Hacker News new | past | comments | ask | show | jobs | submit | johnjungles's comments login

Talk to your skip

Maybe we should have models govern models to prevent models from going haywire and falling into a loop of a repetitive pattern or influencing society towards swarm like behavior patterns

Reminds me of Neal Stephenson's thoughts on the topic here: https://nealstephenson.substack.com/p/remarks-on-ai-from-nz

> By training AIs to fight and defeat other AIs we can perhaps preserve a healthy balance in the new ecosystem. If I had time to do it and if I knew more about how AIs work, I’d be putting my energies into building AIs whose sole purpose was to predate upon existing AI models by using every conceivable strategy to feed bogus data into them, interrupt their power supplies, discourage investors, and otherwise interfere with their operations. Not out of malicious intent per se but just from a general belief that everything should have to compete, and that competition within a diverse ecosystem produces a healthier result in the long run than raising a potential superpredator in a hermetically sealed petri dish where its every need is catered to.


If you want to try out mcp (model context protocol) with little to no setup: I built https://skeet.build/mcp where anyone can try out mcp for cursor and dev tools. We did this because of a painpoint I experienced as an engineer having to deal with crummy mcp setup, lack of support you have no idea how hard it is to set up SSE, deal with API keys and scope issues, and then to find things like the tool that you want isn’t even coded yet. And so one of the areas we found it to be useful was to do the soft communications with tools like Jira linear slack - updating stakeholders and all that friction that engineers hate doing. Some other areas people use a lot of tools with sequential thinking Mostly for workflows that I like: * start a PR with a summary of what I just did * slack or comment to linear/Jira with a summary of what I pushed * pull this issue from sentry and fix it * Find a bug a create a linear issue to fix it * pull this linear issue and do a first pass * pull in this Notion doc with a PRD then create an API reference for it based on this code * Postgres or MySQL schemas for rapid model development Everyone seems to go for the hype but ease of use, practical pragmatic developer workflows, and high quality polished mcp servers are what we’re focused on Lmk what you think!


> Lmk what you think!

I think you've been posting variations on this comment for almost 2 months. If you have something to show, do a "Show HN". You'll get a far better response by doing so than from a plethora of self-promotional comments.


ArgoCD


We built https://skeet.build/mcp that allows you to connect mcp easily to figma, Notion, Jira, etc…

Seems like though people want more integration to more local tools


That's cool! Thanks for the recommendation.


https://skeet.build

Building a tool to supercharge your Cursor, Windsurf, Claude and other developer tools by connecting it to polished, high quality mcp servers for linear, slack, DBs, and other useful workflows.


If you want to try out mcp (model context protocol) with little to no setup:

I built https://skeet.build/mcp where anyone can try out mcp for cursor and dev tools.

We did this because of a painpoint I experienced as an engineer having to deal with crummy mcp setup, lack of support you have no idea how hard it is to set up SSE, deal with API keys and scope issues, and then to find things like the tool that you want isn’t even coded yet.

And so one of the areas we found it to be useful was to do the soft communications with tools like Jira linear slack - updating stakeholders and all that friction that engineers hate doing. Some other areas people use a lot of tools with sequential thinking

Mostly for workflows that I like:

* start a PR with a summary of what I just did * slack or comment to linear/Jira with a summary of what I pushed * pull this issue from sentry and fix it * Find a bug a create a linear issue to fix it * pull this linear issue and do a first pass * pull in this Notion doc with a PRD then create an API reference for it based on this code * Postgres or MySQL schemas for rapid model development

Everyone seems to go for the hype but ease of use, practical pragmatic developer workflows, and high quality polished mcp servers are what we’re focused on

Lmk what you think!

Currently working on a desktop app so everything runs on a native Mac app!


hey! we'll build the same thing but just open source it and make it free :)


If you want to try out mcp (model context protocol) with little to no setup hosted for you:

I built https://skeet.build/mcp where anyone can try out mcp for cursor and dev tools.

We did this because of a painpoint I experienced as an engineer having to deal with crummy mcp setup, lack of support you have no idea how hard it is to set up SSE, deal with API keys and scope issues, and then to find things like the tool that you want isn’t even coded yet.

And so one of the areas we found it to be useful was to do the soft communications with tools like Jira linear slack - updating stakeholders and all that friction that engineers hate doing. Some other areas people use a lot of tools with sequential thinking

Mostly for workflows that I like:

* start a PR with a summary of what I just did * slack or comment to linear/Jira with a summary of what I pushed * pull this issue from sentry and fix it * Find a bug a create a linear issue to fix it * pull this linear issue and do a first pass * pull in this Notion doc with a PRD then create an API reference for it based on this code * Postgres or MySQL schemas for rapid model development

Everyone seems to go for the hype but ease of use, practical pragmatic developer workflows, and high quality polished mcp servers are what we’re focused on

Lmk what you think!


I built https://skeet.build which lets your connect your favorite tools via mcp to Cursor. We focus exclusively on developers and dev tools to build high quality “it just works” experiences for mcp because we found that community mcp quality is low, many mcps were not useful for devs, and SSE remote mcp took a lot of effort to get it to a point where it’s reliable and working well.

[Sequential thinking](https://skeet.build/docs/integrations/sequentialthinking) - it’s like enabling thinking but without the 2x cost

[Memory](https://skeet.build/docs/integrations/memory) - I use this for repo / project specific prompts and workflows

[Linear](https://skeet.build/docs/integrations/linear)- be able to find and issue, create models a branch and do a first pass, update linear with a comment on progress

[github](https://skeet.build/docs/integrations/github) - create a PR with a summary of what o just did

[slack](https://skeet.build/docs/integrations/slack) - send a post to my teams channel with the linear and GitHub PR link with a summary for review

[Postgres](https://skeet.build/docs/integrations/postgres) / [redis](https://skeet.build/docs/integrations/redis) - connect my staging dbs and get my schema to create my models and for typing. Also use it to write tests or do quick one off queries to know the Redis json I just saved.

[Sentry](https://skeet.build/docs/integrations/sentry) - pull the issue and events and fix the issue, create bug tickets in linear / Jira

[Figma](https://skeet.build/docs/integrations/figma) - take a design and implement it in cursor by right clicking copying the link selection

[Opensearch](https://skeet.build/docs/integrations/opensearch) - query error logs when I’m fixing a bug


If you want to try out mcp (model context protocol) with little to no setup:

I built https://skeet.build/mcp where anyone can try out mcp for cursor and now OpenAI agents!

We did this because of a painpoint I experienced as an engineer having to deal with crummy mcp setup, lack of support and complexity trying to stand up your own.

Mostly for workflows like:

* start a PR with a summary of what I just did * slack or comment to linear/Jira with a summary of what I pushed * pull this issue from sentry and fix it * Find a bug a create a linear issue to fix it * pull this linear issue and do a first pass * pull in this Notion doc with a PRD then create an API reference for it based on this code * Postgres or MySQL schemas for rapid model development

Everyone seems to go for the hype but ease of use, practical pragmatic developer workflows, and high quality polished mcp servers are what we’re focused on

Lmk what you think!


This looks super cool and I can see myself using this!

Although the name is a bit unfortunate.


my favorite is implementing issues from linear


Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: