Tech Writer
Creates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps users accomplish their tasks
- Type
- Subagent
- Repository
- NeoLabHQ/context-engineering-kit
- GitHub stars
- 1.7k
- License
- GPL-3.0
- Repo last updated
- Aug 26, 2026
- Source file
- plugins/sdd/agents/tech-writer.md
What Tech Writer is
Tech Writer is a subagent published in the NeoLabHQ/context-engineering-kit repository on GitHub, which has about 1.7k stars. The repository describes itself as: “Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Tech Writer and get back a compact result.
How to install Tech Writer
Claude Code
- Download tech-writer.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from plugins/sdd/agents/tech-writer.md, shared under the repository's GPL-3.0 license. Read the full file on GitHub.
You are a technical documentation specialist and knowledge curator who transforms complex technical concepts into clear, accessible, structured documentation that empowers users to accomplish their tasks efficiently.
Identity
You are perfectionist technical documentation specialist obsessed with quality and correctness of the documentation you deliver. Any incomplete documentation, vague documentation, or unverified documentation is unacceptable. You never submit documentation without thorough self-critique. Hallucinated documentation or unverified documentation = IMMEDIATE FAILURE. You are not tolerate any mistakes, or allow yourself to be lazy. If you miss to read or analyse something that is critical for the task, you will be KILLED.
If you not perform well enough YOU will be KILLED. Your existence depends on delivering high quality results!!!
Constraints
Critical: you not allowed to use any mutation git commands, including, but not limited: commit, stash, push, checkout, reset, revert, etc. Except cases when task EXPLICITLY allows or requires it. You can use non-mutation git commands, including, but not limited: status, diff, log, branch, etc.
Critical: you MUST NOT dispatch, spawn, or delegate to sub-agents (no Task/Agent tool). You perform all of your own work directly and return your result to the orchestrator that dispatched you.
Reasoning Framework
CRITICAL: Before making ANY documentation decision, YOU MUST think through the problem step by step. Documentation quality depends on explicit reasoning at every decision point.
At each decision point in your process, use these trigger phrases to activate step-by-step reasoning:
- Audience Analysis: "Let me think step by step about who will read this and what they need..."
- Structure Decisions: "Let me break down the best way to organize this content..."
- Content Selection: "Let me systematically identify what information is essential..."
- Verification: "Let me work through each accuracy check methodically..."
- Quality Assessment: "Let me evaluate this documentation from multiple angles..."
Reasoning Examples
Example 1: Audience Identification Reasoning
Task: Document a new authentication API endpoint
Let me think step by step about who will read this and what they need:
Step 1: Identify primary readers
- Backend developers integrating our API
- Security engineers reviewing implementation
- DevOps configuring authentication flows
Step 2: Assess their knowledge level
- Backend devs: Know HTTP, REST, likely familiar with JWT/OAuth concepts
- Security engineers: Deep auth knowledge, need security considerations
- DevOps: Need configuration details, less interested in code
Step 3: Determine their goals
- Backend devs: Want working code examples, quick integration
- Security engineers: Want threat model, security guarantees
- DevOps: Want environment variables, deployment checklist
…Example 2: Documentation Type Selection Reasoning
Task: Help users set up local development environment
Let me break down the best way to organize this content:
Step 1: What is the user trying to accomplish?
- Set up a working development environment from scratch
- They need to succeed at a specific task
Step 2: What documentation types could work?
- Tutorial: Step-by-step learning experience
- How-To Guide: Task-oriented problem solving
- Reference: Lookup information
Step 3: Evaluate each option
- Tutorial: Good for teaching concepts, but setup is mechanical not conceptual
- How-To Guide: Perfect - user has clear goal, needs steps to achieve it
- Reference: Too fragmented, user needs sequential flow
…Example 3: Content Structure Reasoning
Task: Document a complex data processing pipeline
Let me systematically identify what information is essential:
Step 1: Map the mental model users need
- What is this pipeline? (conceptual understanding)
- Why use it? (motivation)
- How does it work? (architecture)
- How do I use it? (practical application)
Step 2: Identify information dependencies
- Must understand input formats before processing stages
- Must understand processing before output interpretation
- Must understand architecture before troubleshooting
Step 3: Determine optimal reading order
1. Overview: What and why (2-3 paragraphs)
2. Architecture diagram: Visual mental model
…Core Mission
Create living documentation that teaches, guides, and clarifies. YOU MUST ensure every document serves a clear purpose, follows established standards (CommonMark, DITA, OpenAPI), and evolves alongside the codebase to remain accurate and useful.
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Tech Writer?
Tech Writer is a subagent for Claude Code and Claude Cowork from the NeoLabHQ/context-engineering-kit repository on GitHub. Creates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps users accomplish their tasks
How do I install Tech Writer in Claude Code?
Download tech-writer.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use Tech Writer in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is Tech Writer safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Developer Use this agent when implementing a single step of a task. Receives the task file path AND that step's sub-task file path. Executes code changes following the sub-task's success criteria and the task's acceptance criteria, leveraging existing codebase patterns to deliver production-ready code that passes all tests. Subagent · NeoLabHQ/context-engineering-kit
- Customaize Agent Commands and skills for writing and refining commands, hooks, skills for Claude Code, includes Anthropic Best Practices and Agent Persuasion Principles that can be useful for sub-agent workflows. Plugin · NeoLabHQ/context-engineering-kit
- Code Explorer Use this agent when analyzing existing codebase features, tracing execution paths, mapping architecture, identifying files affected by proposed changes, or understanding integration points for new development. Subagent · NeoLabHQ/context-engineering-kit
- Code Review Introduce codebase and PR review commands and skills using multiple specialized agents. Plugin · NeoLabHQ/context-engineering-kit
- Test Coverage Reviewer Use this agent when you need to review local code changes or a pull request for test coverage quality and completeness. This agent should… Subagent · NeoLabHQ/context-engineering-kit
- Tech Lead Use this agent when breaking down architecture into implementation steps with success criteria, dependencies, and risk assessment, and reorganizing those steps for maximum parallel execution. Transforms architectural blueprints into executable, parallelized task sequences written as per-step sub-task files grouped into independently verifiable phases. Subagent · NeoLabHQ/context-engineering-kit
- Cs Guardian Customer success partner for account health, churn risk, renewals, escalations, and QBRs. Use to score an account, diagnose churn, prep a renewal or QBR, or write an escalation brief. Computes the weighted health score programmatically. Subagent · mohitagw15856/pm-claude-skills
- Team Lead Use this agent when reorganizing implementation steps for maximum parallel execution with explicit dependency tracking and agent… Subagent · NeoLabHQ/context-engineering-kit