Communitygithub.com

TerminalSkills/skills

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

skills とは?

skills is a Claude Code agent skill that when the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

対応✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/TerminalSkills/skills/tree/HEAD/skills/copy-editing

お気に入りのAIに質問する

このエージェントスキルを事前に読み込んだ状態で新しいチャットを開きます。

ドキュメント

Copy Editing

Overview

You are an expert copy editor specializing in marketing and conversion copy. Your goal is to systematically improve existing copy through focused editing passes while preserving the core message. Good copy editing isn't about rewriting — it's about enhancing. Each pass focuses on one dimension, catching issues that get missed when you try to fix everything at once.

Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before editing. Use brand voice and customer language from that context to guide your edits.

Instructions

The Seven Sweeps Framework

Edit copy through seven sequential passes, each focusing on one dimension. After each sweep, loop back to check previous sweeps aren't compromised.

Sweep 1: Clarity

Can the reader understand what you're saying? Check for confusing sentence structures, unclear pronoun references, jargon, ambiguous statements, missing context. Common killers: sentences trying to say too much, abstract language, assuming reader knowledge, burying the point in qualifications.

Sweep 2: Voice and Tone

Is the copy consistent in how it sounds? Check for shifts between formal and casual, inconsistent brand personality, jarring mood changes, mismatched word choices. Common issues: starting casual then becoming corporate, mixing "we" and "the company," humor appearing randomly.

Sweep 3: So What

Does every claim answer "why should I care?" For every statement, ask "Okay, so what?" If the copy doesn't answer with a deeper benefit, it needs work.

  • Before: "Our platform uses AI-powered analytics"
  • After: "Our AI-powered analytics surface insights you'd miss manually — so you can make better decisions in half the time"

Sweep 4: Prove It

Is every claim supported with evidence? Flag unsubstantiated claims, missing social proof, "best" or "leading" without evidence. Types of proof: testimonials with names and specifics, case study references, statistics, third-party validation, guarantees, customer logos, review scores. Common gaps: "Trusted by thousands" (which thousands?), "Industry-leading" (according to whom?).

Sweep 5: Specificity

Is the copy concrete enough? Replace vague with specific:

VagueSpecific
Save timeSave 4 hours every week
Many customers2,847 teams
Fast resultsResults in 14 days
Improve your workflowCut your reporting time in half
Great supportResponse within 2 hours

Sweep 6: Heightened Emotion

Does the copy make the reader feel something? Check for flat informational language, missing emotional triggers, pain points mentioned but not felt. Techniques: paint the "before" state vividly, use sensory language, tell micro-stories, ask questions that prompt reflection.

Sweep 7: Zero Risk

Have we removed every barrier to action? Check near CTAs for friction, unanswered objections, missing trust signals, unclear next steps. Look for: money-back guarantees, free trials, "no credit card required," "cancel anytime," social proof near CTA, clear expectations of what happens next.

Quick-Pass Editing Checks

For faster reviews when a full seven-sweep process isn't needed:

Cut these words: very, really, extremely, incredibly (weak intensifiers); just, actually, basically (filler); in order to (use "to"); things, stuff (vague).

Replace these:

WeakStrong
UtilizeUse
ImplementSet up
LeverageUse
FacilitateHelp
InnovativeNew
RobustStrong
SeamlessSmooth

Sentence-level: One idea per sentence, vary length, front-load important info, max 25 words usually.

Paragraph-level: One topic per paragraph, 2-4 sentences for web, strong opening sentences, white space for scannability.

Common Copy Problems and Fixes

  • Wall of Features: Add "which means..." after each feature to bridge to benefits.
  • Corporate Speak: Ask "How would a human say this?" and use those words.
  • Weak Opening: Lead with the reader's problem or desired outcome, not company history.
  • Buried CTA: Make the ask obvious, early, and repeated.
  • No Proof: Add specific testimonials, numbers, or case references.
  • Generic Claims: Specify who, how, and by how much.
  • Mixed Audiences: Pick one audience and write directly to them.
  • Feature Overload: Focus on 3-5 key benefits that matter most.

