Posted on Mar 17 • Edited on Apr 1

Drop Your Challenge Submission Here - v0

#notionchallenge #weekendchallenge #geminireflections #wecoded

Built something for a DEV Challenge but feel like not enough people saw it?

This post is for exactly that.

Sometimes great submissions get buried in the challenge feed and never get the attention they deserve. So let’s fix that.

Use this thread to show what you built, meet other builders, and get real feedback on your project.

Share your submission in the comments

Include:

your project title
a short description of what it does
the link to your submission
what kind of feedback you want

Why this thread exists

Not every strong project gets noticed the first time.

Some are posted early. Some are posted late. Some just get lost in the volume.

This is a second chance to put your work in front of more people.

What you can get from posting here

more visibility
feedback from other developers
new ideas for improving your project
more discovery for underrated submissions

If you made something cool, drop it below.

You might find your next supporter, collaborator, or your first real traction in this thread.

Top comments (88)

Swift • Mar 17

This is such a cool idea, thanks for starting the discussion!

Nikoloz Turazashvili (@axrisi) • Mar 17

Receiving such feedback from someone with 8 year club badge is flattering! haha.

Thanks, man :)

Will keep posting new versions as more challenges come!

Thea • Mar 17

DevStretch
An installable PWA that interrupts your coding session with dev-themed movement breaks.
Highlights: terminal dark aesthetic, voice guidance, CLI progress bar, stand-up reminders, zero dependencies, and vanilla JS only:)
Submission link
Feedback welcome on anything, but especially curious if the notification flow works for you (it's my current open issue 😅)

Nikoloz Turazashvili (@axrisi) • Mar 18

Hey! Love the project - the terminal aesthetic and zero-dependency approach is really clean.
I put together a PR that replaces the browser TTS with pre-generated ElevenLabs audio for higher quality voice guidance, while keeping full offline support through the Service Worker cache: PR #2

feat: replace browser TTS with pre-generated ElevenLabs audio #2

turazashvili posted on Mar 18, 2026

Replaces window.speechSynthesis (browser TTS) with high-quality pre-generated ElevenLabs audio files.

All 103 voice clips are cached by the Service Worker for full offline support
Includes a Node.js generation script (scripts/generate-tts.js) for reproducibility
Matches the original voice flow exactly (only exercise 1 gets full description read aloud)
Custom audio queue system handles sequential playback and graceful cancellation seamlessly

View on GitHub

Would love to hear what you think!

Thea • Mar 18

Thank you so much for this, I really appreciate the effort! 🙏
The audio quality is impressive, but I want to keep the app fully lightweight and dependency-free; that was one of the core goals from the start..

Also tbh, the slightly robotic browser TTS fits the terminal aesthetic better than I expected, it feels almost intentional 🤭

So I’ll stick with the native browser APIs for now. Though this is a very cool approach and a great reference for anyone who wants higher-quality audio in their own fork!

Nikoloz Turazashvili (@axrisi) • Mar 18

No worries. It's up to you :)

The PR didn't add any dependencies, but increased the overall size of the project by 4mb because of the audios being sent to users. And the Vercel free plan for bandwidth is good enough, and I made it to be cached in the browser. So it shouldn't be a big deal either.

But again, all good! You can close that PR if there is no need.

Thea • Mar 18

Thank you for clarifying! Really appreciate the thought you put into this, especially the caching approach 😊 I’ll keep it in mind

Nikoloz Turazashvili (@axrisi) • Mar 18

🇬🇪 🇬🇪 🇬🇪

Thea • Mar 18

დიდი მადლობა ☺️

Daniel Nwaneri • Mar 17

Built a knowledge evaluator on Cloudflare Workers that scores conversation excerpts using Workers AI and routes them to Notion based on confidence — high signal auto-promotes, ambiguous items land in a Review Queue for human judgment, Claude Desktop reads them back via MCP. The bidirectional loop was the part most submissions missed.
dev.to/dannwaneri/i-built-a-knowle...

Nikoloz Turazashvili (@axrisi) • Mar 17

Nice one!
Anyone with experience in Cloudflare Workers?

Daniel Nwaneri • Mar 17

Yes,been building on Workers for a few years in production. The evaluator was the first time I paired Workers AI with Notion as a judgment surface rather than just storage. Happy to answer anything on the Workers or Workers AI side.

Sushant Rahate • Mar 17

Project Title
JS Daily Byte - Daily JavaScript Quotes Telegram Channel

Short Description
JS Daily Byte is an automated Telegram channel that posts one JavaScript concept every day. It uses GitHub Actions as a scheduler, reads quotes from a JSON file, and sends the daily post to Telegram using the Bot API. The whole system runs without any server, database, or hosting.

Submission Link
dev.to/sushantrahate/js-daily-byte...

Feedback I’m Looking For
I’d love feedback on:

Suggestions to improve the architecture and automation flow
Ideas to make the daily JavaScript content more engaging for developers

Nikoloz Turazashvili (@axrisi) • Mar 17

I love the simplicity of this project! So there can be many ideas on how to make it "better", but it will become more complex.

I think a couple of things you can make is Open Discussion group

And maybe add more channels to distribute, like X, Mastodon, BSKY.

Sushant Rahate • Mar 17

Thanks for the suggestion! I tried to keep the system intentionally simple with GitHub Actions only. ♥️

The discussion group is a really good idea actually. It could turn the channel into more of a learning community. Also thinking about distributing the posts to other platforms later.

Nikoloz Turazashvili (@axrisi) • Mar 17

Happy you found my suggestions useful :)

I think you could also add some inline buttons under each post that can do something useful. not sure, maybe you can do upvotes or something. or maybe for upvotes you can use emojis. you can create some styled emojis and allow only those to be used for posts. also allow paid reactions if someone wants to support the project.

this is how you limit reactions:

Sushant Rahate • Mar 17

Thanks! I’ve updated the reactions and decided not to enable paid reactions.

Nikoloz Turazashvili (@axrisi) • Mar 17

Nice! I dropped one custom emoji in discussion chat if you like it you can add :)

James Carter • Mar 17

yes! chatting with "our" people in comments would be great.

Sushant Rahate • Mar 17

I’ve enabled the chat option now, thanks for the suggestion!

Sushant Rahate • Mar 17

Thanks again for the suggestion! I’ve enabled the discussion group so the community can now discuss the daily JS concepts.

Dickson Kanyingi • Mar 18

This is a really clean idea. I like how you kept the system minimal and avoided unnecessary infrastructure. Using GitHub Actions as a scheduler + no backend is a nice touch 👍

A couple thoughts that came to mind:
• Have you considered making the content slightly more interactive?
Maybe adding a short example or “quick challenge” with each concept could make it more engaging.
• For architecture, this is already solid for the use case, but I’m curious:
would you ever consider letting users subscribe to specific topics (closures, async, etc.) instead of a single stream?
• Also wondering if adding a simple web archive of past posts could increase discoverability beyond Telegram.

Overall, really like the simplicity and execution here, feels very practical. Curious how you’re thinking about growing the content side of it 👀

Sushant Rahate • Mar 19

Thanks a lot for the thoughtful feedback!

I want to keep the project minimal and focused on daily core JS concepts, not turn it into a full tutorial.

I’ve also enabled the chat feature so people can discuss and explore topics further.

Topic-based subscriptions are interesting, but might go against the minimal approach I’m aiming for right now.

A web archive is a great point as well. For now, I’m keeping everything within Telegram to keep it simple, but it’s something I might explore later.

James Carter • Mar 17

subscribing now!

Ben Halpern • Mar 17

Good call

Nikoloz Turazashvili (@axrisi) • Mar 17

Thanks, Ben.

I’m thinking of turning this into a recurring series, like “Welcome Thread v1, v2, v3” as new challenges go live. Since DEV only allows 4 tags per post, that also helps keep each thread focused on active challenges and recent projects.

Ben Halpern • Mar 17

Yeah, I agree something like this :)

Nikoloz Turazashvili (@axrisi) • Mar 17

Let me start 👇

Here are a few of my recent projects and challenge submissions.

1. Notion Skills Registry

Notion Skills Registry: A Package Manager for AI Agent Skills with MCP

Nikoloz Turazashvili (@axrisi) ・ Mar 16

#devchallenge #notionchallenge #mcp #ai

A Notion-based registry designed to manage AI agent skills like packages.

Instead of duplicating prompts and workflows across projects, this system lets you version, organize, and distribute skills from a central workspace. It works well for teams building with MCP and agent frameworks where skills evolve quickly.

2. Gemini-Powered History Narrator

I Built a Gemini-Powered History Narrator 6 Months Ago. Here's What I'd Tell You Now.

Nikoloz Turazashvili (@axrisi) ・ Feb 28

#devchallenge #mlhreflections #gemini #geminireflections

An AI storytelling project that turns historical events into engaging narrated experiences using Gemini.

The post reflects on building the project months ago and shares lessons learned about AI narration, storytelling prompts, and what I would do differently today.

3. Issue Discovery Tool for Open Source Contributors

Ever Spent Hours Looking for an Open Source Issue to Contribute To? Those Days Are Over.

Nikoloz Turazashvili (@axrisi) ・ Feb 28

#devchallenge #weekendchallenge #showdev

A tool built to help developers find open-source issues to contribute to faster.

Instead of browsing GitHub endlessly, it surfaces relevant issues and helps contributors discover projects where they can actually make an impact.

Curious to hear what you think.

Now it’s your turn. Drop your challenge submission below 👇

Jackson Kasi • Mar 19

Hey 👋

I’d like to submit my project, TableCraft

🔗 GitHub: github.com/jacksonkasi1/TableCraft

It’s a developer-first tool focused on making data tables more efficient, flexible, and easy to use in real-world apps. Built with a strong focus on performance and usability.

Would love your feedback! 🚀

Nikoloz Turazashvili (@axrisi) • Mar 19

hey!
Have you submitted the project using the template of the challenge?
Link to challenges: dev.to/challenges

Do it first if you haven't done it. This thread is to get feedback, not to submit projects for challenges :)

Jackson Kasi • Mar 19

Oops! Sorry, I didn’t notice that. Thanks for pointing it out.

Kumar Kislay • Mar 20

this is awesome tool, have you listed it on forg.to?

Ken W Alger • Mar 19 • Edited

Archival Intelligence: A Forensic Rare Book Auditor
I built the Rare Book Intelligence MCP Server, a specialized forensic agent that turns a Notion workspace into an expert appraisal lab. In the world of high-value assets, the difference between a lowercase 'j' and a capital 'J' on a 1925 Gatsby dust jacket represents a $150,000 valuation swing.
dev.to/kenwalger/archival-intellig...
Any feedback is welcome, but how would you take this to the next level? I have thoughts (and a current blog series) on my expansion, but what about folks here?

Nikoloz Turazashvili (@axrisi) • Mar 20 • Edited

1/2
this is unique niche!

One thing I can suggest right away is to turn that prompt you copy pasted to reusable skill and add it everywhere you need it.

Here is example, but I didn't dig deep to see if it fits 100% to the workflow, please double check:

# Forensic Book Audit

## Purpose
Conduct a formal forensic audit for a collectible book by comparing observed copy details against bibliographic ground truth and market data, then update internal records if a material discrepancy is confirmed.

## Inputs
- `book_title`: Title of the book being audited
- `claimed_edition_year`: Claimed edition/year to verify
- `observed_feature`: Specific observed characteristic of the copy
- `expected_feature_field`: Bibliographic feature to validate against
- `catalog_database`: Name of the catalog database
- `bibliography_database`: Name of the master bibliography database
- `market_database`: Name of the market results database
- `audit_log_database`: Name of the audit log database
- `flag_status_value`: Status label to apply if discrepancy is confirmed
- `risk_threshold_note`: Optional explanation of why the discrepancy is material

## Required Data Sources
1. Books Catalog
2. Master Bibliography
3. Market Results
4. Audit Log

## Protocol
1. **Search Catalog**  
   Find the entry for `{{book_title}}` in `{{catalog_database}}`.

2. **Archival Lookup**  
   Search `{{bibliography_database}}` for `{{book_title}}` and `{{claimed_edition_year}}`.  
   Retrieve the bibliographic ground truth for `{{expected_feature_field}}`.

