Tinkerer. Fixer. Product Builder. Crafting Products with AI @Google Writes and builds on anshumani.com/ and teaches on: maven.com/anshumani
Singapore
- Tweets 4,339
- Following 272
- Followers 15,530
- Likes 6,636
Pinned Tweet
I'm teaching three free lessons on Maven, starting September 29. Each is an hour long, with a live walkthrough and a recording available afterwards.
2
5
748
I'm teaching three free lessons on Maven, starting September 29. Each is an hour long, with a live walkthrough and a recording available afterwards.
2
5
748
October 13: The Voice-First AI Stack for People Who Live in Meetings
We'll cover dictation, searchable meeting transcripts, and using those transcripts to draft briefs and action items. I'll also show how to connect meeting notes, email, calendar, and files to an agent through MCP.
maven.com/p/dfb773/the-voice…
2
82
Each session walks through a practical setup you can use in your own work. Join one or all three.
Sign up here: maven.com/anshumani
56
Every agent I use now (Claude, ChatGPT, Grok) can reason well. None of them do a task the same way twice.
I noticed this doing something boring: asking an agent to review a contract the way I do it, with my checklist, my exceptions. Tuesday's output didn't match Thursday's. Not because the model got worse. Nothing ever told it my procedure, and it forgets my last correction the moment the session ends.
That's not a model problem. It's a missing-skill problem.
A skill is a small file that teaches an agent your procedure once. Claude, ChatGPT, and Gemini all read the same format, and it stays out of the way until the task actually matches.
There are two ways to get one. Adapt what already exists: skill repositories now hold strong, well-tested skills for real work like code review, data cleaning, and documentation, so find one close to your workflow and adjust it. Or build one from your own expertise, the stuff no registry has because no one else does your job your way. That second kind takes longer and is worth more, but neither is the lesser option.
Building it well has an order that's easy to skip: interview yourself for the gotchas nobody wrote down, write the description before anything else since that's the only part the agent always sees, write the body next with nothing generic in it, then add two or three real evals so you're not just guessing it works. Most skills fail because someone skipped that last step.
I'm running a live workshop on this on September 17, 10:30am to 2pm EDT. We build a real skill from a task you actually do, test it, and ship it in one sitting.
maven.com/anshumani/agent-sk…
5
1
9
1,496
This is the full primer behind my Agent Skills masterclass, a practical, no-fluff reference for building, evaluating, and shipping skills across Claude Code, ChatGPT and Gemini.
You'll get the open Agent Skills standard and SKILL [.] md file format; a clear mental model for skills vs MCP vs subagents vs plugins; platform-by-platform breakdowns for Claude Code, ChatGPT and Gemini, including their extended frontmatter and quirks; a full workflow for designing a new skill from scratch, sourcing real expertise, and avoiding the generic-instructions trap; techniques for writing descriptions that trigger reliably instead of silently failing; an eval-driven development framework for testing and scoring skills before you ship them.
23 pages, written for anyone (technical or non-technical) building or maintaining agent skills.
Share with friends, colleagues and other builders. Agent Skills are for everyone.
maven.com/anshumani/o/fa0c8b
2
3
14
1,564
I am running three free lightning lessons on Maven next week:
The first is about why AI features fail on evaluation rather than on the model - we'll walk the loop end to end: define what "good" means, build a Golden Set, pick the right eval type, then automate.
The second cuts through the vocabulary around agents, MCPs, and skills, working inside ChatGPT, Claude Code, and Cowork; no prior setup needed.
The third is about getting out of the keyboard's way - typing caps you at 50–70 WPM and forces editing before you've finished thinking, so we'll look at voice-first agentic tools that turn messy conversation into structured product output.
They're independent, so come to whichever is useful. Every session is recorded and the video goes out afterwards, so sign up even if the time doesn't work.
1
1
644
Agents and Agent Skills: A Practical Walkthrough - Thursday, September 10, 3:00 PM PDT maven.com/p/a59035/agents-an…
1
101
Agentic Toolset Powering the Super IC Product Manager - Friday, September 11, 3:00 PM PDT maven.com/p/2cc927/agentic-t…
73
Announcing the third cohort of my flagship course, Level Up to Product Super IC with AI. It goes live September 12 and runs through October 10.
This cohort is massively expanded: a full five weeks, with a three-hour live workshop every weekend and office hours during the week, and all material updated for where AI is today.
The first two cohorts hold a perfect 5.0 rating on Maven, with alumni from Stripe, WhatsApp, Netflix, Swiggy, Rakuten and many more global companies (see their reviews below).
1
1
7
1,158
Up at 3 AM in Singapore watching the finals with the 10-year-old. Fastest he has ever woken up!
13
1,583
My interview with Nikhil Kapahi of the Inner Scorecard podcast is now out. This was a wide-ranging conversation where we spoke about AI, its impact on SMBs and the creative arts, the Super IC philosophy, how I've thought about my career and made decisions, being a parent in the modern world and many more topics.
The interview is in two parts on Youtube: piped.video/watch?v=-qR5VV5V…
You can also listen to it on Spotify and Apple Podcasts:
1
2
1,149
The language around AI agents gets in the way of understanding them. Terms like agents, MCP, and skills are used constantly, often without anyone explaining what they actually refer to, and that makes the whole subject feel more complicated than it really is.
In the third free session of my Summer of AI Building series, I want to clear that up. On Tuesday, July 14 at 3:00 PM PDT, I will go through what an agent, an MCP, and a skill each mean, using plain language and real examples, and then build and install a simple skill inside Claude Cowork so you can see how the pieces fit together.
3
1
4
547