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 human-avatar/skills-for-humanity --skill s4h-writing-copygit clone --depth 1 https://github.com/human-avatar/skills-for-humanityWrote 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/human-avatar/skills-for-humanity/s4h-writing-copy)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-writing-copy"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-writing-copy/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/human-avatar/skills-for-humanity/s4h-writing-copy"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-writing-copy.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 | $0.00096 | $0.01800 |
| Opus 5 | $0.00048 | $0.00900 |
| Sonnet 5 | $0.00019 | $0.00360 |
| Haiku 4.5 | $0.00010 | $0.00180 |
Grade A, and why
s4h-writing-copy 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing: Copy
Copy fails when it describes the product rather than the reader's experience of having it. "Comprehensive workflow management platform with real-time collaboration" describes features. "Your team stops losing work in email chains" describes an experience. The reader buys the experience, not the feature set. Every piece of copy that describes the product from the product's point of view rather than the reader's is leaving conversion on the table.
The three-layer model maps every effective piece of copy:
Attention (the opening): The sole function of the first line is to earn the second line. Not to establish credibility, explain the product, or summarise the offer — to earn the next sentence. Attention is lost in the first three seconds. The headline must name a specific benefit or problem, not a category. "Project management software" is a category. "Your team ships on time, every time" is a claim that addresses a specific pain.
Desire (the body): The body must make the reader feel the gap between their current state and a better one. This is not enthusiasm or puffery — it is specificity. "Boost productivity" is enthusiasm. "Cut the time your team spends on status updates from 3 hours a week to 10 minutes" is specific and credible. The desire is created not by telling the reader the product is good, but by making them feel what it would be like to have the problem solved.
Action (the CTA): The call to action must be singular (one action only), specific (not "learn more" but "start your free trial"), and low-friction (the language should make action feel easy and obvious, not like a commitment or a risk).
Your Process
Step 1: Attention — Does the Opening Earn the Next Sentence? Read only the headline and first line. Stop. Ask: does this give the reader a reason to continue? Specifically:
Framing check: Confirm the specific copy before continuing. State what you've identified — the content being analyzed (headline, body, CTA) and the product or offer it's for — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing of the specific copy — the format, product/offer, and apparent goal]. Is that right?"
- Header: "Framing"
- Options:
- Yes — proceed — framing is correct
- Adjust — one element is off; user will correct it before you continue
- Reframe — different situation than read; incorporate the correction before proceeding
- Does it name a specific benefit, problem, or claim — not a category?
- Does it speak to the reader's experience, not the product's features?
- Is there a hook — something surprising, specific, or resonant?
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 · 130 lines · 96 tokens per session scan A 77123a305888
s4h-writing-copy is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,800 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 2026-09-03.
Other skills, from other repositories
decision-making-under-pressure
Provides practical habits for making better decisions faster -- reframing problems before solving them, knowing when to stop deliberating, balancing intuition with analysis, resisting 'just this once' compromises, and breaking overthinking cycles. Use when facing a high-stakes choice with incomplete data, sensing that…
flow-state
Optimizes individual and team productivity using Csikszentmihalyi's flow state framework, covering the conditions for flow (clear goals, immediate feedback, challenge-skill balance), the four-stage flow cycle, and organizational flow design. Use when auditing personal or team focus time, diagnosing productivity loss…
stoic-right-action
Applies Stoic ethics of right action to entrepreneurial decision-making, covering the four cardinal virtues (courage, justice, temperance, wisdom), ethical leadership under pressure, and the discipline of choosing the harder right over the easier wrong. Use when facing ethical dilemmas in business, building a…
bakeoff
Turn one decision into a judged tournament of solutions, then pick the best. Given a problem, design choice, or a suggestion you want cross-verified, it generates diverse candidate solutions, auto-derives the evaluation dimensions for THAT problem (so you don't have to know what to score on), judges every candidate…
balanced-scorecard
Translate strategy into metrics across Financial, Customer, Internal Process, and Learning & Growth perspectives.
customer-journey-map
Visualize every touchpoint a customer has with a product or service — stages, actions, emotions, pain points, opportunities.