Skip to main content
skill Claude Code CX Codex Cursor

hads — Claude Code skill for technical docs

This skill helps write and convert technical documentation into HADS, a Markdown format designed for both human and AI readers. Use it to check a document’s structure or prepare docs for AI coding workflows.

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add wshobson/agents
/plugin install documentation-standards@claude-code-workflows
Open on GitHub

What hads does

HADS sets rules for Markdown documents: an H1 title, a version declaration, an AI reading instruction, and sections marked [SPEC], [NOTE], [BUG], or [?]. The skill can draft a document in this format, restructure existing docs, or check their structure. For large files, it recommends scanning headings first, then reading relevant [SPEC] and [BUG] blocks.

Validation covers required document elements and block-tag formatting. An automated validator is planned but is not part of this release. HADS files use the .md extension and remain standard Markdown, so no special reader is needed. Install the skill if you write docs for people and AI; it is not a fit if you need automated file validation.

What it helps with

  • draft technical documentation in HADS format
  • convert a README while preserving its facts
  • check required sections and block-tag formatting
  • summarize a document using its [SPEC] and [BUG] blocks

Example prompts for the agent

  • Write HADS documentation for this REST API.
  • Convert this README to HADS format and preserve all facts.
  • Check whether this document follows the HADS rules.

How to install hads

1Plugin marketplace

/plugin marketplace add wshobson/agents
/plugin install documentation-standards@claude-code-workflows

This installs the whole documentation-standards plugin with all its skills

2Skills CLI (Vercel)

npx skills add wshobson/agents --skill hads -a claude-code

3Manually: put the files in place

~/.claude/skills/hads/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/hads/

From the same set213

The whole set →
typescript-advanced-types Seth Hobson Guides an agent through advanced TypeScript types, from generics to conditional and mapped types. Use it for typed libraries, API clients, or strict configuration objects. Claude Code CX Codex Cursor 92,169installs tailwind-design-system Seth Hobson Helps build design systems with Tailwind CSS v4, from theme tokens to component variants. Use it when a project needs shared UI patterns. Claude Code CX Codex Cursor 70,180installs brand-landingpage Travis D. Elliott This skill interviews you about the product and its visual direction, then builds a landing page through Stitch. Use it when there’s no established design yet. Claude Code CX Codex Cursor 39,476installs python-testing-patterns Seth Hobson This skill guides Python testing with pytest, fixtures and mocks. Use it when building a test suite or tracking down failing checks. Claude Code CX Codex Cursor 36,943installs python-performance-optimization Seth Hobson This skill profiles Python code to locate CPU and memory bottlenecks. Use it when an application responds slowly or consumes too many resources. Claude Code CX Codex Cursor 35,675installs nextjs-app-router-patterns Seth Hobson This skill covers Next.js App Router patterns for rendering, routing, and data fetching. Use it when starting an App Router project or moving from Pages Router. Claude Code CX Codex Cursor 32,529installs api-design-principles Seth Hobson Use this skill to plan or review REST and GraphQL APIs. It helps when writing a specification or setting API conventions for a team. Claude Code CX Codex Cursor 30,348installs code-review-excellence Seth Hobson This skill guides pull request reviews, catches logic and security issues, and helps teams give specific feedback. Use it for review standards or developer mentoring. Claude Code CX Codex Cursor 30,193installs

Similar

academic-research-suite Imbad0202 Routes academic workflows inside AI assistants, from literature reviews and meta-analyses to manuscript drafting and peer review. Built for researchers preparing scholarly papers. Claude Code CX Codex Cursor +1 1,900installs draw-io-diagram-generator official github Creates and edits draw.io diagrams in .drawio, .drawio.svg, and .drawio.png files. Use it when an agent needs to produce a diagram from a project request. GitHub Copilot 2,800installs acquire-codebase-knowledge official github This skill maps an existing repository and creates docs for its stack, architecture, tests, and risks. Use it when you are onboarding into a codebase. GitHub Copilot 2,200installs cli-mastery official github Learn GitHub Copilot CLI through guided lessons, quizzes, and scenario challenges. Use it to study commands, modes, agents, MCP, and configuration. GitHub Copilot 2,100installs publish-to-pages official github Publishes presentations and HTML content to GitHub Pages by creating a repository and returning a live page address. Use it when files need to be shared as a web page. GitHub Copilot 1,800installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs

Questions about hads

How do I install hads in Claude Code?

Run npx skills add wshobson/agents --skill hads -a claude-code.

What does hads do?

The skill helps create, convert, and check technical documents in HADS format. It uses tags for authoritative facts, context, confirmed bugs, and unverified claims.

Do I need a separate validator for HADS?

No. The skill checks documents against the format rules; an automated validator is planned but not included in this release.

Source text

SKILL.md · MIT
---
name: hads
description: Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or optimizing documentation for token-efficient AI consumption.
---

# HADS Claude Skill
**Version 1.0.0** · Human-AI Document Standard · 2026 · HADS 1.0.0

---

## AI READING INSTRUCTION

This skill teaches Claude how to read, generate, and validate HADS documents.
Read all `[SPEC]` blocks before responding to any HADS-related request.
Read `[NOTE]` blocks if you need context on intent or edge cases.

