Who this is for
Engineers who solve the design in their head but stall on turning it into a written spec everyone can review.
The moment this saves you
I've solved the design in my head on the walk home, then I sit down to write the spec and the blank doc kills all my momentum, so the doc never gets written and the context stays trapped in my head.
See it work
Messy spoken thought in. A clean, structured artifact out.
Okay let me talk through the spec for the notifications system. The problem is right now notifications are sent inline and synchronously, which is slow and fragile. The approach I'm thinking is an event bus, services publish events, a notification worker subscribes and handles delivery. The main tradeoff is added infra complexity, we'd need to run the bus, but we get decoupling and retries for free. Open questions, do we use the existing Redis or bring in something like Kafka, and how do we handle notification preferences, per user or per event type. I'm leaning Redis to start. Out of scope for v1 is digesting and batching notifications.
Spec: Notifications system
- Problem: Notifications are sent inline and synchronously, slow and fragile.
- Proposed approach: Event bus. Services publish events; a notification worker subscribes and handles delivery.
- Tradeoffs: Added infra complexity (running the bus) in exchange for decoupling and free retries.
- Open questions:
- Existing Redis vs introducing Kafka? (leaning Redis to start) - Notification preferences: per user or per event type?
- Out of scope (v1): Digesting and batching notifications
The workflow
Record a voice note
Hit the hotkey and talk, no formatting, no typing.
Tag it with this context
Contextli shapes your words into the structured output above.
Find it later
Everything's searchable and organised by context.
Pull it into Claude or ChatGPT
Bring your contexts straight into your AI tools with the Contextli MCP.
Your raw recording and transcription stay on your device, so you can always go back to the original.
The prompt behind this context
I'm going to talk through a technical design or spec. Turn it into a spec skeleton with: a bold Title, then labeled sections: Problem (what we're solving), Proposed approach (the design, in my framing), Tradeoffs (what we gain and what gets harder), Open questions (a bullet list of the unresolved decisions, keeping my lean if I state one), and Out of scope (only if I mention what's excluded). Keep my technical reasoning and any leanings exactly. Don't invent approaches, tradeoffs, or decisions I didn't raise. Output only the skeleton.
Make it your own. This is a starting point. Once it's in Contextli, tweak the instructions so the output comes out exactly how you like it.
Use this context
One click copies it and shows you exactly how to drop it into Contextli.
Next, open Contextli, go to the Contexts page, click Import, choose From JSON, paste, then Import Context. It is ready to use.
Make it your own. This is a starting point. Once it's in Contextli, tweak the instructions so the output comes out exactly how you like it.
Your raw recording and transcription stay on your device, so you can always go back to the original.
Related contexts
Code Decision Log
Right after you make the call, while the tradeoffs are still fresh, talk through why you went this way and what you rejected. Three months from now when someone asks 'why a queue here?', the answer is already written down.
Feature Request
A customer asks for something and it lands in your head as a vague 'they want X.' Say what they actually asked and the problem underneath. You get a brief with the real user problem, not just the feature, so the backlog reflects needs instead of demands.
On-Call Incident Note
You just fought a fire at 2am and the postmortem is tomorrow, when half the timeline will be gone. Talk through what broke, what you did, and what fixed it, right now. You get a postmortem-ready note while the details are still sharp and real.
Questions people ask
Questions developers ask about Technical Spec Note
What should a spec note include?
A good spec note includes a clear title, steps to reproduce the issue, the expected behavior, the actual behavior observed, the severity or priority, and the environment details such as OS, browser, and app version. The Technical Spec Note context structures your spoken description into these fields automatically, so nothing gets left out when you are in the middle of debugging.
How do I write a spec note in under a minute?
Speak what you found: describe the issue, what you expected, what actually happened, and how bad it is. The Technical Spec Note context structures your words into a complete spec note you can paste directly into Jira, Linear, or GitHub Issues. Most take under 60 seconds to dictate, so you capture them without breaking your flow.
How do developers capture issues without interrupting their flow?
The key is to capture the issue immediately without switching context mentally. Contextli lets you speak a quick voice note describing it and produces a spec note from it. You can dictate while the issue is still on screen, then paste the formatted output into Jira, Linear, or GitHub Issues when you come up for air. No typing is required during the capture step.
Can I write a spec note by talking instead of typing?
Yes. The Technical Spec Note context lets you speak a description in plain language and converts it into a structured spec note with all the required fields filled. You speak the way you would explain it to a colleague, and the context handles the formatting.
How do I add this context to Contextli?
Copy the context on this page, then open Contextli and go to the Contexts page. Click Import, choose From JSON, paste it into the Import from Clipboard window, and click Import Context. It is ready to use in under 30 seconds. If you do not have Contextli yet, you can download it for free first.
Is my voice recording private? Does Contextli send it anywhere?
Your voice recording and the transcription are stored on your device only. Contextli processes your audio locally and does not send your recordings or transcription text to any server. The structured output it produces is text you control, and you decide where it goes.
Can I change what the output looks like?
Yes. Every context in Contextli is a starting point you can edit. Open the context in the app, change the instructions to adjust the structure, tone, or fields, and save. The next time you use it, the output reflects your changes. You are not locked into the default format.
Do I need to install an app to use this context?
Yes. Contextli is a free app. Download it, then copy this context and paste it into the Import from Clipboard window on the Contexts page. The whole process takes about 30 seconds.