Skip to content
Agentmart
Submit a tool

tech-writing

Technical writing and documentation skill — specs, runbooks, changelogs, meeting notes, ADRs

Skill by amas-nghia

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying tech-writing?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/amas-nghia-tech-writing

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Technical writing and documentation skill — specs, runbooks, changelogs, meeting notes, ADRs

Use cases: writing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/tech-writing

What's inside

Skill name
tech-writing
Description
Technical writing and documentation skill — specs, runbooks, changelogs, meeting notes, ADRs
License
MIT
Instructions
177 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Agent Skills spec issues

  • name: "tech-writing" does not match folder "skill-tech-writing"

Files (2)

  • SKILL.md
  • package.json

SKILL.md (first lines)

# Technical Writing Skill

## Nguyên tắc cốt lõi

- Viết cho người đọc chưa biết gì về context
- Mỗi đoạn trả lời **một câu hỏi cụ thể**
- Code examples phải chạy được ngay, không phải pseudocode
- Cấu trúc theo nhu cầu đọc: từ overview → detail, không ngược lại
- Ngắn gọn hơn luôn tốt hơn — không thêm từ để "có vẻ đầy đủ"

## Loại tài liệu và template

### 1. Technical Spec / PRD

```markdown
# Feature: [Tên feature]

## Problem
[Vấn đề hiện tại là gì? Ai bị ảnh hưởng?]

## Proposed Solution
[Giải pháp đề xuất — 1-3 câu]

## Requirements
### Must Have
- [ ] ...
### Nice to Have
- [ ] ...

## Design / Architecture
[Sơ đồ hoặc mô tả data flow, API contract]

## Out of Scope
[Cái gì KHÔNG nằm trong feature này]

## Open Questions
- [ ] Question 1 → [assigned to] [deadline]
```

### 2. API Documentation

```markdown
## POST /api/vault/tasks

Tạo task mới trong vault.

**Request Body**
| Field | Type | Required | Description |
|---|---|---|---|
| title | string | ✓ | Tiêu đề task |
| column | string | ✓ | `todo` / `in-progress` / `review` / `done` |
| priority | string | | `critical` / `high` / `medium` / `low` |

**Response 201**
```json
{ "data": { "id": "task-abc123", "title": "...", "status": "todo" } }
```

**Errors**
- `400` — Missing required fields
- `409` — Task with same title exists in column
```

### 3. Runbook

```markdown
# Runbook: [Tên sự cố / procedure]

## Trigger
[Khi nào dùng runbook này]

## Impact
[Ảnh hưởng tới gì nếu không xử lý]

## Steps
1. [Bước cụ thể với lệnh exact]
   ```bash
   pm2 restart relayhq-api
   ```
2. [Verify bằng cách nào]
   ```bash
   curl http://localhost:44210/api/health
   ```

## Rollback
[Cách undo nếu cần]

## Escalation
[Khi nào cần leo thang, ai là người tiếp nhận]
```

### 4. Architecture Decision Record (ADR)

```markdown
# ADR-NNN: [Tiêu đề quyết định]

**Date:** YYYY-MM-DD  
**Status:** Proposed / Accepted / Deprecated

## Context
[Tình huống đặt ra vấn đề — facts, không opinion]

## Decision
[Quyết định cụ thể đã chọn]

## Rationale
[Tại sao chọn option này — trade-offs được acknowledge]

## Alternatives Considered
- **Option A**: [mô tả] — rejected vì [reason]
- **Option B**: [mô tả] — rejected vì [reason]

## Consequences
- Positive: ...
- Negative: ...
- Neutral: ...
```

### 5. Meeting Notes / Sprint Summary

From amas-nghia/relayhq, MIT.

More from amas-nghia/relayhq

Signals

Stars
2
Forks
0
Open issues
1
Last commit (this folder)
May 5, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from amas-nghia

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get tech-writing running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying tech-writing?

CallGet help
Cite this page

tech-writing skill. Agent Mart. https://agentmart.dev/skills/amas-nghia-tech-writing (last updated 2026-10-24)