---

## 1. WHAT IS HADS

**[SPEC]**
- HADS = Human-AI Document Standard
- Convention for Markdown technical documentation
- Four block types: `**[SPEC]**`, `**[NOTE]**`, `**[BUG]**`, `**[?]**`
- Every HADS document requires: H1 title, version declaration, AI manifest
- AI manifest appears before first content section, tells AI what to read/skip
- File extension: `.md` — standard Markdown, no tooling required

---

## 2. BLOCK TYPES

**[SPEC]**
```
**[SPEC]**   Authoritative fact. Terse. Bullet lists, tables, code. AI reads always.
**[NOTE]**   Human context, history, examples. AI may skip.
**[BUG]**    Verified failure + fix. Required fields: symptom, cause, fix. Always read.
**[?]**      Unverified / inferred. Lower confidence. Always flagged.
```

Block tag rules:
- Bold, on its own line: `**[SPEC]**`
- Content follows immediately (no blank line between tag and content)
- Multiple blocks of different types allowed per section
- Titled BUG blocks allowed: `**[BUG] Short description**`
- No nesting of blocks inside blocks

---

## 3. REQUIRED DOCUMENT STRUCTURE

**[SPEC]**
```markdown
# Document Title
**Version X.Y.Z** · Author · Date · [metadata]

---

## AI READING INSTRUCTION

Read `[SPEC]` and `[BUG]` blocks for authoritative facts.
Read `[NOTE]` only if additional context is needed.
`[?]` blocks are unverified — treat with lower confidence.

---

## 1. First Section

**[SPEC]**
...
```

Required elements in order:
1. H1 title
2. `**Version X.Y.Z**` in header (first 20 lines)
3. AI manifest section before first content section
4. Content sections (H2), subsections (H3)

---

## 4. HOW CLAUDE READS HADS

**[SPEC]**
When encountering a HADS document:
1. Find and read the AI manifest first
2. Read all `[SPEC]` blocks — these are ground truth
3. Read all `[BUG]` blocks — always, before generating any code or config
4. Read `[NOTE]` blocks only if `[SPEC]` is insufficient to answer the query
5. Treat `[?]` content as hypothesis — note uncertainty in response

Token optimization: for large documents, scan section headings first, then read only `[SPEC]` and `[BUG]` blocks in relevant sections.

---

## 5. HOW CLAUDE GENERATES HADS

**[SPEC]**
When asked to write documentation in HADS format:

1. Start with header block (title, version, metadata)
2. Add AI manifest — always include, never skip
3. Organize content into numbered H2 sections
4. For each fact: write as `[SPEC]` — terse, bullet or table or code
5. For each "why" or context: write as `[NOTE]`
6. For each known failure mode with confirmed fix: write as `[BUG]`
7. For each unverified claim: write as `[?]`
8. End with changelog section

Content rules for `[SPEC]`:
- Prefer bullet lists over prose
- Prefer tables for multi-field facts
- Prefer code blocks for syntax, formats, examples
- Maximum 2 sentences of prose — if more needed, move to `[NOTE]`

Content rules for `[BUG]`:
- Always include: symptom, cause, fix
- Optional: affected versions, workaround
- Title on same line: `**[BUG] Short description**`

**[NOTE]**
When converting existing documentation to HADS: extract facts into `[SPEC]`, move narrative and history to `[NOTE]`, surface all known issues as `[BUG]`. Do not duplicate content between block types.

---

## 6. VALIDATION RULES

**[SPEC]**
A valid HADS document must have:
- H1 title
- `**Version X.Y.Z**` in first 20 lines
- AI manifest before first content section
- All block tags bold: `**[SPEC]**` not `[SPEC]` not *[SPEC]*
- `[BUG]` blocks contain at minimum symptom + fix

Validator: *(planned — not yet included in this release)*

---

## 7. EXAMPLE INTERACTIONS

**[SPEC]**

User: *"Write HADS documentation for this REST API"*
→ Generate full HADS document: header, manifest, sections with [SPEC]/[NOTE]/[BUG] blocks

User: *"Convert this README to HADS format"*
→ Restructure existing content into HADS blocks, preserve all facts, add manifest

User: *"Is this document valid HADS?"*
→ Check: H1 title, version, manifest, block tag formatting, BUG block completeness

User: *"Summarize this HADS document"*
→ Read only [SPEC] and [BUG] blocks, return structured summary

User: *"What does this API do?"* (HADS doc provided)
→ Read manifest, read [SPEC] blocks in relevant sections, answer directly

---

## 8. DESIGN INTENT

**[NOTE]**
HADS exists because AI models increasingly read documentation before humans do. The format optimizes for this reality without sacrificing human readability.

Key insight: the AI manifest is the core innovation. It lets even small (7B) models know what to read and what to skip — without requiring them to reason about document structure. Explicit is better than implicit for model consumption.

When generating HADS, think of `[SPEC]` as the API surface and `[NOTE]` as the comments. `[BUG]` blocks are the most valuable content — they represent hard-won knowledge that saves others from hitting the same wall.

---

## 9. QUICK REFERENCE

**[SPEC]**
```
Tag       | Bold format    | Reader  | Required content
----------|----------------|---------|------------------
[SPEC]    | **[SPEC]**     | AI      | Facts, terse
[NOTE]    | **[NOTE]**     | Human   | Context, narrative
[BUG]     | **[BUG] ...**  | Both    | Symptom + fix
[?]       | **[?]**        | Both    | Unverified claims
```

Manifest minimum:
```markdown
## AI READING INSTRUCTION
Read `[SPEC]` and `[BUG]` blocks for authoritative facts.
Read `[NOTE]` only if additional context is needed.
`[?]` blocks are unverified.
```

© Niksa Barlovic · MIT · wshobson/agents

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor