ok, sparingly |
| TikTok | Native, ~spoken | — | Sound-on, pattern interrupt in 1st second |
| ~150 chars visible | ~70 chars | Professional proof, no hype | |
| — | Subject ≤45 chars + preheader | Curiosity or benefit, never clickbait-lie |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 57 lines · 103 tokens per session scan A feac24fe9a02
sc:ad-copywriting is a skill published in the GitHub repository squadcodercom/squadcoder (11 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 836 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
product-capability
Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ecc-native PRD-to-SRS lane instead of vague planning prose.
kl-consistency-test
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.
harness-setup
HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.