oliverchan2024

Excali-mode can do most things as Excalidraw, but without connect to the server,it can run locally standalone.

I develop this because I see my friend play video in Emacs with his package called video.el, and I do some research on it, the result is, it use emacs's dynamic module and the newest Canvas API.

So, I think maybe I can use this tech-stack to do something really cool. At that time, I was chat with my friend, he said, maybe it can run excalidraw inside emacs. I think the idea is worth to try.

I developed a small C module does drawing with Cairo and Pango, and I port rough.js to C, to make excali-mode can support most functions of excalidraw.

Too hard to use.

A qualitative account from a one person music company

I’ve been pairing with AI coding tools a lot, and kept running into the same problems:

- Every time I switch tools/models, I have to re-explain the project. - Specs live in my head or in random chat history. - The AI happily writes code, but there’s no clear “this is the task, this is how we verify it, this is how we log the change”.

SPEC-AGENTS.md is a tiny attempt to fix that.

You drop an `AGENTS.md` file (this repo) plus a small `.phrase/` folder into your project. That file tells the AI to:

- treat docs as the source of truth (`spec_`, `plan_`, `task_`, `change_`, `issue_`, `adr_`) - only tackle one atomic `taskNNN` per session - always write back what happened (what changed, how it was verified)

There’s no server, no binary, no tooling – it’s just conventions the AI is expected to follow. Any tool that can read files (CLI, editor plugin, chat with “read files” feature) can play along.

Rough loop:

1. You and the AI update `spec_` / `plan_` in `.phrase/phases/...` to describe what you want. 2. You break that into small `taskNNN` items, each with a clear output + verification step. 3. The AI implements one task, runs tests/manual checks, and tells you what it did. 4. It writes back to `task_` and `change_`, and updates `spec_` / `issue_` / `adr_*` if needed.

The README has an ASCII diagram and a small “dark mode toggle” example conversation to show what this looks like in practice. There’s also a Chinese section because I originally wrote this for my own projects.

This is still an experiment. It adds a bit of ceremony, so it’s probably overkill for one-off scripts, but it feels good for small projects where you want more structure without bringing in a full PM tool.

I’d love to know:

- Does this doc-first, one-task-per-session style match how you work with AI, or is it too much? - If you already use specs (OpenSpec, your own templates, etc.), would you keep this as a separate “AI contract”, or just integrate the ideas? - What’s missing for this to be useful in your day-to-day?

I think you have a very valuable ability, which is always being able to distinguish what excellent answers are.

Sometimes I miss it, and when I go back to look, I almost can't find it back.

My method is similar to yours, although I don't clear chat history. Because I think if I have that time, it's better to ask directly.

How much time does it take for you to clear chat history every week?

I think this is a method. However, you haven't really solved the problem I mentioned, after all, in your method, the conversation history will only increase.

Suppose you have a hundred conversations that can be retained, how would you manage them?

Honestly, I'm looking forward to hearing your experience with the Canon Cat, and does it match what's said in this article? It's very difficult to find specific operation videos of the Canon Cat, and they are also quite hard to understand.

Welcome use org-sueprtag, a package with org-mode and Eamacs. It's feature org-sueprtag-view-table provide similar function.

And it design for a big document, with many nodes in it, it will filter this nodes by tags and properties.

A minor mode for Org mode that displays #+INCLUDE directive contents inline within your Org buffers.

Great, thank you to share.

I don't use linux, but I'm happy to know that.

A new behavior scheduler with Cron-style scheduling, Org-mode timestamp integration, and dynamic template variables. Automatic sync and conflict detection enhance task management and productivity.

How could I edit the title? I forget put it to Show HN.

You can’t represent others’ opinions. And you’re free to use whatever you want, it’s your choice. I was just pointing out that it seemed like you hadn’t really explored org-supertag but were making comments on it, which felt a bit like trolling.

Yes, you’re right. Many people have mentioned this to me. I’ve updated the README in the latest version, hoping it will make it easier for everyone to understand.

I’m glad that you find this small project useful.

Thank you for the reminder. I’m currently struggling with which open-source license to use. I don’t really want to use GPL-3 because it’s too strict.

Org-roam uses a database, but it is not fully database-based. It only stores the mapping relationships between IDs in the database, but the content itself is not stored in the database.

However, org-supertag is database-based, storing both the content and the relationship mappings in the database.

Cool!

Org-supertag isn't another version org-roam, it's totally differnt way. And, org-supertag can work with org-roram or Denote.

Your words suggest that you haven’t looked into org-supertag.

No tool can meet everyone’s needs. No matter what the tool is, as long as it has a user base, it proves its effectiveness—it’s just not suitable for you.

I was used many tools, include Workflowy and Roam. For me, org-mode & Emacs is the best tool of all, no tool can compare.

Thank you.

Get it.

Great idea.

You're right, I'm working on it.

From my perspective, they are all derivatives of org-mode.

Thank you for your appreciation and suggestions. I’m not quite sure how to publish it to MELPA, but I’ll figure it out as soon as possible.

I like Firefox OS, but unfortunately, I rarely saw any smartphones actually running this system. I feel deeply regretful about it.

Thanky you, hope you like it, and feel free to submit issues, if anything wrong happens.

Yep, it's me.