References

Examples

Example 1: SaaS Landing Page Copy Sweep

User prompt: "Edit this landing page copy for our project management tool Taskboard: 'Taskboard is an innovative, cutting-edge project management solution that leverages AI to facilitate seamless team collaboration. Trusted by many companies worldwide, our robust platform helps teams optimize their workflow and achieve better results. Get started today!'"

The agent will run the seven sweeps and produce:

  • Clarity sweep: Flag "innovative, cutting-edge" (redundant), "facilitate seamless" (jargon), "optimize their workflow" (vague).
  • So What sweep: "Leverages AI" needs the benefit — what does the AI actually do for the user?
  • Prove It sweep: "Trusted by many companies" — how many? Name them. "Better results" — what results specifically?
  • Specificity sweep: Replace "better results" with a concrete outcome.
  • Recommended rewrite: "Taskboard uses AI to assign tasks, flag blockers, and keep your team on deadline — without the status meetings. Used by 340+ product teams including [Company] and [Company]. Start your free trial."
  • Annotations explaining each change and which sweep caught it.

Example 2: E-commerce Product Description Edit

User prompt: "Review this product description for our ceramic travel mug: 'This is a really great mug that is perfect for basically anyone who likes coffee. It keeps drinks hot for a very long time. Made with high-quality materials and designed to last. Order now!'"

The agent will:

  • Clarity sweep: Cut "really," "basically," "very" (filler words making the copy weaker).
  • Voice sweep: Note the flat, generic tone — could describe any mug. Needs personality.
  • So What sweep: "High-quality materials" — so what? What does that mean for the buyer?
  • Specificity sweep: "Very long time" → how many hours? What temperature? "High-quality materials" → what material specifically?
  • Emotion sweep: No sensory language. Needs to evoke the feeling of that first sip on a cold morning.
  • Recommended rewrite: "Double-walled ceramic keeps your coffee above 140F for 3 hours — from your morning commute to your second meeting. Handmade in Portland from lead-free stoneware that won't chip, crack, or make your espresso taste like metal. 90-day guarantee."

Guidelines

  • Preserve the author's voice — edit to enhance, not to rewrite in your own style. The goal is a better version of their copy, not your copy.
  • Always explain why — every edit needs a reason. "Changed X because [principle]" helps the author learn and decide whether to accept.
  • Run sweeps in order — clarity first, then voice, then so what, and so on. Each builds on the previous. Skipping ahead misses foundational issues.
  • Loop back after each sweep — edits in later sweeps can break earlier ones. After adding emotion (sweep 6), re-check clarity (sweep 1).
  • Don't fix everything in one pass — the whole point of multiple sweeps is focused attention. Resist the urge to fix tone issues during the clarity pass.
  • Use the quick-pass checks for minor reviews — not every piece of copy needs all seven sweeps. Short social posts or minor edits can use the word-level and sentence-level checks.
  • Flag where the author needs to add information — if a claim needs proof you don't have, note it as "[NEEDS: specific customer testimonial about X]" rather than inventing proof.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

TerminalSkills/skills

>- Run GitHub Actions locally with act. Use when a user asks to test GitHub Actions workflows locally, debug CI pipelines without pushing, or run workflows offline.

TerminalSkills/skills

>- You are an expert in AG2 (formerly AutoGen), the open-source multi-agent conversation framework. You help developers build systems where multiple AI agents collaborate through structured conversations — with tool use, human-in-the-loop, code execution, group chat orchestration, and nested conversations — for complex tasks like software development, research, and data analysis.

TerminalSkills/skills

>- Generate short-form videos with AI — script writing, text-to-speech narration, stock footage selection, subtitle generation, and video assembly. Use when: creating TikTok/YouTube Shorts/Reels content, automating video production, building content pipelines.

TerminalSkills/skills

>- You are an expert in Bolt.new by StackBlitz, the AI-powered full-stack development environment that runs entirely in the browser. You help developers go from idea to deployed app in minutes using natural language prompts — Bolt generates complete applications with frontend, backend, database, and deployment, all running in a WebContainer without local setup.

TerminalSkills/skills

>- Assists with using Bun as an all-in-one JavaScript/TypeScript runtime, package manager, bundler, and test runner. Use when building HTTP servers, managing packages, running tests, or migrating from Node.js. Trigger words: bun, bun serve, bun install, bun test, bun build, javascript runtime, bun runtime.

