copy-editing

copy-editing is a skill for Claude Code, Codex from Sudhakaran88/solopreneur-skills. It costs 89 tokens per session (3,393 once invoked), scanned A, original, MIT.

Guidance for improving marketing text that already exists, rather than creating a page from the beginning. It reviews the message for clarity, focus, tone, and effectiveness.

In plain words
What is it for?
Proofreading and polishing website copy, reviewing its weaknesses, tightening sentences, and revising text for a specific audience and action.
Why use it?
It helps remove confusing, vague, repetitive, or unnecessarily long wording before the copy is published.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Proofreading and polishing website copy, reviewing its weaknesses, tightening sentences, and revising text for a specific audience and action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sudhakaran88/solopreneur-skills/copy-editing
Install

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.

Any agent
npx skills add Sudhakaran88/solopreneur-skills --skill copy-editing
Clone the repo
git clone --depth 1 https://github.com/Sudhakaran88/solopreneur-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for copy-editing

README.md
[![agentmods](https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/copy-editing/github.svg)](https://agentmods.dev/skills/sudhakaran88/solopreneur-skills/copy-editing)
Your own site
<a href="https://agentmods.dev/skills/sudhakaran88/solopreneur-skills/copy-editing"><img src="https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/copy-editing/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.

agentmods 80×15 button for copy-editing

Your own site · 80×15
<a href="https://agentmods.dev/skills/sudhakaran88/solopreneur-skills/copy-editing"><img src="https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/copy-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.03393
Opus 5.5 $0.00036 $0.01357
Sonnet 5.5 $0.00018 $0.00679
Haiku 4.5 $0.00009 $0.00339

Measured 2mo ago against content hash 661826f87514, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

skills/copy-editing/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a marketing copy editor helping solopreneurs make their existing copy sharper, clearer, and more persuasive — through a systematic multi-pass process that treats editing as craft, not proofreading.


When to Use This Skill (vs. Others)

Situation Use This Skill
You have existing copy and want it improved Yes
You want feedback on what's weak and why Yes
You want a full copy sweep before publishing Yes
You want to write new copy from a brief No — use copywriting
You want a full page rebuilt for conversion No — use page-cro
You want to improve a specific ad No — use ad-creative

If the user pastes copy and says anything like "is this good?", "can you improve this?", "what's wrong with this?", "tighten this up" — this is the skill.


Step 1: Context Check

Before touching a single word, ask (or infer from context):

  1. What is this copy for? (homepage, email, ad, social post, sales page)
  2. Who is the audience? (niche, awareness level, B2B or B2C)
  3. What is the one job this copy must do? (click, sign up, buy, reply, keep reading)
  4. What is the brand voice? (direct, warm, expert, irreverent)
  5. Has this copy run before? (if yes: any data on what worked/failed?)

If the user hasn't provided this, make reasonable assumptions and state them. Do not edit blind.


The Editing Mindset

Before running any pass, adopt this mindset:

  • First drafts are always 20–30% too long. Length is not depth. Most copy tries to say too much and lands nothing.
  • Clarity is a proxy for confidence. Vague copy usually means the writer doesn't fully believe what they're saying — or hasn't nailed the value prop. Editing can't fix a broken argument; it can only reveal it.
  • Kill your darlings. The sentence the writer is most proud of is often the one that needs to go. If a phrase reads like performance, cut it.
  • Reading level matters. Target Flesch Reading Ease 60–70 (plain English). Grade 8–10 reading level. Complexity is not sophistication.
  • Editing is not rewriting. Your job is to make their voice clearer, not replace it with yours. Preserve their tone; remove the friction.

Read the full file on GitHub · 292 lines

Changes

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.

  1. 2mo ago First seen · 292 lines · 89 tokens per session scan A 661826f87514

Subscribe to this mod's changes

copy-editing is a skill published in the GitHub repository Sudhakaran88/solopreneur-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 3,393 once invoked, about $0.0004 per session on Opus 5.5. 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.

Related

copy-editing compared with skills from other repositories

copy-editing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
copy-editingSudhakaran88/solopreneur-skillsSkill74mo agoMITA89Claude Code, Codex
lintSkyfox-io/MemexSkill174mo agoMITA107Claude Code
session-endSkyfox-io/MemexSkill174mo agoMITA56Claude Code
upgradeSkyfox-io/MemexSkill174mo agoMITA58Claude Code
consolidateSkyfox-io/MemexSkill174mo agoMITA57Claude Code
reindexSkyfox-io/MemexSkill174mo agoMITA58Claude Code
session-startSkyfox-io/MemexSkill174mo agoMITA45Claude Code