Agent skill

Product Writing

by scarletkc in scarletkc/agents

Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup, compatibility, or technical results.

Apache-2.0Auto-check passedDevelopment

Install Product Writing

skills CLI
$ npx skills add scarletkc/agents --skill product-writing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install scarletkc/agents product-writing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/product-writing .claude/skills/product-writing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
product-writing
GitHub stars
226
Token cost
~2.4k tokens
SKILL.md length
1,351 words
Files
2
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup, compatibility, or technical results.

  • Tasks that involve Technical documentation
  • SKILL.md covers Work from the task, Interface copy, errors, and help, Status and diagnostic output and Documentation and technical…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Product Writing is an agent skill from scarletkc/agents. Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup, compatibility, or technical results.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `evals/evals.json`).

It sits in Development, covering Technical documentation. The repository describes itself as: Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Technical documentation

Example prompts

  • “/product-writing”

What it can do on your machine

Read from SKILL.md and the folder at commit eb55005. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Product Writing loads about 2.4k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 1,351 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from scarletkc/agents at commit eb55005, republished under its Apache-2.0 licence (© scarletkc). 1,351 words, ~2,425 tokens.

Download SKILL.mdSave it as .claude/skills/product-writing/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
product-writing
description
Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup, compatibility, or technical results.
license
Apache-2.0
metadata.author
scarletkc
metadata.source
https://github.com/scarletkc/agents
metadata.summary
Write accurate product copy and useful technical docs.

Product Writing

Help the reader understand what is happening and what they can do next.

Work from the task

Use only the sections relevant to the requested copy. Preserve the user's meaning, terminology, audience, and requested format. Follow existing product conventions where they help readers recognize controls, commands, and states. A wording task does not itself authorize changes to product behavior or a reorganization of the documentation.

Ground behavioral claims in supplied facts, the relevant implementation or specification, or an observed result. When a fact cannot be verified, identify that uncertainty where it matters and complete the parts that are supported. Do not invent behavior or a cause to make the text sound complete.

Interface copy, errors, and help

  • Name the action or state accurately. Distinguish saving a setting from testing a connection, accepting a request from completing a job, and partial success from full success. For example, a queued export should not announce that a file is ready to download.
  • Make recovery useful. Identify what failed and the relevant input or operation. Include a next step when it is known and actionable. An unknown network failure does not establish that credentials are wrong. Put detail in the message, an expanded view, or a specific help link as the interface allows; an error need not fill a fixed template.
  • Preserve meaningful distinctions. Keep prerequisites, limits, and consequences that affect the reader's decision. Use the product's names for controls and commands. Do not shorten away which item an action affects or imply that an irreversible action is temporary.

Status and diagnostic output

  • Describe the state the label promises. Effective settings account for runtime overrides; stored settings should be identified as such. If only the API key comes from the environment, label that field rather than the entire endpoint as environment-provided.
  • Keep failure visible. Distinguish unknown or unavailable values from empty, missing, or default values. If partial results are supported, identify what could not be checked. Follow the project's failure behavior instead of introducing a fallback merely to produce a message.
  • Preserve output contracts. Keep prose and decoration out of JSON, TSV, and other machine formats. Use existing diagnostic channels for explanations. Keep paths, IDs, and commands complete where users need to copy them, subject to the product's redaction rules.
  • Give diagnostic views distinct jobs. When a dedicated inspection command already provides all values and origins, a health summary can focus on deviations, failures, and their sources, with a pointer to full details. Without that separate view, preserve the values needed to investigate the problem. Fifteen normal field: origin rows can bury the two overrides that matter, but removing the only available configuration view loses information. Re-read adjacent labels to catch duplication such as default (default).

