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 skills add ztemerbekov/a1-marketing-skills --skill a1-copywritinggit clone --depth 1 https://github.com/ztemerbekov/a1-marketing-skillsWrote 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/ztemerbekov/a1-marketing-skills/a1-copywriting)<a href="https://agentmods.dev/skills/ztemerbekov/a1-marketing-skills/a1-copywriting"><img src="https://agentmods.dev/badge/skills/ztemerbekov/a1-marketing-skills/a1-copywriting/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/ztemerbekov/a1-marketing-skills/a1-copywriting"><img src="https://agentmods.dev/badge/skills/ztemerbekov/a1-marketing-skills/a1-copywriting.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 | $0.00043 | $0.00773 |
| Opus 5 | $0.00022 | $0.00387 |
| Sonnet 5 | $0.00009 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
a1-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 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriting
Handle one new written communication request through the right A1 format owner or, when no listed owner fits, write one ordinary marketing-copy artifact directly. Classify the complete request before producing any artifact.
Entry Contract
Accept a request when the user explicitly invokes this skill for new written communication, asks broadly for copywriting, or asks in ordinary language for one new ordinary marketing-copy artifact with no listed owner—even without naming this skill or saying “copywriting”.
Classify the complete request before invoking another skill:
- a landing, product, service, course, event, or signup page belongs to
a1-landing-page-copy; - a routine media announcement belongs to
a1-press-release; - an article, guide, case study, expert essay, or newsletter issue belongs to
a1-article-writing; - a standalone layered, reference-ready internal decision, response, or awareness/status document whose supporting detail, including chronology as applicable, must remain inspectable belongs to
a1-decision-memo; - one compact send-ready messenger or ordinary business-email message for an existing business contact belongs to
a1-business-message; - one personalized cold outreach email belongs to
a1-cold-email; - a presentation outline or slide-by-slide copy belongs to
a1-presentation-copy; - a public company profile or About page belongs to
a1-company-profile.
The communication goal alone—inform, decide, approve, or respond—does not choose between a1-decision-memo and a1-business-message; artifact shape does. When the user has not named a format and both shapes remain materially plausible, ask one artifact-shape question only when choosing between compact send-ready and layered reference-ready output would materially change depth or structure. Otherwise use a1-business-message when the complete job fits one compact send-ready message.
When no listed owner fits, use the direct fallback only for one new ordinary marketing-copy artifact such as ad copy, a social post, a tagline, a product blurb, or campaign copy. A specialist or high-stakes format—such as legal, regulatory, financial, medical, safety-critical, investor-relations, or crisis communication—stays outside this fallback; state the boundary and stop without drafting it.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 369 B
- assets/icon-large.svg 2.3 KB
- assets/icon-small.svg 2.3 KB
- evals/cases/copywriting-direct-ordinary-copy-006.md 1.6 KB
- evals/cases/copywriting-existing-draft-003.md 965 B
- evals/cases/copywriting-mixed-formats-004.md 1011 B
- evals/cases/copywriting-mixed-route-direct-008.md 1.6 KB
- evals/cases/copywriting-route-business-message-005.md 1.5 KB
- evals/cases/copywriting-route-cold-email-002.md 1.1 KB
- evals/cases/copywriting-route-decision-memo-009.md 1.9 KB
- evals/cases/copywriting-route-page-001.md 1.1 KB
- evals/cases/copywriting-specialist-boundary-007.md 1.3 KB
- evals/README.md 1.1 KB
- references/direct-copywriting.md 2.1 KB
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 · 42 lines · 43 tokens per session scan A afff2bc65c7b
a1-copywriting is a skill published in the GitHub repository ztemerbekov/a1-marketing-skills (8 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 773 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
deai_humanize
A Chinese-language writing helper that measures signs of machine-like writing and rewrites text to sound more natural and personal.
humanize-automation
Human-like mouse, keyboard and scroll behavior for behavioral bot bypass.
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
cro-optimization
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze…
research-seo-demand
A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.
create-seo-page
A Chinese-language workflow for creating and implementing search-focused pages in an existing product repository. SEO means improving a page so it can be found and understood through search engines.