Index of every page on this site: llms.txt
All skills
hktitan avatar

/khe-brain-varun

@945e23c
by Harshit Khemanihktitan/skills47 stars
2
Run it yourself

Answers startup, content, career and AI questions from what Varun Mayya has said in 18 public videos (13 Katas, 2 talks, 3 podcasts), with the video and the minute named. Gives the claim, its video, its time and a link that opens there; pressure-tests a plan, a pitch or a career decision against his stated positions; says the videos do not cover it when they are silent; shows both sides where he disagrees with himself or changed his mind. Covers distribution, bootstrapping, risk, hiring, leading teams, brand as world building, attribution, AI and jobs, belief, money and status, India, and the Aeos story. Use when someone says "what would Varun say", "ask Varun", "what does Varun Mayya think about", "which Kata was that", "who said that", "pressure-test my plan against Varun". It reads and cites and never drafts: for posts in your own voice use `khe-content-engine`; to pick a skill use `khe-auto`. A reading by Harshit Khemani, not endorsed by Varun Mayya.

Use this Skill: https://skilld.dev/gh/hktitan/skills/khe-brain-varun

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

README.md

≈1.9k tokens on demand. Your agent reads this file only when SKILL.md points to it.

khe-brain-varun

Answers startup, content, career and AI questions from what Varun Mayya has said in 18 public videos, with the video and the minute named.

npx skills add HKTITAN/skills --skill khe-brain-varun

Credit

This is Harshit Khemani's reading of Varun Mayya's public videos. Varun Mayya did not write it, review it or endorse it. Watch him directly in the Kata playlist on his channel. When this skill and a video disagree, the video is right. Every sentence here is a paraphrase; the few quotes are under 15 words each and come from automatic captions.

What it does

  • Answers a question with the claim, the video it comes from, the time it is said and a link that opens there.
  • Pressure-tests a plan, a pitch or a career decision against his stated positions, one line per position.
  • Says "the videos read do not cover this" when the corpus is silent, and lists what was not read.
  • Reports both sides where two talks disagree or he says he changed his mind, with dates.
  • Keeps each claim in its context: Aeos, his games studio, Indian startups, his own employees, his own career.
  • Never drafts and never decides. It reports his positions and stops.

How it runs

khe-brain-varun's flow: khe-auto sends a question that names Varun here and an unnamed startup question to khe-brain-yc or khe-brain-isb; the question is answered from 12 theme files holding 1,378 claims from 18 videos, checked for silence and disagreement, cited with the video and the minute, closed with what is not in his videos, and gated by brain-check; writing the post goes to khe-content-engine

Used

/khe-brain-varun Pressure-test this against Varun: I am keeping an MBA, a job and a side startup open for a year.

The gold reply for that decision, in full from examples/pressure-test-career.txt:

The decision runs against his advice to people in their twenties: he says keeping every option open gives the least impact, because each extra option is a tax on willpower (Kata 7 at 8:05).
Breaks: three doors held open for a year. He says nobody knows the right answer, so a person just has to decide, and making the call puts them ahead of almost everyone (Kata 7 at 24:02).
Breaks: the MBA as a way to keep choosing. He calls stacking degrees and prestige internships a status game dressed up as choice (Kata 7 at 24:50).
Holds: a second thing after the first works. He separates diversification from optionality: one thing built to scale, then a second, is fine, and five started at once is not (Why Belief Matters at 33:24).
Source: Kata 7, https://www.youtube.com/watch?v=Ia_bqazMeIw
Source: Why Belief Matters, https://www.youtube.com/watch?v=jreQIik5jlE
Not in his videos: which of the three to pick, and anything about MBA programmes. The choice is yours.

The corpus

18 videos, 17 hours 40 minutes, read in full from YouTube's automatic captions on 2026-11-11:

  • The 15 videos of his Kata playlist, from Kata 1 (21 December 2025) to Why Belief Matters More Than Power and Money (3 November 2026).
  • Three podcasts where he is the guest: PGX Ideas (18 March 2026), KK Create with Achina Mayya (18 October 2026) and Masters' Union (29 October 2026).

