Doc Sync logo

Doc Sync

Community
jmagly
doc-sync

Synchronize documentation and code with bounded, scope-first drift checks

Overview

Publisherjmagly
Repositoryaiwg
Skill namedoc-sync
Stars
225
Forks
34
Bundled files
Instructions only
LicenseMIT
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 jmagly on GitHub. Read the source before you install it.

Installation

Install the Doc Sync 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/jmagly/aiwg/tree/main/agentic/code/addons/aiwg-utils/skills/doc-sync
  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/jmagly/aiwg.git /tmp/aiwg
mkdir -p .claude/skills
cp -r /tmp/aiwg/agentic/code/addons/aiwg-utils/skills/doc-sync .claude/skills/doc-sync
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Doc Sync 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 Doc Sync 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 Doc Sync 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.

Doc Sync

Detect and resolve documentation drift without front-loading a full repository audit. Treat standard Claude Code Sonnet context as the baseline.

Triggers

Users may say:

  • "doc sync"
  • "sync docs"
  • "fix doc drift"
  • "reconcile docs"
  • "update docs to match code"
  • "update code to match docs"
  • "check for documentation drift"

Parameters

direction is required:

  • code-to-docs: update docs to match code
  • docs-to-code: identify code gaps against docs
  • full: bidirectional reconciliation with human review for conflicts

Options:

  • --dry-run: report only, no file edits
  • --scope <path>: limit the audit to a subtree or file group
  • --incremental: start from changed files since the last sync, then current git changed files if no last-run record exists
  • --parallel N: cap concurrent auditors; default 2, maximum 4

Artifact root resolution

Treat every .aiwg/... path below as a logical artifact path. Before reading or writing sync state, working evidence, or reports, run aiwg artifacts path from the active workspace and use the returned absolute directory as AIWG_ARTIFACT_ROOT. Never write these payloads to a literal project-local .aiwg/ when AIWG_ARTIFACTS_PATH or .aiwg-location redirects the corpus.

Context Budget Rules

  • Start with git status --short, git diff --name-only, and git diff --cached --name-only.
  • If no --scope or --incremental is supplied, derive a candidate scope from changed files and ask before expanding to the full repo.
  • Use inventories (rg --files, find, git path lists) before reading file bodies.
  • Dispatch auditors only for domains implicated by the scoped files.
  • Each auditor returns at most 10 findings and 600 words to the parent context. Detailed evidence goes under $AIWG_ARTIFACT_ROOT/working/doc-sync/.
  • Do not preload other skills into auditor agents.
  • For combined doc-sync, blog, and commit requests, keep blog/release coverage as one scoped lane and return a handoff summary for commit-and-push.

Workflow

  1. Parse direction and options.
  2. Build the cheap scope inventory from git path lists.
  3. Select relevant lanes only: CLI/API docs, provider docs, skill/agent catalogs, README/changelog/release/blog material, or config/schema docs.
  4. Run bounded auditors for selected lanes only.
  5. Write $AIWG_ARTIFACT_ROOT/reports/doc-sync-{timestamp}.md with scope, findings, auto-fixable items, human-review items, and changed files.
  6. If not --dry-run, apply high-confidence fixes only.
  7. Validate modified files with targeted checks.
  8. Record $AIWG_ARTIFACT_ROOT/reports/doc-sync-last-run.json.
  9. Return report path, files changed, validation commands, and remaining review items.

Output Contract

Return:

  • report path
  • scope audited
  • files changed
  • validation commands run
  • remaining human-review items
  • recommended handoff skill, if any

Frequently asked questions

What does the Doc Sync AI skill do?

Synchronize documentation and code with bounded, scope-first drift checks

Why use Doc Sync on TypingMind?

Because you install it once and use it with any model. Doc Sync 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 Doc Sync in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/aiwg-utils/skills/doc-sync. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Doc Sync?

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 Doc Sync?

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

Is the Doc Sync AI skill free?

Yes. It is published on GitHub by jmagly under the MIT license. 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 👇