Documentation and technical explanations

  • Give each page one responsibility. A how-to completes an operation, a reference defines a contract, a design record explains choices, and a report presents findings and their basis. Put a section on the page that owns its reader question. When a page mixes independent tasks, separate them and leave a useful pointer at the boundary. An overview's responsibility is orientation: summarize the available paths and link to their details instead of becoming a second reference manual.
  • Keep README sections focused. The introduction identifies the product, its audience, and its purpose. Positioning explains why someone would choose it. Quick-start instructions give the shortest complete path to a useful result, including prerequisites, commands, and essential caveats. Full option catalogs, architecture explanations, and decision histories belong in their respective documents, linked from the relevant section. Do not turn a quick start into an architecture tour or a positioning section into a feature dump. Keep a compatibility warning beside the step it affects; moving background detail must not hide a condition needed to follow the instructions safely.
  • Keep reasons near the decisions they support. A setup step may need a short explanation of why a prerequisite matters. A long history of rejected designs usually belongs in a design record linked from the guide, unless that history is the page's purpose. Reports need enough method, source context, assumptions, and limitations for readers to assess the findings.
  • Separate summaries from competing specifications. Keep one maintained source for a detailed contract. A summary explains what the reader needs now; a second complete field table, default list, or precedence rule creates another specification to maintain. For example, a README can show a minimal configuration and link to the full schema instead of copying all seven fields into another table. Detailed repetition may be necessary for independently distributed artifacts; check how those copies stay synchronized.
  • Plan how changeable facts stay correct. Supported versions, pinned install commands, and compatibility limits may be necessary. Verify them against the maintained source, then check what will keep them aligned on the next change: generation, an existing release check, or an explicit maintenance responsibility. Avoid adding a second hand-maintained copy of a build ID, migration count, or current deployment version just to make a page self-contained. Prefer a pointer or generated value when the reader needs the current answer. Preserve version constraints that are part of the instructions; do not remove them simply because versions change.
  • Distinguish records from live state. A dated report can record the version and status actually observed, with the evidence and limits of that observation. A standing operational guide should direct readers to the command or dashboard that answers what is running now. A merged change alone does not establish deployment, and a successful deployment alone does not establish every health or verification claim.
  • Make the next reference useful. Link to the section, command, API entry, or symbol that answers the reader's question. For implementation details, PROTOCOL_VERSION is a useful pointer; a repository root leaves the reader to search again. For normal setup, prefer user-facing instructions. Keep caveats next to the steps they qualify and preserve working anchors.
Show full SKILL.md (374 more words)Show less

Comments and standalone artifacts

Read titles, comments, and deliverables as someone who has not seen the working conversation. Remove abandoned options and temporary scope qualifications that make sense only in that conversation. An export button title does not need "without the bulk-download panel" if readers were never offered such a panel. Keep exclusions when they explain a real contract, compatibility limit, or tradeoff the reader needs; preserve history in documents requested to record it.

Comments are most useful for reasons the code does not make apparent: ordering constraints, upstream defects, compatibility workarounds, and invariants a later edit could break. Explain an alternative when it is one a maintainer would reasonably reach for. For example, a comment explaining why a lock must be released before invoking a callback can prevent a deadlock; "release the lock" merely repeats the operation. Do not replace that reason with a shorter restatement of the code. Keep public API documentation and useful algorithm overviews as well.

Claims and evidence

Match the support to the claim. Performance comparisons need applicable measurements or a cited result with its scope. Compatibility claims need the relevant implementation or maintained specification. An editorial recommendation can explain a concrete benefit, such as naming the failed field so the reader can locate it; recommending clearer wording does not require a benchmark.

Keep observations, hypotheses, preferences, and recommendations distinct. Preserve user-provided opinions as opinions. Qualify unsupported claims or explain the gap rather than invent proof or erase useful uncertainty.

Review and verification

In a review, identify the wording, its effect on the reader, and a concrete correction when the evidence supports one. If the copy already works, say so; optional preferences should not become required rewrites. For an editing task, make the requested edits and explain consequential choices only as needed.

Check meaning, terminology, formatting, and affected links. When behavior changes, search for dependent help text, errors, documentation, and bundled skill descriptions that need the same update. Keep catalog and localization entries in sync where applicable; avoid turning a small edit into a general audit.

Use the project's relevant checks. When output behavior changes, cover success and failure: parse machine formats and check channels; for human messages, assert the relevant information without relying on incidental wrapping or color.

© scarletkc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/product-writing of scarletkc/agents.

  • SKILL.md
  • evals/evals.json

Open the folder on GitHubat commit eb55005

Compare with similar skills

Product Writing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Product Writing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Product Writing this skillscarletkc/agents226—~2.4kAutomated safety check: PassApache-2.0
Diagram Designcathrynlavery/diagram-design49k1 repos~7.6kAutomated safety check: PassMIT
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
Doc SyncJetBrains/ideavim10k2 repos~2.6kAutomated safety check: PassMIT
Mailspring App ScreenshotsFoundry376/Mailspring18k—~1.5kAutomated safety check: PassGPL-3.0
Draw.io Diagram StudioAgents365-ai/drawio-skill10k—~2.4kAutomated safety check: NotesMIT

Similar skills

  • Diagram Design

    cathrynlavery/diagram-design

    Creates branded diagrams, from architecture, flowchart and sequence to charts and maps, as self-contained HTML with inline SVG, with import from draw.io, Mermaid and Excalidraw.

