Doc

Documentation Skill

Config-driven documentation scaffolding. Config lives inside the skill at config/defaults.yaml — no repo-root files needed.

Commands

start = scaffold docs/ + create experiment. Use this when beginning new work. expt = create experiment only. Use when docs/ already exists.

Agent Behavior — READ THIS

You are responsible for tracking the active experiment per conversation. When the user creates an experiment or references one, remember its index. Pass it to every script call — scripts are stateless and parallel-safe.

When to use each command

Context resolution (when user doesn't give an index)

1. Experiment created or resumed in this conversation → use it
2. User referenced one by name/number → use it
3. User's request clearly relates to one experiment → use it
4. Ambiguous → ask: "Which experiment?" then run /doc list to show options

You resolve context. Scripts just take a number.

Auto-behaviors

• Checkpoint automatically at natural stopping points — end of conversation, before context switch, after a milestone. Don't wait to be asked.
• Plans go in experiments. NEVER write plans to .claude/plan.md or any ephemeral storage. ALWAYS use /doc plan.
• Never overwrite. Always create new numbered files. Plans evolve: 01, 02, 03.
• Resume before continuing. When picking up an existing experiment, run /doc resume first to load context.

Checkpoint content — MANDATORY

The ckpt command arg is a short label (2-5 words), NOT the checkpoint content. After the script creates the file, you MUST write the body into it using this structure:

```mermaid
graph TD
    A[Starting state] --> B[What was done]
    B --> C[Current state]
    C --> D[Next steps]
```

## What
What was accomplished. Bullet points, brief.

## Key Takeaways
Surprising findings, confirmed/rejected hypotheses, numbers that matter.

## Issues
Blockers hit, workarounds used, unresolved problems. Include error messages if relevant.

## Decisions
Key choices made and why. What was considered and rejected.

## Next
Concrete next steps with enough detail that a new agent can pick up cold.
Include file paths, command examples, and what to watch out for.

The checkpoint must contain everything a fresh agent needs to continue the work without asking questions. Be brief but complete — file paths, key numbers, what worked, what didn't.

DO NOT cram content into the description argument. Keep the arg short: /doc ckpt 7 "v1 analysis complete" then edit the file.

Experiment Structure

experiments/NNN-{name}/
├── .meta.json          auto-updated by scripts
├── plans/              multiple plans, numbered
├── findings/           multiple findings, numbered  
├── checkpoints/        progress snapshots, numbered
├── review/             structured reviews, numbered
└── research/           prompt + response pairs, numbered

Setup

/doc start my-investigation — that's it. Scaffolds docs/ and creates the first experiment.

To customize folder structure or naming: edit config/defaults.yaml inside the skill.

Rules

1. Scripts only create empty templates (frontmatter + headings). YOU must write the actual content into the file after the script runs. Never treat the script call as the finished step.
2. Always use the scripts for file creation. Never manually create experiment dirs or edit .meta.json.
3. Index is just the number. 23 not 023 not 023-docs-and-structs.
4. No auto-commit. Scripts scaffold files — you or the user decide when to commit.
5. Plans go in experiments. Never in .claude/plan.md. This is non-negotiable.
6. Files are immutable. Don't edit old plans/findings — create a new numbered one.
7. Valid learnings domains are listed in config/defaults.yaml. learn will error on invalid domains.
8. Keep titles short. Titles become filenames. Use 2-5 words max — concise and descriptive. "auth-flow" not "investigation-into-authentication-flow-reliability-issues". The numbering prefix handles ordering; the title just needs to identify the topic at a glance.

$ARGUMENTS