superpowers VS rift-transcription

Meanwhile, the ecosystem materialized. obra/superpowers shipped a complete software development methodology built on composable skills — 1,276+ stars and growing. The cobusgreyling/loop-engineering repo cataloged patterns from Osmani and Cherny into a practical reference.

Projects like Superpowers proved that agents can follow structured methodologies — brainstorm before coding, write tests before implementation, review against specs before declaring success. The skills are mandatory workflows, not suggestions. The agent checks for relevant skills before any task.

If you're looking for complementary skills and plugins then have a look at Addy Osmani's Agent Skills or Superpowers, both provide essential coding assistant skills like Test-Driven Development (TDD). OpenSpec provides consistency, and your workflow can evolve around it.

Before any implementation, I plan. I use the brainstorming skill from Superpowers to think through the approach, then Grill Me - a separate skill that probes for contradictions, gaps, and missing assumptions, question by question. Once I'm satisfied, I save the result as a PRD and move to writing-plans (also from Superpowers), which produces a detailed implementation plan: class names, properties, architecture, tests.

These don't replace the spec; they govern how the agent acts on it. Superpowers uses guided Q&A to clarify intent, then runs sub-agents behind a verification-before-completion gate. GSD manages context in waves for solo developers. HVE Core runs an RPI loop: Research, Plan, Implement, Review.

> It would be extremely cool to be able to write one or two lines of prompt in my harness, and have a light model iterate with me a few times writing/proposing requirements, guidelines and explanations, refining the prompt until it's ready to be sent to the actual LLM.

I feel like the vast majority of AI-using coders already do this via skills suites like Superpowers (see /superpowers:brainstorming), no? https://github.com/obra/superpowers

I sometimes use Superpowers skills such as writing-plan and writing-spec. The Superpowers brainstorming skill stores design specs under docs/superpowers/specs/YYYY-MM-DD--design.md, and the writing-plans skill stores implementation plans under docs/superpowers/plans/YYYY-MM-DD-.md. (GitHub, GitHub)

obra/superpowers – GitHub

I would delay polishing until right before delivery.

Eventually, I will add a polishing step to my own https://rift-transcription.vercel.app.

Right now, you can experience what true realtime streaming transcription feels like.

I plan to add two "levels" of polishing:

- Simple deterministic text replacements will be applied to both interim and final text.

- LLM polishing will only be applied right before delivery.

- It will be possible to undo one or both polishing steps. (Actually even more fine-grained undo: at the replacement rule level).

# My over-engineered console.log replacement is API/feature-stable: https://github.com/Leftium/gg

- Named `gg` for grep-ibility and ease of typing.

- However Claude has been inserting most calls for me (and can now read back the client-side results without any dev interaction!)

- Here is how Claude used gg to fix a layout bug in itself (gg ships with an optional dev console): https://github.com/Leftium/gg/blob/main/references/gg-consol...

---

# I've been prototyping realtime streaming transcription UX: https://rift-transcription.vercel.app

- Really want to use dictation app in addition to typing on a daily basis, but the current UX of all apps I've tried are insufficient.

---

# https://veneer.leftium.com is a thin layer over Google forms + sheets

- If you can use Google forms, you can publish a nice looking web site with an optional form

- Example: https://www.vivimil.com

- Example: https://veneer.leftium.com/s.1RoVLit_cAJPZBeFYzSwHc7vADV_fYL...

- DEMO (feel free to try the sign up feature): https://veneer.leftium.com/g.chwbD7sLmAoLe65Z8

Yeah, I will add post-processing to my prototype, too. I already prepared a detailed spec (prototyping new ways to do this, as well): https://github.com/Leftium/rift-transcription/blob/main/spec...

One idea I was tossing around was streaming transcription + batch re-transcription:

- Use streaming transcription, which works most of the time (for example, I've found the Web Speech API pretty good, as well as moonshine)

- If the streaming transcription was poor, select the bad part and re-transcribe with a more accurate batch transcription model.

WASM-based port: https://github.com/moonshine-ai/moonshine-js

I also did a survey of other in-browser transcription solutions: https://github.com/Leftium/rift-transcription/blob/main/refe...

- Notably, there is an (unrelated?) moonshine demo based on transformers.js (using WebGPU) with WASM fallback.

> just a silent failure and your recording (I tend to talk for 5-10mins) is gone

One of the reasons for my streaming transcription app: https://rift-transcription.vercel.app

- You see results in less than a second as you talk.

My app also supports multimodal input: interleave talking with typing. (Click the Replay" button to see a color-coded demo.)

Supports local models (with a little setup: https://rift-transcription.vercel.app/local-setup)

I've been making something similar; this is my new tab page: https://multi-launch.leftium.com

Special features:

- similar concept to Keyjump queries: the links change to search templates depending on if the query input has a value

- it can launch multiple bookmarks/queries at once (the blue category buttons)

---

The next version is based on search bangs: https://zbang.leftium.com

- Right now it's just a list of search bangs, but this list will be moved to a slash command

- Then the list will be replaced with your own bookmarks, sorted by "frecency," with favorites pinned to the top.

- Another tab will list your bookmark (search) history: a sort of "zero effort" journal. (I switched to Kagi, which lacks search history. And browser history is insufficient.)

- Another tab can contain your notes (like SimpleNote)

- I may even integrate dictation, so you don't even have to touch the keyboard (https://rift-transcription.vercel.app)

Very nice!

I've been using mdserve. A nice feature is a sidebar that lists all the MD files in a directory. I wish it could also list sub-directories.

The reason is because I organize related MD files in directories, with sub-directories. Folders without MD files should be filtered out.

Here is an example project with MD files in both reference and specs (and root) folders. Other folders should be filtered out: https://github.com/Leftium/rift-transcription

---

The brew install did not work; the App source name is wrong: `Error: It seems the App source '/opt/homebrew/Caskroom/markdown-prism/0.2.0/Markdown Prism.app' is not there.`

- No, I did not know everything I wanted to cover beforehand. Claude helps me brainstorm, research, and elaborate on my ideas. The spec is a living document, that I occasionally check-in: https://github.com/Leftium/rift-transcription/commits/main/s...

- It was definitely not one CC session. In fact, this spec is a spin-off of several other specs on several other branches.

- I've actually experienced quite the opposite: I suggest an idea for the spec and Claude says "great idea!" Then I change my mind and go in the opposite direction: "great idea!" again. Once in a while, I have to argue with Claude to get my idea implemented (like adding dependencies to parse into a proper AST instead of regex.)

- One tip: it's very useful to explain the "why" to Claude vs the "what." In fact, if you just explain the why/problem without a specific solution, Claude may surprise you with the options they come up with!