Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Create Project Documentation Adrs Prds

ASecurity

Complete workflow for project documentation including ADRs, PRDs, personas, and docs organization. Use when setting up documentation for a new project or improving existing docs. Triggers on project documentation, ADR, PRD, personas, docs structure, documentation setup.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashdatabasedocumentation

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill create-project-documentation-adrs-prds --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Create Project Documentation Adrs Prds?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Create Project Documentation Adrs Prds
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-create-project-documentation-adrs-prds/badge)](https://www.skillsdirectory.com/skills/rondoflow-create-project-documentation-adrs-prds)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: create-project-documentation-adrs-prds
description: "Complete workflow for project documentation including ADRs, PRDs, personas, and docs organization. Use when setting up documentation for a new project or improving existing docs. Triggers on project documentation, ADR, PRD, personas, docs structure, documentation setup."
category: "Content & Writing"
author: community
version: "1.0.0"
icon: pencil
---

# Project Documentation (Meta-Skill)

Complete workflow for setting up and maintaining project documentation.


## Installation

### OpenClaw / Moltbot / Clawbot

```bash
npx clawhub@latest install project-documentation
```


---

## When to Use

- Starting a new project and need docs structure
- Improving documentation on existing project
- Setting up ADRs, PRDs, or persona docs
- Want consistent documentation across projects

---

## Docs-First Philosophy

Start every project with documentation, not code:

```
1. Define the idea      → What is this? What problem does it solve?
2. Define the personas  → Who uses this? What are their journeys?
3. Define the features  → What does it do for each persona?
4. Define the stack     → What technologies? Why?
5. Then build           → With full context established
```

---

## Directory Structure

```
docs/
├── architecture/        # CURRENT STATE - Living docs of actual code
│   ├── overview.md
│   └── data-flow.md
├── guides/              # CURRENT STATE - How to use/operate
│   ├── getting-started.md
│   └── configuration.md
├── runbooks/            # CURRENT STATE - Short, actionable guides
│   ├── local-dev.md
│   ├── deploy.md
│   └── database.md
├── planning/            # FUTURE - Not for docs site
│   ├── roadmap.md
│   └── specs/
├── decisions/           # ADRs - Decision records
│   ├── 001-tech-stack.md
│   └── 002-auth-approach.md
└── product/             # PRD, personas
    ├── overview.md
    ├── personas/
    └── features.md
```

---

## Critical Separation: Current vs Future

| Category | Purpose | Goes on Docs Site? |
|----------|---------|-------------------|
| **Current State** | How things work now | Yes |
| **Planning** | Future specs, designs | No |
| **Architecture** | Living docs of code | Yes |
| **Roadmap/Todos** | What we're working on | No |
| **Runbooks** | How to operate | Yes |
| **Proposed Runbooks** | Future plans | No |

---

## Documentation Types

### Architecture Decision Records (ADRs)

Template:
```markdown
# ADR-001: [Title]

## Status
[Proposed | Accepted | Deprecated | Superseded]

## Context
[What is the issue we're solving?]

## Decision
[What did we decide?]

## Consequences
[What are the results - positive and negative?]

## Alternatives Considered
[What other options did we evaluate?]
```

### Product Requirements Document (PRD)

Template:
```markdown
# PRD: [Feature Name]

## Problem
[What problem are we solving?]

## Users
[Which personas does this serve?]

## Requirements
- [ ] Requirement 1
- [ ] Requirement 2

## Non-Goals
[What are we explicitly NOT doing?]

## Success Metrics
[How do we know this worked?]
```

### Persona Documentation

Template:
```markdown
# Persona: [Name]

## Who They Are
- Background
- Technical level
- Goals

## Pain Points
- [Pain 1]
- [Pain 2]

## Journey
1. Discovery
2. Onboarding
3. Daily use
4. Advanced usage

## Content Needs
- Doc types they need
- Format preferences
```

### Runbooks

Template:
```markdown
# Runbook: [Task Name]

## Prerequisites
- [Requirement 1]
- [Requirement 2]

## Steps
1. [Step 1]
2. [Step 2]

## Verify
[How to confirm success]

## Troubleshooting
| Problem | Solution |
|---------|----------|
| [Issue] | [Fix] |
```

---

## Roadmap Format

```markdown
## Roadmap

### Current Sprint
- [ ] Add user authentication endpoint
- [ ] Create login form component
- [ ] Wire form to auth endpoint

### Backlog
- [ ] Password reset flow
- [ ] OAuth integration
- [ ] Two-factor auth
```

---

## Quality Gates

Before shipping docs:

- [ ] Separates current state from planning
- [ ] Uses appropriate template for doc type
- [ ] Written for the right audience
- [ ] Actionable (runbooks) or explanatory (guides)
- [ ] No stale/outdated information

---

## Anti-Patterns

- **Mixing future plans with current state** — Confuses what's real
- **Planning docs on docs site** — Users expect reality
- **One-size-fits-all docs** — Different audiences need different depth
- **Building features before personas** — No context for decisions
- **Documentation written once and forgotten** — Keep it current

---

## Checklist for New Projects

- [ ] Create docs/ directory structure
- [ ] Write initial PRD/overview
- [ ] Document 2-3 personas
- [ ] Create ADR-001 for tech stack
- [ ] Set up roadmap format
- [ ] Create essential runbooks (local-dev, deploy)
- [ ] Separate planning/ from current-state docs

---

## Related Skills

- **Commands:** [/bootstrap-docs](../../../commands/bootstrap/bootstrap-docs.md), [/new-feature](../../../commands/development/new-feature.md)
- **Agent:** [development](../../../agents/development/)

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →