
Technical Writing
OfficialFreeCreate precise documentation for the eve repository.
Free · Opens the source repo
What Technical Writing does
The Technical Writing skill is designed for developers and technical writers working with the eve repository. It provides a structured approach to writing, editing, reviewing, and auditing user-facing documentation that is clear and task-focused. The skill emphasizes the importance of treating developers and AI agents as the primary audience, ensuring that each section is easy to scan, retrieve, and act upon without relying on unstated context. This is crucial for effective communication, especially in technical environments where clarity is paramount.
To facilitate the documentation process, the skill outlines specific workflows based on the type of changes you are making. For new pages or complete rewrites, you can follow the writing workflow, while targeted changes to existing documentation are guided by the editing workflow. Before finalizing any modifications, the review framework ensures that all changes meet the necessary quality standards. Additionally, references to style rules and prose quality help maintain consistency and professionalism in the documentation.
One of the key aspects of this skill is the emphasis on verification. It encourages users to rely on current source material, CLI help, and existing documentation rather than assumptions based on outdated training data. This approach minimizes the risk of inaccuracies in the documentation and ensures that it reflects the most current state of the eve repository. By verifying commands, flags, and API names against the latest sources, you can create documentation that is not only accurate but also useful for users.
Overall, this skill is ideal for anyone involved in maintaining or improving documentation for the eve repository. Whether you are a developer looking to clarify API behavior or a technical writer aiming to enhance user understanding, the Technical Writing skill provides the necessary tools and guidelines to produce high-quality documentation.
When to use it
Use this skill when you need to create or update documentation for the eve repository, particularly when clarity and accuracy are critical.
When not to use it
This skill is not suitable for general writing tasks outside the context of technical documentation for the eve repository.
What you can build with it
Creating New Documentation Pages
When starting from scratch, follow the writing workflow to ensure your new documentation is structured and clear.
Updating Existing Documentation
Use the editing workflow to make targeted changes to existing documentation, ensuring accuracy and relevance.
Conducting Documentation Reviews
Before finalizing any changes, utilize the review framework to maintain high quality and consistency in your documentation.
How to install Technical Writing
View source1. Install with the skills CLI
npx skills add vercel/eve/technical-writing --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by vercelTechnical writing
Write accurate, task-focused documentation for eve. Treat developers and AI agents as readers: make each section easy to scan, retrieve, and act on without relying on unstated context.
Choose a workflow
- For a new page or full rewrite, read references/writing-workflow.md.
- For targeted or structural changes to existing pages, read references/editing-workflow.md.
- Before finalizing any change, read references/review-framework.md.
- For formatting and terminology, read references/style-rules.md.
- For wording, voice, or AI-pattern concerns, read references/prose-quality.md.
- For page structure, read references/content-types.md when the content type is unclear or changing.
Verify before writing
Do not rely on training data for eve behavior. Use this source hierarchy:
- Current source, public types, and tests in
packages/eve - Current CLI help and setup implementation
- Existing pages under
docs/ - Merged pull requests, changelogs, and release notes
- Research plans under
research/as proposed intent, not shipped behavior - Support evidence such as Slack threads or issues
Use support evidence to identify the reader's problem, not to establish product behavior. Verify commands, flags, API names, defaults, limitations, and examples against the current repository. For a docs-only change, also compare the implementation with the latest public release so the docs do not announce branch-only behavior. When docs accompany product code in the same change, state that dependency during review. If a claim cannot be verified, omit it or report the missing owner or source. Never leave [VERIFY] markers in a completed docs change.
Follow eve conventions
- Write
evelowercase, including headings and sentence starts when practical. - Use exact public names such as
defineAgent,eve dev, andeve add channel/slack. - Distinguish the root agent, the built-in
agenttool, declared subagents, and remote agents. They have different inheritance and execution semantics. - Distinguish eve connections from Vercel Connect, the model-facing
Workflowtool from authored Vercel Workflows, and durable session state from sandbox filesystem or attachment storage. - Name diagnostic surfaces precisely: Vercel runtime logs, Agent Runs, OpenTelemetry,
eve logs, andeve tracesare not interchangeable. - Treat
docs/**as published documentation. Updatedocs/meta.jsonwhen navigation changes. - Keep
.mdfiles framework-agnostic. Use MDX components only in.mdxfiles and only when nearby pages establish the convention. - Preserve published routes and heading anchors when possible. When moving a page, update authored links and add permanent redirects for old HTML and Markdown URLs.
- Prefer TypeScript examples. Include imports and language labels, and verify examples against current exports.
- Show only supported commands and flags. Check CLI help or the command implementation before documenting them.
- Link to related pages with descriptive text. Include the critical fact locally because retrieved sections may be read without their links.
- Do not document proposed behavior as shipped. Describe unsupported boundaries directly when they affect a user task.
Write for the task
- Lead each page and section with the answer or outcome.
- Address the reader as
you; use imperative verbs for steps. - Prefer active voice, present tense, concrete nouns, and consistent terms.
- Preserve the author's supported meaning, nuance, and uncertainty. Make the minimum effective edit and leave strong prose alone.
- Keep one page focused on one primary job. Add a section to an existing page when it already owns the task.
- Put the happy path before alternatives and failure modes.
- Add troubleshooting where observed failures cluster around a workflow. Use symptoms, verified causes, and concrete next checks.
- Write self-contained sections. Repeat the full noun in key statements instead of relying on ambiguous pronouns.
- Use specific limits and behavior only when the repository or an authoritative platform source supports them.
Avoid common failures
- Do not invent flags, registry entries, connectors, workarounds, or platform guarantees.
- Do not turn one product request into a new page. First decide whether the gap belongs to docs, product, or both.
- Do not duplicate broad guides when a focused section or cross-link resolves the problem.
- Do not rewrite clear prose merely to match a personal preference.
- Do not manufacture examples, opinions, reactions, or specificity to make prose sound more human.
- Do not use promotional language, rhetorical questions, filler, or claims that a task is easy, simple, or quick.
- Do not use
weunless describing a deliberate Vercel or eve team action.
Finish the change
- Re-read every changed page in full.
- Verify each new technical claim against its source.
- Search for contradictory statements and affected cross-links.
- Run the review workflow.
- Check changed prose against the prose-quality reference when wording changed materially.
- Run
pnpm docs:checkwhen preparing to push, unless the user requests earlier validation.
Frequently asked questions about Technical Writing
Similar skills
Supabase Docs Authoring
Streamline your Supabase documentation process.
Docs Writer
Streamline your documentation process with precision.
Clinical Case Report
Generate structured medical case presentations.
CrossFrame Suite
Streamline complex workflows for Chinese structural analysis.
Em Dash Expert
Master the em dash for clear, precise writing.
Nature Statistics Reporting
Enhance manuscript statistics for high-impact journal submissions.
