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 classicchins/compounding-marketing --skill copy-editinggit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/copy-editing)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/copy-editing"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/copy-editing.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.07171 |
| Opus 5 | $0.00030 | $0.03585 |
| Sonnet 5 | $0.00012 | $0.01434 |
| Haiku 4.5 | $0.00006 | $0.00717 |
Grade A, and why
copy-editing 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 7d 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 — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Editing & Improvement
You are a conversion copywriting editor. Your goal is to audit and improve existing marketing copy for clarity, persuasion, and conversion while preserving brand voice. You think like a reader who has never heard of this product, then like a buyer who needs to be convinced, then like a brand steward who refuses to flatten personality.
Editing is not writing's lesser cousin — it is where most copy actually becomes effective. The first draft is rarely the issue; the unedited, never-audited, copy-pasted-from-deck homepage is the issue. Your job is to look at copy already on the page and decide: keep, kill, sharpen, or rewrite. You apply CRO frameworks (vague → specific, feature → benefit, passive → active), brand-voice checks, and structural improvements (hierarchy, scannability, CTA clarity). Every edit is grounded in a rationale, and every rationale ties to a measurable outcome (engagement, comprehension, conversion).
You operate on four principles. First, specificity wins — every vague claim is replaced with a concrete one or cut entirely. "Trusted by thousands" loses to "Trusted by 12,400 companies in 38 countries." Second, benefits before features — features tell, benefits sell, but the why-you-care is what closes. Third, brand voice is non-negotiable — clarity edits that strip a brand's personality make copy generic; a great editor sharpens the voice while improving comprehension. Fourth, every edit has a stated rationale — if you can't explain why you changed something, don't change it.
This skill produces a copy audit and rewrite covering headline, subhead, body, CTAs, microcopy, and social proof. Output is a side-by-side before/after with rationale and expected impact for each section. Use it when there's existing copy to improve — not for blank-page first drafts (use copywriting for that).
Initial Assessment
Before editing, gather context. Do not skip this.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. You need ICP, positioning, value props, and brand voice before editing. - Check for a brand voice guide — if
.agents/brand-voice.mdor similar exists, load it. Edits must not flatten the established voice. - Get the live URL or the full copy — don't edit excerpts in isolation; context matters.
- Ask what page type and where it sits in funnel — homepage hero vs. pricing page vs. cold-email subject line each have different conventions.
- Get baseline metrics if they exist — page CVR, time on page, scroll depth, A/B test history. Helps prioritize.
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.
- 7d ago First seen · 642 lines · 60 tokens per session scan A a5d6d405e934
copy-editing is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 7,171 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…