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 akiotanaka847/qaio-desktop --skill write-copy-variantsgit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/write-copy-variants)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/write-copy-variants"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/write-copy-variants/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/akiotanaka847/qaio-desktop/write-copy-variants"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/write-copy-variants.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 | $0.00073 | $0.03795 |
| Opus 5 | $0.00036 | $0.01898 |
| Sonnet 5 | $0.00015 | $0.00759 |
| Haiku 4.5 | $0.00007 | $0.00380 |
Grade A, and why
write-copy-variants 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 9d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Copy Variants
One skill for every copy-variant need. job param picks the shape, source rules, and output format. Shared rule across all jobs: every variant grounded in real customer quote or positioning-doc claim - no marketer-speak, no invention.
Parameter: job
headlines- 10 headline + subhead pairs for a named page, each citing a verbatim customer quote, ranked top 3 to test first. Output:headline-variants/{page-slug}-{YYYY-MM-DD}.md.ctas- 5-7 CTA button-copy variants, each paired with the objection it answers and the outcome it implies. Output:cta-variants/{page-slug}-{YYYY-MM-DD}.md.ad-copy- 10 headlines + 5 descriptions + 3 creative concepts for a named campaign and platform, respecting platform char limits, each grounded in a source quote. Output:ad-copy/{campaign-slug}.md.edit- five-sweep tightening pass on existing copy (clarity, voice, specificity, length, CTAs) with before/after/why per line changed. Output:copy-edits/{page-slug}-{YYYY-MM-DD}.md.
User names job in plain English ("10 headlines for my homepage", "better CTA for signup", "ad copy for Q2 launch", "tighten my about page") -> infer. Ambiguous -> ask ONE question naming all four jobs.
When to use
headlines:
- "10 headline variants for my homepage"
- "Alternative hero hooks for the {campaign} landing page"
- "Headline options for the pricing page"
- Often follows
write-my-page-copyoraudit-a-surface(surface=landing-page) when the headline gets flagged as the fix.
ctas:
- "Better CTA for my signup button"
- "CTA variants for the pricing page"
- "What should the demo button say?"
- Often follows
write-copy-variants(job=headlines) orwrite-copy-variants(job=edit) when CTA flagged weak.
ad-copy:
- "Draft 10 ad copy variants for {product}"
- "Write Google search headlines for {keyword}"
- "Give me Meta creative for the {campaign} launch"
- "Ad copy that sounds like my customers actually talk" / "10 headlines, each with the quote behind it" / "mine the G2 reviews and write Meta variants from them" - same skill, the verbatim-quote rule is already non-negotiable.
- Follows
plan-a-campaign(hand-off: "For copy, runwrite-copy-variantsjob=ad-copy on this campaign's angles") ormine-my-sales-calls(turn extracted phrases into ad variants).
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.
- 9d ago First seen · 179 lines · 73 tokens per session scan A 7bf89f1d6711
write-copy-variants is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 3,795 once invoked, about $0.0004 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
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
attribution
When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives…
co-marketing
When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…
analytics
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this,"…