    49k GitHub starsUsed in 1 repo~7.6k tokens
    DevelopmentAuto-check passed
  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed
  • Doc Sync

    JetBrains/ideavim

    Official

    Keeps IdeaVim documentation in sync with code changes. An agent skill from JetBrains/ideavim.

    10k GitHub starsUsed in 2 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Mailspring App Screenshots

    Foundry376/Mailspring

    Captures screenshots of the running Mailspring dev app for docs, PRs or visual checks by launching it with a debugging port, driving the UI and clipping to an element.

    18k GitHub stars~1.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Draw.io Diagram Studio

    Agents365-ai/drawio-skill

    Creates and edits editable draw.io diagrams from descriptions, code, infrastructure files, SQL and API schemas, with sync, review, test and export tools.

    10k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check: notes
  • Dark Architecture Diagram Builder

    Cocoon-AI/architecture-diagram-generator

    Creates dark-themed system, cloud, security and network architecture diagrams as self-contained HTML files with inline SVG and CSS.

    7.4k GitHub starsUsed in 1 repo~2.1k tokens
    DevelopmentAuto-check passed

More from scarletkc/agents

All 11 skills in this repo
  • Antigravity CLI

    scarletkc/agents

    Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent.

    226 GitHub stars~1.6k tokensUpdated 19 days ago
    Auto-check passed
  • Grok CLI

    scarletkc/agents

    Delegate bounded tasks to Grok Build from a supervising agent such as Codex.

    226 GitHub stars~1.5k tokensUpdated 19 days ago
    Auto-check: warnings
  • Talk Like Scarletkc

    scarletkc/agents

    按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本,适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔,或在翻译中保留本人语气和立场时使用,无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。

    226 GitHub stars~1.2k tokensUpdated 19 days ago
    Auto-check passed
  • Ask To Plan

    scarletkc/agents

    Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices.

    226 GitHub stars~2.4k tokensUpdated 19 days ago
    Auto-check passed
  • Codex CLI

    scarletkc/agents

    When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model and reasoning effort.

    226 GitHub stars~2.8k tokensUpdated 19 days ago
    Auto-check passed
  • Marketing Copy

    scarletkc/agents

    Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls…

    226 GitHub stars~1.3k tokensUpdated 19 days ago
    Auto-check passed

Categories

Questions about Product Writing

What does Product Writing do?

Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup, compatibility, or technical results. Product Writing is an agent skill from scarletkc/agents. Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup, compatibility, or technical results.

When should I use Product Writing?

Product Writing fits situations like: tasks that involve Technical documentation.

How do I install Product Writing in Claude Code?

Run `npx skills add scarletkc/agents --skill product-writing -a claude-code`. Or copy the skill folder (skills/product-writing in scarletkc/agents) into .claude/skills/product-writing in your project. Claude Code loads it when a task matches its description.

How do I install Product Writing in Codex?

Run `npx skills add scarletkc/agents --skill product-writing -a codex`. Or copy the skill folder (skills/product-writing in scarletkc/agents) into .agents/skills/product-writing in your project. Codex loads it when a task matches its description.

Can I use Product Writing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add scarletkc/agents --skill product-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-writing, .gemini/skills/product-writing, .github/skills/product-writing and .opencode/skills/product-writing in your project.

What does Product Writing need to run?

SKILL.md names no scripts, command-line tools or credentials: Product Writing is instructions for the agent only.

Does Product Writing access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Product Writing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Product Writing use?

Product Writing is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Product Writing use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Product Writing?

Skills that share tags, products or a category with Product Writing: Diagram Design (cathrynlavery/diagram-design, 49k stars), Simple English (moeru-ai/airi, 50k stars), Doc Sync (JetBrains/ideavim, 10k stars) and Mailspring App Screenshots (Foundry376/Mailspring, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Product Writing?

scarletkc (a GitHub user) maintains it in scarletkc/agents, which has 226 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 21, 2026.

Source: scarletkc/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.