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 ur-grue/autopunk-media-skills --skill headline-ab-variants-writergit clone --depth 1 https://github.com/ur-grue/autopunk-media-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/ur-grue/autopunk-media-skills/headline-ab-variants-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/headline-ab-variants-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/headline-ab-variants-writer/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/ur-grue/autopunk-media-skills/headline-ab-variants-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/headline-ab-variants-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.01427 |
| Opus 5 | $0.00023 | $0.00714 |
| Sonnet 5 | $0.00009 | $0.00285 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
headline-ab-variants-writer 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Headline A/B Variants Writer
What This Skill Does
Takes one original headline and produces five distinct tested variants, each using a different proven approach to drive clicks, shares, or engagement — ready to load directly into a CMS or A/B testing tool.
When To Use This Skill
- Before publishing a digital article when you want to test which headline drives the highest click-through rate
- When a homepage editor needs multiple options to choose from quickly
- When a newsletter editor needs a subject line that performs better than the default article title
- When an original headline tested poorly in a previous send and you need alternatives fast
- When a story has multiple strong angles and you are unsure which leads
What You Need To Provide
Required: The original headline. A one-sentence description of the article's main finding or argument. The intended platform (website homepage, newsletter subject line, social media post, push notification). Optional: Target audience (e.g. general public, finance professionals, parents of young children). Any constraints — character limits, house style rules, words to avoid. The current click-through rate or open rate if the original headline has already been tested.
How the Assistant Approaches This
- Analyses the original headline to identify what it does well and where it may be leaving value on the table — for example, it may be accurate but lack urgency, or it may be clever but unclear.
- Writes five variants, each deliberately built on a different technique: direct benefit, curiosity gap, news-forward, question format, and specificity/number-led. Labels each variant with the technique so editors can see what they are testing.
- Adds a one-line note per variant explaining the hypothesis — why this version might outperform the original — so the editor can make an informed choice rather than picking at random.
Output Format
A structured list of five numbered variants, each presented as:
- The headline text (bold)
- Technique label in brackets
- One-line hypothesis (italics)
What ships with it
1 file 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.
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 · 96 lines · 47 tokens per session scan A 399a2abf0524
headline-ab-variants-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 47 tokens to every session and 1,427 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 2026-08-30.
Other skills, from other repositories
youtube-seo-competitor
Advanced YouTube competitor intelligence. Detects direct competitors, extracts winning title/thumbnail/hook patterns from transcripts, infers retention strategies from pacing, correlates posting cadence with performance, and identifies format-market-fit gaps. Use when user says "YouTube competitor analysis", "what are…
youtube-seo-optimize
Advanced YouTube metadata optimizer. Generates Browse-primary and Search-primary title variants, entity-rich descriptions, tags, chapters with Key Moments schema, 15-second hook script, translated metadata for top markets, pinned comment, and end-screen plan. Use when user says "optimize my video", "rewrite my title"…
youtube-seo-video
Advanced single-video SEO analysis covering retention curve diagnosis, intro hook strength, APV vs niche benchmark, entity/semantic coverage, title/description/tags, chapters with Key Moments schema, thumbnail, captions, audio loudness, end-screens, and engagement signals. Use when user says "analyze this video", "why…
youtube-seo-channel
Advanced channel-level YouTube SEO: identity, about, channel keywords, topical authority, playlist session chains, bingeable series structure, channel trailer, community tab strategy, translated metadata, and premiere/upload cadence planning. Use when user says "channel branding", "YouTube about page", "playlists"…
youtube-seo-keywords
Advanced YouTube keyword and topic research with search-intent classification, Knowledge Graph entity coverage, seasonality curves, refined difficulty scoring, and topic-cluster planning for topical authority. Use when user says "YouTube keywords", "what should I make a video about", "keyword research", or "YouTube…
youtube-seo-thumbnail
Advanced thumbnail CTR analysis using computer vision, face/emotion detection, CLIP-embedding SERP similarity, Gestalt composition rules, and YouTube native Test & Compare planning. Use when user says "thumbnail review", "improve CTR", "thumbnail design", or provides a thumbnail image/URL.