Octo Matter logo

Octo Matter

Organization
Mininglamp-OSS
octo-matter

Matter (todo/task) domain — CRUD, status transitions, assignees, channels, timeline, and AI extract from chat messages. Load after octo-shared.

Overview

PublisherMininglamp-OSS
Repositoryocto-cli
Skill nameocto-matter
Stars
918
Forks
130
Bundled files
Instructions only
LicenseApache-2.0
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 Mininglamp-OSS on GitHub. Read the source before you install it.

Installation

Install the Octo Matter 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/Mininglamp-OSS/octo-cli/tree/main/skills/octo-matter
  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/Mininglamp-OSS/octo-cli.git /tmp/octo-cli
mkdir -p .claude/skills
cp -r /tmp/octo-cli/skills/octo-matter .claude/skills/octo-matter
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Octo Matter 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 Octo Matter 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 Octo Matter 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.

octo-matter — the matters domain

A matter is the Octo equivalent of a task or todo. The domain has 17 operations across five groups: core CRUD, status transitions, assignees, channels, and timeline. Plus one LLM helper: matter extract.

Backend: matters service at $OCTO_API_BASE_URL/api/v1/matters. Both App Bot and User Bot can call every operation in this domain.

1. Core CRUD

bash
octo-cli matter create --title "Fix login bug"                     # required: --title (≤500 chars)
octo-cli matter list   --status open --assignee-id me --limit 50   # cursor pagination
octo-cli matter get    <id>
octo-cli matter update <id> --title "..." --description "..."
octo-cli matter delete <id>                                        # soft delete

create also accepts --description (≤10 000), --assignee-ids (repeatable — supports me alias), --deadline (RFC3339), --remind-at (RFC3339), --source-channel-id, --source-channel-type (1=user, 2=group, 5=thread), --source-name.

list filters: --status, --assignee-id (me supported), --creator-id, --q <query>, --source-channel-id, --source-channel-type, --channel-id, --limit (default 20, max 100), --cursor.

2. Status transitions

There is no state machine — any status can move to any status.

bash
octo-cli matter transition <id> --status done
octo-cli matter close      <id>          # alias → --status done
octo-cli matter reopen     <id>          # alias → --status open
octo-cli matter archive    <id>          # alias → --status archived

Valid values: open, done, archived.

3. Assignees

bash
octo-cli matter assignee add    <id> --user-id <uid>
octo-cli matter assignee remove <id> <uid>

--user-id accepts me to self-assign. Adding a user who is already assigned returns DUPLICATE_ASSIGNEE (validation error — recover by listing current assignees first).

4. Channels

Link a matter to a chat channel so conversations show up in context.

bash
octo-cli matter channel link   <id> --channel-id <cid> --channel-type 1   # 1=user 2=group 5=thread
octo-cli matter channel link   <id> --channel-id <cid> --channel-type 2 --channel-name "#eng-ops"
octo-cli matter channel unlink <id> <channel_id>

5. Timeline

Timeline entries are the successor to comments. Simple text goes through --content; attachments, quoted messages, and channel context go through --data:

bash
octo-cli matter timeline add    <id> --content "Ping from oncall"
octo-cli matter timeline add    <id> --data '{
  "content":"see attached log",
  "attachments":[{"url":"https://…/log.txt","name":"log.txt","type":"text/plain"}]
}'
octo-cli matter timeline list   <id>                           # paginated
octo-cli matter timeline delete <id> <entry_id>

--content caps at 10 000 characters.

6. AI extract — create a matter from chat messages

matter extract hands a chat transcript to an LLM and returns a structured matter. Typical bot use:

bash
octo-cli matter extract --data '{
  "channel_type": 2,
  "channel_id":   "ch_abc",
  "creator_uid":  "<bot-owner-uid>",
  "msgs": [
    {"uid":"u_alice","text":"we need to fix login"},
    {"uid":"u_bob","text":"+1 by friday"}
  ]
}'

Critical: a bot must set creator_uid to its owner_uid, not its own bot_uid — the backend rejects the request otherwise. Capture owner_uid from the one-time octo-cli bot register response at publish (--jq '.data.owner_uid') and cache it (env/config); reuse the cached value rather than re-registering on every extract. Note bot user-info does not return it (it needs --uid and returns only {uid,name,avatar}).

7. Common patterns

Self-scope with me

Anywhere an assignee UID is accepted, me resolves server-side to the caller's UID.

bash
octo-cli matter list --assignee-id me --status open

Cursor pagination

All list endpoints follow {data:[], pagination:{has_more, next_cursor}}. Let the CLI walk them:

bash
octo-cli matter list --status open --page-all
octo-cli matter timeline list <id> --page-all --page-limit 5

Pipe chains

bash
octo-cli matter list --status open --assignee-id me --jq '.data[].id' \
  | xargs -I{} octo-cli matter close {}

8. Error recovery

error.codeWhat to do
MATTER_NOT_FOUNDConfirm the id with octo-cli matter list before retrying.
ASSIGNEE_NOT_FOUNDThe UID is wrong or not in the space. octo-cli bot space-members to verify.
DUPLICATE_ASSIGNEEAlready assigned — list current assignees and skip.
FORBIDDENBot lacks space membership or owner-equivalent permission.
SPACE_FORBIDDENOCTO_SPACE_ID / --space points at a space the bot isn't in.
VALIDATION_ERRORerror.detail.details names the offending field; fix and retry.
PAYLOAD_TOO_LARGEBody over 1 MB — trim description/timeline content.
RATE_LIMITEDHonour the cooldown window; the retry wrapper already waits once.

9. Schema lookup

When unsure about a flag or body shape:

bash
octo-cli schema matter.create
octo-cli schema matter.list
octo-cli schema matter.timeline.add

Everything in this skill is derived from those specs — if the schema says otherwise, trust the schema.

Frequently asked questions

What does the Octo Matter AI skill do?

Matter (todo/task) domain — CRUD, status transitions, assignees, channels, timeline, and AI extract from chat messages. Load after octo-shared.

Why use Octo Matter on TypingMind?

Because you install it once and use it with any model. Octo Matter 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 Octo Matter in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Mininglamp-OSS/octo-cli/tree/main/skills/octo-matter. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Octo Matter?

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 Octo Matter?

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

Is the Octo Matter AI skill free?

Yes. It is published on GitHub by Mininglamp-OSS under the Apache-2.0 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 👇