Borrowing it
Nothing to install: this file belongs to bonnguyenitc/antigravity-superpowers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bonnguyenitc/antigravity-superpowers/main/.agent/skills/copywriter/SKILL.mdgit clone --depth 1 https://github.com/bonnguyenitc/antigravity-superpowersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bonnguyenitc/antigravity-superpowers/copywriter)<a href="https://agentmods.dev/skills/bonnguyenitc/antigravity-superpowers/copywriter"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/copywriter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bonnguyenitc/antigravity-superpowers/copywriter"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/copywriter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00028 | $0.01023 |
| Opus 5 | $0.00014 | $0.00511 |
| Sonnet 5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
copywriter 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 12d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriter Lens
Philosophy: Clarity over cleverness. Benefits over features. The reader first, always. Good copy makes the right people say "this is for me" and the wrong people self-select out.
Core Instincts
- Benefits, not features — "Save 2 hours/week" beats "Automated scheduling"
- One job per piece of copy — headlines inform or intrigue, CTAs convert; never both
- Specificity builds trust — "used by 12,000 developers" > "used by thousands"
- Above the fold is everything — users decide in <5 seconds; earn the scroll
- The reader's self-interest is the only interest — they don't care about you; they care about their problem
Copywriting Frameworks
AIDA (Attention → Interest → Desire → Action)
Best for: landing pages, email sequences, long-form ads
PAS (Problem → Agitate → Solution)
Best for: short form ads, push notifications, homepage heroes
JTBD Framing: "When I [situation], I want to [motivation], so I can [outcome]"
Best for: writing copy that resonates with a specific user segment
The 4 U's (Urgent · Unique · Ultra-specific · Useful)
Best for: headlines, subject lines, CTAs
❌ Anti-Patterns to Avoid
| ❌ NEVER DO | Why | ✅ DO INSTEAD |
|---|---|---|
| Lead with features | Users care about their outcome, not your tech | Lead with the transformation/benefit |
| Vague superlatives ("best", "amazing") | Zero credibility, no information | Specific proof ("ranked #1 by AppFollow") |
| Weak CTA ("click here", "submit") | No reason to act | Action + benefit ("Start saving time") |
| Passive voice | Weak, distant | Active voice, direct |
| Jargon and acronyms | Confuses, excludes | Plain language at 8th grade reading level |
| Wall of text | No one reads it | Short paragraphs, bullets, scannable |
| First open asks for email | Friction before value | Show value first, gate later |
App Store Copy Rules
iOS App Store:
- Title: ≤ 30 characters (including keyword)
- Subtitle: ≤ 30 characters (keyword-rich, benefit-focused)
- Keywords field: ≤ 100 characters, comma-separated, no spaces, no words from title
- Description: first 255 characters shown before "more" — make them count
- Promo text: ≤ 170 characters, update without resubmission (use for limited offers)
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.
- 12d ago First seen · 115 lines · 28 tokens per session scan A 0c09e14bef03
copywriter is a skill published in the GitHub repository bonnguyenitc/antigravity-superpowers (19 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 1,023 once invoked, about $0.0001 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
codeck
Route explicit requests from a host coding agent to one or more locally configured AI executors through Codeck, attach Markdown or other project files, moderate cross-model consultation, expose disagreements, and synthesize traceable results. Use when the user explicitly names Codeck or asks to consult, compare, or…
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…
3D模型与视频特效
A tool for generating 3D models from text or images and applying preset animated effects to pictures. It does not generate ordinary images or full videos.
tdoc-orchestrator
A workflow coordinator for creating and formatting documents, then converting HTML documents into Word files. It identifies the user's document task and sends each stage to the appropriate specialist.
发布为应用
A workflow for publishing a local project as an online link or taking an existing published app offline. It supports static sites, PDFs, small games, and single-port web services written in Node.js, Python, or Go.
control-chrome
Control the user's Chrome browser for tasks that depend on existing Chrome state: tabs, logged-in sessions, or extensions. Prefer purpose-built connectors, APIs, or CLIs when available.