Write Ai Doc logo

Write Ai Doc

Community
onevcat
write-ai-doc

Create and maintain curated docs-ai/ records for substantial features and non-trivial, decision-shaping fixes (numbered entries with 000-plan.md before implementation and 001-action.md after). Do not use for reviews, audits, routine investigations, working notes, or status reports unless onevcat explicitly asks for a docs-ai/ record.

Overview

Publisheronevcat
RepositoryProwl
Skill namewrite-ai-doc
Stars
647
Forks
66
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by onevcat on GitHub. Read the source before you install it.

Installation

Install the Write Ai Doc AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/onevcat/Prowl/tree/main/.claude/skills/write-ai-doc
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/onevcat/Prowl.git /tmp/Prowl
mkdir -p .claude/skills
cp -r /tmp/Prowl/.claude/skills/write-ai-doc .claude/skills/write-ai-doc
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Write Ai Doc in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Write Ai Doc on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Write Ai Doc is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Write AI Doc

docs-ai/ is Prowl's curated product/design record, not a working-note log. A numbered folder is reserved for a substantial feature or a non-trivial, decision-shaping fix, each holding an RFC-like plan and an action log. Future humans and agents use it to answer "why is it built this way?" — so entries must be selected deliberately and stay accurate against the code. Read docs-ai/README.md for the index and intent.

When to write one

Create a new entry only when the work is either:

  • a substantial feature with an enduring product or architecture decision (for example, a new UI surface, subsystem, or multi-reducer behavior);
  • a non-trivial fix whose root cause, design decision, or resulting behavior must guide future implementation.

Do not create an entry merely because the work is detailed, takes time, or produces useful findings. Skip reviews, code or post-release audits, routine research/investigations and debugging, status reports, test runs, pure formatting or dependency bumps, routine upstream ports already recorded in the upstream ledger (docs-ai/017-upstream-sync-process/upstream-ledger.md), and docs-only changes. A user may explicitly request a record for an otherwise non-qualifying task. When in doubt, do not write one.

Workflow

1. New entry — plan first, before coding

  1. Pick the next number: ls docs-ai/ | sort and take highest NNN + 1 (three digits).
  2. Create docs-ai/NNN-<kebab-slug>/000-plan.md from the template below, Status: Planned. Write it as part of planning — background, goals, approach, alternatives — not as an afterthought.
  3. Implement the work (normal branch/PR flow).
  4. Write 001-action.md: what actually happened, chronological, with PR/commit refs, the resulting key files, and deviations from the plan. Flip plan status to Implemented. Ship the docs in the same PR as the change when practical.

2. Follow-up on an existing entry (in-frame fix or extension)

  1. Add the next-numbered file in the folder, e.g. 002-<topic>.md (template below).
  2. At the end of 000-plan.md's Amendments section append: - Updated 2026-MM-DD: <one line> — see [002-<topic>.md](002-<topic>.md).
  3. If the follow-up invalidates part of the plan or action text, correct that text in place (keep it truthful) and note the correction in the amendment.
  4. Multi-PR entries (a plan with a slice table, e.g. 063): each slice ships its own 00N-<slice>.md amendment in the slice's PR, starting at 002; write 001-action.md once, when the last slice lands (or the entry is superseded), summarizing the slices.

3. Large pivot / redesign

If the change replaces the entry's approach rather than patching it, open a NEW numbered entry, cross-link both directions, and mark the old plan Status: Superseded by [NNN-new-slug](../NNN-new-slug/000-plan.md).

Templates

000-plan.md

markdown
# NNN — <Title>: Plan

| | |
| --- | --- |
| **Status** | Planned \| Implemented \| Superseded by <link> |
| **Anchor date** | 2026-MM-DD |
| **Primary PRs** | #a, #b (fill in as they merge) |
| **Related** | [NNN-other](../NNN-other/000-plan.md), `docs/...` |

## Background
The product problem/pain and its context; for a fix, the observed symptom.

## Goals
Bullets. Add a **Non-goals** subsection when scope exclusion is a real decision.

## Design / Approach
The intended approach; name the key types/files it touches.

## Alternatives & decisions
Options considered and why the chosen one won. Record decisions, not just designs.

## Amendments
(append `- Updated 2026-MM-DD: ... — see [00N-topic.md](00N-topic.md)` lines here)

001-action.md

markdown
# NNN — <Title>: Action Log

## Timeline
| Date | Change | Ref |
| --- | --- | --- |

## Outcome & current state (as of 2026-MM-DD)
What exists in code now; key files/types with repo-relative paths.

## Deviations from plan
Where reality diverged from 000-plan.md, or "None known."

## Open questions
Unverified claims, oddities worth revisiting, or "None."

Amendment (002+)

markdown
# NNN.00M — <Topic>

## Context
Why this follow-up happened.

## Change
What was done. | ## Refs: PR #x | ## Current state (optional)

Writing rules

  • English, factual, RFC-ish; prefer tables over prose for timelines. Plans are typically 40–120 lines, actions 30–100 — long enough to be useful, short enough to be read.
  • Every repo-relative file path you write must exist (verify with Glob/Grep before writing). Facts you can't verify belong under Open questions, not in prose.
  • Reference fork PRs as #123, upstream PRs as upstream #123, files as inline code. Cross-link sibling entries with relative links.
  • docs-ai/ is the curated home for fork history plus fork-internal product, design, and operational docs. It is not a task journal. Numbered files are immutable history; non-numbered files inside an entry folder (e.g. 001-.../release-runbook.md, 017-.../upstream-ledger.md, 013-prowl-cli/contracts/, 020-observability/runbook.md) are living documents — update them in place when the process/contract they describe changes, and link them instead of duplicating their content.
  • docs/ (the user-facing agent manual) is separate: current behavior goes there, history/decisions/runbooks go in docs-ai. Never link doc-onevcat/ — that directory was dissolved into docs-ai in 2026-07.
  • The app module and scheme are Prowl; the app sources are in App/Sources/.... Numbered entries before 074 use the old paths (supacode/...); the path table is in docs-ai/README.md.
  • After adding or renaming an entry, add/refresh its row in docs-ai/README.md's index.
  • Do not state build/test results you didn't produce.

Frequently asked questions

What does the Write Ai Doc AI skill do?

Create and maintain curated docs-ai/ records for substantial features and non-trivial, decision-shaping fixes (numbered entries with 000-plan.md before implementation and 001-action.md after). Do not use for reviews, audits, routine investigations, working notes, or status reports unless onevcat explicitly asks for a docs-ai/ record.

Why use Write Ai Doc on TypingMind?

Because you install it once and use it with any model. Write Ai Doc is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Write Ai Doc in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/onevcat/Prowl/tree/main/.claude/skills/write-ai-doc. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Write Ai Doc?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Write Ai Doc?

As many as you like. As long as a model supports skills, you can use Write Ai Doc with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Write Ai Doc AI skill free?

It is published on GitHub by onevcat. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