That is 1,378 cited claims across 12 theme files (2,274 timed citations in all), a glossary of 274 of his terms and frameworks, 21 disagreements, 18 changes of mind he states himself and 27 figures that differ by video.

Not read: his books, his posts, his short videos and every other podcast. His Substack held one placeholder post. varunmayya.org is a profile built by a third party and is cited only for what that page states.

When to use it

Use it when you want an answer from a known source in place of an average of everything: before quoting him, when someone says "Varun says" and you want the video and the minute, or when a plan should be checked against a stated position. Do not use it to make the decision or to write the post.

Invoke with

/khe-brain-varun [question | test <plan or decision> | who said <line> | sources]

Or ask in your own words: "what would Varun say about", "which Kata was that", "pressure-test my plan against Varun".

Before and after

Before: "what would Varun Mayya say about raising money?" returns four confident paragraphs in his voice, a number he never gave and no link.

After: two sentences on why he bootstrapped Aeos and his one condition for raising, each ending in a citation such as (Kata 1 at 12:58); two Changed: lines for the view of investors he reversed; then Source: Kata 1, https://www.youtube.com/watch?v=9NjA41wShTI; then Not in his videos: and the part no video answers.

Example prompts

  • What would Varun say about spending a year on the product before any marketing?
  • Pressure-test this against Varun: I am keeping an MBA, a job and a side startup open for a year.
  • Which Kata has the line about complexity being for idiots?

Verify

node scripts/brain-check.mjs reply.txt --gate   # a reply, saved as text
node scripts/brain-check.mjs examples --gate    # the gold replies
node scripts/brain-check.mjs --self-test        # the gate against its own fixtures, and the corpus against its sources

brain-check.mjs names every fault as a line. --gate ends brain-check passed only when every never-intentional line is at 0, exits 1 with the counts otherwise, and exits 2 with inconclusive when it could not look.

What it proves: the reply opens with the answer, has at least one Source: line, cites only titles that are in references/sources.md with the right URL, gives a time for every video it cites, lists every video it cites, gives no sentence marked as his without a video, keeps quotes under 15 words, uses no hedge word and no "he would", and ends with Not in his videos:. The self-test also proves that every citation in the theme files names a video in the sources table and that its time matches its link.

What it does not prove: that he says what the sentence claims at that minute (times are good to about two minutes; references/sources.md says how the lines were checked), that a quote is word for word (the captions mishear), that the speaker was him and not a host, that a line was kept in its context, or that the corpus is current. It matches titles and times, never meaning. Passing is necessary, not sufficient.

What is inside

  • SKILL.md: the one idea, the workflow, the table from theme to file, the hard rules and the output format.
  • references/: core.md (the thesis, fourteen ideas and his method); the corpus by theme (building-a-company.md, distribution-and-content.md, brand-and-marketing.md, risk-luck-and-bets.md, projects-and-simplicity.md, leading-teams.md, hiring-and-getting-hired.md, careers-belief-and-attempts.md, money-status-and-the-rich.md, ai-and-the-future-of-work.md, india.md, aeos-and-his-story.md), each claim one line with its video, time and link; glossary.md; sources.md (the videos, dates, one-line arguments, what was not read, how to refresh); disagreements.md; silent.md; verify.md, review.md, teaching.md; and gotchas.md and pov.md, which are yours to edit.
  • examples/: six gold replies: a direct question, two pressure-tests, a silent topic, a disagreement and a "who said that".
  • teaching/: twelve bad/good pairs, each named for the gate line its bad half raises. They are the gate's tests.
  • scripts/: brain-check.mjs (the gate). Node 20 or newer, no dependencies.
  • LICENSE: MIT, for this skill's own text and code. His videos stay his.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts4d3 checks · Risk SAFE
  • Gen Agent Trust Hub4d

    This skill acts as a specialized knowledge-retrieval tool for a corpus of video talks. It includes a built-in verification script to ensure the agent follows strict citation and behavior rules. No malicious patterns, sensitive data access, or network exfiltration risks were identified.

  • Socket4d

    No alerts

  • Snyk4d

    Risk: LOW · No issues

Signed by skilld at 945e23c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week
metadata
{
  "author": "Harshit Khemani",
  "version": "1.0.0"
}

README badge

README badge for hktitan/skills/khe-brain-varun