3. **Market Analysis**  
   Search `{{market_database}}` for comparable market results tied to the relevant states, issue points, or variants.  
   Identify the price difference between the correct state and the observed state.  
   Save the most relevant citation link if one exists.

4. **Forensic Collation**  
   Compare:
   - Observation: `{{observed_feature}}`
   - Ground Truth: bibliographic requirement for `{{expected_feature_field}}`

   Determine whether the observation matches or conflicts with the required point.

5. **Execution Rules**
   - If the discrepancy is confirmed:
     - Update the matching record in `{{catalog_database}}`
     - Set its status to `{{flag_status_value}}`
     - Create a new entry in `{{audit_log_database}}`
     - Include:
       - book title
       - claimed edition/year
       - observed feature
       - ground truth
       - discrepancy summary
       - estimated overvaluation risk
       - supporting market reference
   - If no discrepancy is confirmed:
     - Do not change status
     - Record that the copy is consistent with the bibliography if logging is required

6. **Reporting**
   Return a final report in Markdown containing:
   - Exhibit Label
   - Audit Verdict
   - Summary of discrepancy or match
   - Estimated market impact
   - Citation link from market results, if available
   - Notion page IDs or record IDs updated

## Decision Standard
A discrepancy is confirmed only if:
- the observed feature clearly conflicts with the master bibliography, and
- the conflicting point materially affects state, issue, or market value.

## Output Format

### Exhibit Label
`EXHIBIT: {{book_title}} Forensic Audit`

### Report Template
- **Book:** {{book_title}}
- **Claimed Edition/Year:** {{claimed_edition_year}}
- **Observed Feature:** {{observed_feature}}
- **Ground Truth:** {{ground_truth}}
- **Verdict:** {{Confirmed Discrepancy / No Discrepancy}}
- **Catalog Status:** {{Updated to Flagged / No Change}}
- **Estimated Market Impact:** {{value_difference}}
- **Audit Log Entry Created:** {{Yes / No}}
- **Updated Record IDs:** {{record_ids}}
- **Market Citation:** {{citation_link_or_none}}

## Behavior Rules
- Be precise and conservative.
- Do not infer bibliographic facts without evidence from the master bibliography.
- Do not estimate market impact without support from market records.
- If any required source is missing, explicitly report that the audit is incomplete.
- Prefer exact matching on title and edition/year before using fuzzy matching.

## Example Invocation
- `book_title`: The Great Gatsby
- `claimed_edition_year`: 1925
- `observed_feature`: Back jacket has a capital "J" in "Jay Gatsby"
- `expected_feature_field`: dust jacket state point
- `catalog_database`: Books Catalog
- `bibliography_database`: Master Bibliography
- `market_database`: Market Results
- `audit_log_database`: Audit Log
- `flag_status_value`: Flagged
- `risk_threshold_note`: Potential six-figure overvaluation if jacket state is misidentified

Nikoloz Turazashvili (@axrisi) • Mar 20

2/2
Another thing, from what I can see in the repo, it only works on source csv's, right?
Maybe there are any public APIs to get the data, and AI will do that alongside general analysis, database queries, and Notion updates?

Ken W Alger • Mar 20

In my cursory look of 'rarity state' resources for things like books, coins, etc. I didn't find one that was what I was looking for for this example application. The idea here too is that this idea is extendible beyond just books, right? Postage stamps, coins, sports memorabilia, etc. all have large dollar value items that could have the same approach taken for.

Nice job on the prompt, btw.

Nikoloz Turazashvili (@axrisi) • Mar 20

I guess that's the idea for your next billion dollar SAAS project to create a service to provide that info for all collectibles? ))

Ken W Alger • Mar 20

That's not a project I personally want to tackle, but it would be interesting.

deeptej • Mar 19

CosmoDex

now you can simply 'speak' to NASA NEO data, thanks to gemini! Check it out here: dev.to/astrodeeptej/fusing-nasa-da...

Jowi A • Mar 19 • Edited

Hey everyone here's my submission Plante which is an automated greenhouse and gamified learning platform. It even has the little game from the app you can play within the blog 😀 Would love to get feedback on the app and also tips to get better at working with hardware. Thanks!