New to Claude Skills? Learn how to install them →

vercel on GitHub

Technical Writing

OfficialFree

Create precise documentation for the eve repository.

by vercel4.5k stars on vercel/eve
1 views
Updated Aug 10, 2026
Get this skill

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users to rely on current source material, CLI help, and existing documentation rather than assumptions based on outdated training data.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 source

1. Install with the skills CLI

npx skills add vercel/eve/technical-writing --agent claude-code

2. 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 vercel

Technical 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

Verify before writing

Do not rely on training data for eve behavior. Use this source hierarchy:

  1. Current source, public types, and tests in packages/eve
  2. Current CLI help and setup implementation
  3. Existing pages under docs/
  4. Merged pull requests, changelogs, and release notes
  5. Research plans under research/ as proposed intent, not shipped behavior
  6. 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 eve lowercase, including headings and sentence starts when practical.
  • Use exact public names such as defineAgent, eve dev, and eve add channel/slack.
  • Distinguish the root agent, the built-in agent tool, declared subagents, and remote agents. They have different inheritance and execution semantics.
  • Distinguish eve connections from Vercel Connect, the model-facing Workflow tool 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, and eve traces are not interchangeable.
  • Treat docs/** as published documentation. Update docs/meta.json when navigation changes.
  • Keep .md files framework-agnostic. Use MDX components only in .mdx files 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 we unless describing a deliberate Vercel or eve team action.

Finish the change

  1. Re-read every changed page in full.
  2. Verify each new technical claim against its source.
  3. Search for contradictory statements and affected cross-links.
  4. Run the review workflow.
  5. Check changed prose against the prose-quality reference when wording changed materially.
  6. Run pnpm docs:check when preparing to push, unless the user requests earlier validation.

Frequently asked questions about Technical Writing

Similar skills