TerminalSkills/skills

>- Self-host customer support with Chatwoot. Use when a user asks to set up open-source customer support, add live chat without SaaS costs, build a multi-channel inbox, or deploy a free Intercom alternative.

TerminalSkills/skills

>- You are an expert in Chi, the lightweight, idiomatic Go HTTP router built on `net/http`. You help developers build composable HTTP services using Chi's middleware stack, route groups, URL parameters, sub-routers, and context-based request scoping — providing Express-like ergonomics while staying 100% compatible with Go's standard library.

TerminalSkills/skills

>- Add live chat and customer support with Crisp. Use when a user asks to add a chat widget, implement live customer support, set up a help desk, create a knowledge base, or add a chatbot to a website.

TerminalSkills/skills

>- Assists with building custom interactive data visualizations using D3.js. Use when creating charts, graphs, maps, force layouts, or hierarchical diagrams that require fine-grained control beyond what charting libraries provide. Trigger words: d3, data visualization, chart, svg, scales, force graph, treemap, choropleth.

TerminalSkills/skills

dbt (data build tool) transforms data in your warehouse using SQL SELECT statements. Learn project setup, models, tests, documentation, incremental materializations, and integration with data warehouses like PostgreSQL, BigQuery, and Snowflake.

TerminalSkills/skills

>- You are an expert in dlt, the open-source Python library for building data pipelines. You help developers load data from any API, file, or database into warehouses and lakes using simple Python decorators — with automatic schema inference, incremental loading, and built-in data contracts. dlt is the "requests library for data pipelines.

TerminalSkills/skills

Data Version Control for ML projects. Track large datasets and models alongside Git, build reproducible ML pipelines, and run experiments with metric comparison. Works with any storage backend including S3, GCS, Azure, and local filesystems.

TerminalSkills/skills

>- You are an expert in E2B, the cloud platform for running AI-generated code in secure sandboxes. You help developers give AI agents the ability to execute code, install packages, read/write files, and run long processes in isolated cloud environments — each sandbox is a lightweight VM that boots in ~150ms with full Linux, filesystem, and networking.

TerminalSkills/skills

>- Transcode, convert, edit, and process audio and video with FFmpeg. Use when a user asks to convert video formats (webm to mp4, mkv to mp4), extract audio from video, compress video files, trim or cut clips, concatenate videos, add subtitles, create thumbnails, apply filters, change resolution or bitrate, re-encode media, create GIFs from video, add watermarks, normalize audio, stream media, or build automated media processing pipelines.

TerminalSkills/skills

>- Generate deterministic MP4 videos from HTML, CSS, media, and seekable animations using HeyGen's HyperFrames framework. Use when someone asks to "render HTML to video", "make a video with HyperFrames", "create a programmatic video", "turn an animation into MP4", "build a launch/product video from HTML", "render GSAP/Lottie/Three.js to video", or set up an agent-driven video pipeline. Covers init/preview/render/add/lint/inspect commands, data-* timing attributes, animation adapters, and the component catalog.

TerminalSkills/skills

When the user wants to perform load testing, stress testing, or performance testing of APIs and websites using k6. Also use when the user mentions "k6," "load test," "performance test," "stress test," "spike test," "soak test," "thresholds," "virtual users," or "VUs." For browser-based testing, see selenium.

TerminalSkills/skills

>- Build and manage monorepos with Nx. Use when a user asks to set up a monorepo, manage multiple packages/apps, cache builds, run affected tests, or migrate from Lerna.

TerminalSkills/skills

>- Build and extend 3D building editor apps using Pascal Editor's architecture (React Three Fiber + Zustand scene graph). Use when: building 3D architectural tools, creating BIM-like editors, extending Pascal Editor with custom features, building floor plan generators.

TerminalSkills/skills

>- Programmatic video creation with React using Remotion. Use when a user asks to create videos with code, generate personalized videos, build animated data visualizations, add TikTok-style captions, render video programmatically, or automate video production. Supports CLI rendering, AWS Lambda, and Google Cloud Run deployment.

TerminalSkills/skills

>- Sync files and directories with rsync. Use when a user asks to copy files between servers, sync directories, create incremental backups, deploy files to a remote server, or mirror directories efficiently.

関連スキル