TypingMindTypingMindThe best frontend for AI
Awiki Save logo

Awiki Save

Community
TacoTakumi
awiki-save

Save content from the current conversation to the Agent Wiki. Use when research, decisions, or valuable findings should be preserved.

Overview

PublisherTacoTakumi
Repositoryagent-wiki
Skill nameawiki-save
Stars
51
Forks
2
Bundled files
Instructions only
Links
Skill sourceRepositoryHomepage
  • 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 TacoTakumi on GitHub. Read the source before you install it.

Installation

Install the Awiki Save 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/TacoTakumi/agent-wiki/tree/main/src/agent_wiki/skills/awiki-save
  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/TacoTakumi/agent-wiki.git /tmp/agent-wiki
mkdir -p .claude/skills
cp -r /tmp/agent-wiki/src/agent_wiki/skills/awiki-save .claude/skills/awiki-save
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Awiki Save 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 Awiki Save 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 Awiki Save 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.

Agent Wiki Save

Save valuable content from the current conversation to the wiki. First decide whether you're creating a new page or updating an existing one — search first (awiki search "<query>") so you don't create a duplicate.

New page

  1. Generate a summary: Write a clean markdown summary of the content to save. Include:

    • A clear # Title heading
    • Key findings, decisions, or knowledge
    • [[wikilinks]] to related topics if known

  2. Write to a temp file: Save the summary to a temp .md file

  3. Ingest: Run awiki ingest <temp-file> --topic <topic> --tags <tags>

  4. Report: Tell the user what was saved and where

Updating an existing page

Pages are generated from an immutable-by-convention source in raw/ — never hand-edit a page in a topic folder. To fold a finding into an existing page:

  1. Find the raw source: Run awiki raw <page>, where <page> is the page's path (projects/my-page.md), slug or title. It prints the raw file's path, taken from the page's sources: frontmatter. The raw name can differ from the page slug: ingest names the raw after the input file and the page after its # H1.

  2. Edit the raw, not the page.

  3. Reingest: Run awiki reingest <page> with the same page reference (a raw name also works). This re-renders the page from the raw; it does not author changes itself.

  4. Review the diff: On a normal edit-the-raw loop, reingest will stop with a divergence diff (the page's pre-edit lines differ from your edited raw). That is expected — confirm the - lines are just the old versions of what you rewrote (not unique page-only content you'd lose), then re-run with --force.

  5. Report what changed.

Footgun: reingest regenerates the page's slug from the first # H1. Changing the H1 renames the page path and orphans the old one — keep the H1 stable unless you intend to rename.

Alternative: awiki ingest <file> --update authors the raw externally and rebuilds, matched by basename. Use one path or the other, not both at once.

Remote vault (awiki init --remote …): the raw lives on the server, so steps 1–2 (editing raw/<stem>.md in place) don't apply — over the wire reingest only re-renders the page from the server's current raw. To change content remotely: awiki show raw/<stem>.md > <stem>.md, edit it, then awiki ingest <stem>.md --update (the client uploads the new bytes; the server rewrites the matching raw and rebuilds).

Choosing a Topic

Ask the user which topic to file under if not obvious:

  • projects — project-specific knowledge
  • decisions — architectural or technical decisions
  • research — general research findings
  • tools — tool configurations and usage notes

Choosing Tags

Suggest relevant tags based on the content. Keep them short and lowercase.

Frequently asked questions

What does the Awiki Save AI skill do?

Save content from the current conversation to the Agent Wiki. Use when research, decisions, or valuable findings should be preserved.

Why use Awiki Save on TypingMind?

Because you install it once and use it with any model. Awiki Save 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 Awiki Save in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TacoTakumi/agent-wiki/tree/main/src/agent_wiki/skills/awiki-save. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Awiki Save?

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 Awiki Save?

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

Is the Awiki Save AI skill free?

It is published on GitHub by TacoTakumi. 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.

Related AI Skills

View all
anthropics logo

Algorithmic Art

anthropics
OrganizationPopular

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or…

21.8K
184K
2 files
View
anthropics logo

Doc Coauthoring

anthropics
OrganizationPopular

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This…

21.8K
184K
Instructions
View
vercel logo

Authoring Skills

vercel
OrganizationPopular

How to create and maintain agent skills in .agents/skills/. Use when creating a new SKILL.md, writing skill descriptions, choosing frontmatter fields, or deciding what content belongs in a skill vs…

34.7K
143.1K
Instructions
View
vercel logo

Dce Edge

vercel
OrganizationPopular

DCE-safe require() patterns and edge runtime constraints. Use when writing conditional require() calls, guarding Node-only imports (node:stream etc.), or editing define-env-plugin.ts / app-render /…

34.7K
143.1K
Instructions
View

Set up your own AI workspace now

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