Skip to content
Back to skills

Docs Human

ASecurity

Human-readable documentation standard — scannable, plain-language docs derived from the agent docs but formatted for human consumption. Defines the project's human-doc file set and format rules. Use when creating or updating documentation intended for human stakeholders.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 19, 2026
ai-agentsgoapidocumentation

Works with

  • api

Security analysis

A100/100

Scanned September 19, 2026

npx -y skills add dustinkeeton/wafflestack --skill docs-human --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Docs Human?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Docs Human
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dustinkeeton-docs-human/badge)](https://www.skillsdirectory.com/skills/dustinkeeton-docs-human)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: docs-human
description: Human-readable documentation standard — scannable, plain-language docs derived from the agent docs but formatted for human consumption. Defines the project's human-doc file set and format rules. Use when creating or updating documentation intended for human stakeholders.
user-invocable: false
---

# Human Documentation

## Purpose

Produce documentation that humans can quickly scan to understand the project. The human docs for this project are `DECISIONS.md`, `STATUS.md`, and `ARCHITECTURE.md` at the repo root. Derive from the machine docs and the codebase, but reformat for human readers — plain language, headings, and bullets over walls of prose.

Prioritize:

- **Decision log** — what was decided, why, and what alternatives were considered
- **Status visibility** — what's done, what's in progress, what's blocked
- **Change history** — what changed and why, in reverse chronological order (newest on top)
- **Plain language** — avoid jargon where possible, explain technical terms

## Documentation Files

### `DECISIONS.md` (root)

Decision log in reverse chronological order:

```markdown
## YYYY-MM-DD: Decision Title

**Context**: What situation prompted this decision
**Decision**: What was decided
**Alternatives considered**: What else was evaluated
**Rationale**: Why this option was chosen
**Impact**: What this affects
```

### `STATUS.md` (root)

Current project status:

- Feature completion matrix (feature × status)
- Current sprint/focus area
- Known issues and blockers
- Dependency status (external tools, APIs)

### `ARCHITECTURE.md` (root)

High-level architecture overview for humans:

- System diagram — produce it with the `diagram` skill (archify HTML when installed, a Mermaid block otherwise)
- Feature descriptions in plain language
- How features interact
- Configuration overview
- Getting started for new contributors

## Format Rules

1. Use headings liberally for scannability
2. Lead with the most important information
3. Use bullet points over paragraphs
4. Include dates on all log entries
5. Keep STATUS.md under 100 lines — it's a snapshot, not a history

## Owner-voiced docs — do not rewrite

`README.md`, `schema/FORMAT.md`, and `schema/SETUP.md` are owner-voiced
canonical documents (the schema files ship to consumers via npx). Never
rewrite them in a docs pass — if they have drifted from reality, flag the
drift in your report instead.


Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…