HADS Doc Standard
Software development skill, available on Zeplik
HADS Doc Standard is a ready-to-run software development skill on Zeplik. Produces or checks Human-AI Document Standard markdown with SPEC/NOTE/BUG/? Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured document you can keep and reuse: A HADS-formatted markdown doc (H1 + version + AI manifest + numbered sections of SPEC/NOTE/BUG/? blocks).
The HADS Doc Standard skill loads automatically when your request matches it, or you can invoke it directly by typing /hads in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the HADS Doc Standard skill can do
- Generate new HADS-formatted markdown documents from scratch
- Convert existing documentation into SPEC/NOTE/BUG/? blocks
- Validate HADS documents against the required structure checklist
- Insert a compliant AI manifest section into documentation
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the HADS Doc Standard skill works
HADS -- Human-AI Document Standard
HADS is a Markdown convention for technical documentation that both humans and AI models read efficiently. This skill teaches how to read, generate, and validate HADS documents. It is a documentation format -- for capturing a single decision and its rationale, use architecture-decision-records instead.
Block Types
**[SPEC]** Authoritative fact. Terse: bullets, tables, code. AI reads always.
**[NOTE]** Human context, history, examples. AI may skip.
**[BUG]** Verified failure + fix. Required: symptom, cause, fix. Always read.
**[?]** Unverified / inferred. Lower confidence. Always flagged.
Block rules: tag is bold on its own line; content follows immediately with no blank line; no nesting; BUG blocks may carry a title (**[BUG] Short description**).
Required Document Structure
In order:
- H1 title
**Version X.Y.Z**in the first ~20 lines (with author/date/metadata)- AI manifest section before the first content section
- Numbered H2 content sections (with H3 subsections)
Minimum AI manifest:
## AI READING INSTRUCTION
Read `[SPEC]` and `[BUG]` blocks for authoritative facts.
Read `[NOTE]` only if additional context is needed.
`[?]` blocks are unverified.
How to Read a HADS Document
- Find and read the AI manifest first.
- Read all
[SPEC]blocks -- these are ground truth. - Read all
[BUG]blocks before generating any code or config. - Read
[NOTE]blocks only if SPEC is insufficient. - Treat
[?]content as hypothesis and note the uncertainty.
Token optimization for large docs: scan section headings, then read only SPEC and BUG blocks in relevant sections.
How to Generate a HADS Document
- Write the header block (title, version, metadata).
- Add the AI manifest -- always, never skip.
- Organize content into numbered H2 sections.
- Each fact ->
[SPEC], terse (bullets/tables/code, max 2 sentences of prose). - Each "why"/context ->
[NOTE]. - Each known failure with a confirmed fix ->
[BUG](symptom, cause, fix). - Each unverified claim ->
[?]. - End with a changelog section.
When converting existing docs: extract facts into [SPEC], move narrative/history to [NOTE], surface known issues as [BUG]. Do not duplicate content across block types.
Validation Checklist
A valid HADS document has:
- An H1 title
**Version X.Y.Z**in the first ~20 lines- An AI manifest before the first content section
- All block tags bold (
**[SPEC]**, not[SPEC]or*[SPEC]*) [BUG]blocks containing at minimum a symptom and a fix
Quick Reference
Tag | Bold format | Reader | Required content
----------|----------------|---------|------------------
[SPEC] | **[SPEC]** | AI | Facts, terse
[NOTE] | **[NOTE]** | Human | Context, narrative
[BUG] | **[BUG] ...** | Both | Symptom + fix
[?] | **[?]** | Both | Unverified claims
Output
Either a new HADS-formatted document (header, AI manifest, numbered sections of SPEC/NOTE/BUG/? blocks) or a validation verdict listing which required elements pass or fail.
How to use the HADS Doc Standard skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the HADS Doc Standard skill right away.
Describe your software development task
Ask in plain language, or type /hads to invoke the skill directly. Zeplik recognizes the HADS Doc Standard skill and applies its method.
Review and refine the result
Zeplik returns a structured document you can edit, download, and reuse. Ask follow-ups to refine it.
Source and credit
- Author
- wshobson
- License
- MIT
Adapted from the open-source wshobson/agents project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the HADS Doc Standard skill?
- HADS Doc Standard is a ready-to-run software development skill on Zeplik. Produces or checks Human-AI Document Standard markdown with SPEC/NOTE/BUG/? Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured document you can keep and reuse: A HADS-formatted markdown doc (H1 + version + AI manifest + numbered sections of SPEC/NOTE/BUG/? blocks).
- How do I use HADS Doc Standard on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /hads in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the HADS Doc Standard skill use?
- Any model you choose. Zeplik works across every model in one chat, so the HADS Doc Standard skill runs on your preferred model for the task.
- Where does the HADS Doc Standard skill come from?
- The HADS Doc Standard skill is adapted from the open-source wshobson/agents project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the HADS Doc Standard skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related software development skills
- .NET BackendBuild ASP.NET Core 8+ backends with EF Core: auth, background jobs, production API patterns
- Advanced Git WorkflowsUse for advanced Git surgery: interactive rebase, cherry-pick, bisect, reflog recovery, and history cleanup before merging. Not for parallel worktree workflows (use using-git-worktrees).
- Adversarial Code ReviewHunt for bugs in code the user shares by assuming defects exist and attacking the code through several distinct lenses, then report severity-ranked findings with evidence. Use for "review this", "what could go wrong", "bug hunt", or pre-merge scrutiny of a change. Read-only, it reports problems and does not rewrite the code. Not for style cleanup (use simplify-code) or for writing new code.
- AI Agent FrameworksUse when building multi-agent systems or agent orchestration -- LangChain/LangGraph, agent team design, task coordination, pipelines. Not for authoring a Zeplik skill (use skill-creator).
- Algolia SearchAdd Algolia search: indexing strategies, React InstantSearch, relevance tuning, search-as-you-type
- Android CI/CDAutomate Android CI/CD to Google Play: keystore, GitHub Secrets, multi-stage release workflow for RN, Flutter, native
More on Zeplik
Try HADS Doc Standard on Zeplik
Every model, one chat. Bring the HADS Doc Standard skill into your next conversation and let the assistant do the work.