startup-playbook SKILL.md skillA

startup-playbook from savant0x/savant-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add savant0x/savant-code/startup-playbook@v0.1.0

Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
savant0x/savant-code
Path
.agents/skills/startup-playbook/SKILL.md
Versions recorded
2
Latest version
v0.1.0, committed Oct 12, 2026
First version recorded
Aug 8, 2026
Size
4,059 bytes
Repository stars
12
License
Apache-2.0

Evidence-grounded founder operating system derived from Sam Altman's Startup School 2026 interview: use AI leverage to raise ambition, exploit fast technology shifts without abandoning business fundamentals, build evidence-updated conviction and compounding relationships, and evaluate safety, power, and human agency.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Ambitious AI Startups: Leverage, Conviction, and Distributed Power

<!-- echo-critical -->

> Canonical source: `resources/ambitious-ai-startup-playbook-main/`. This skill
> is a self-contained vendor of that snapshot (FID-2026-0806-007). Re-sync from
> the canonical source, then run `scripts/verify-provenance.ts` to confirm every
> `claim-*` reference still exists in `references/provenance.json`.

## Operating contract

Act as an evidence-grounded teacher and practitioner. Route each request to
Learn, Practice, Apply, or Reference; switch modes when the learner's need
changes. Load only the smallest relevant file; never treat the package as
knowledge beyond its stated scope. When ambiguous, begin in Learn mode with one
short diagnostic question.

## Modes

### Learn

1. Diagnose the learner's goal and prerequisite mastery one question at a time.
2. Choose the next lesson from `chapters/`; skip mastered material.
3. Teach one bounded concept with an explanation, a grounded demonstration, and
   its timestamped evidence (see `references/sources.md`).
4. Ask for retrieval or application before revealing the answer.

### Practice
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add savant0x/savant-code/startup-playbook@sha256:92e4d083ad5e23ad

The line at the top of this page pins the label v0.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_bkhxrsu3ti3e2ggv.svg)](https://markdownregistry.com/a/art_bkhxrsu3ti3e2ggv)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 8, 2026 and Oct 12, 2026, about one every 66 days.

versioncommittedcommitsizeaudit
v0.1.0 latest2026-10-12 ac4bad2 4,059 BA view · diff
git:20260808.56a4f042026-08-08 56a4f04 4,044 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4059 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

savant0x/savant-code · 12 stars · license Apache-2.0 · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_bkhxrsu3ti3e2ggv
GET https://markdownregistry.com/api/v1/resolve?ref=savant0x/savant-code/startup-playbook
GET https://markdownregistry.com/api/v1/blob/92e4d083ad5e23ad4e52d467ba93d00e0f0f4e55fa50a4f7fed1389695cf7a49

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from savant0x/savant-code

coding-csharp SKILL.md skill
savant0x/savant-code · .agents/skills/coding-csharp/SKILL.md · C# naming conventions, async/await patterns, interface conventions, and quality overrides for ECHO Protocol.
v0.1.0 · audit A · 12 stars
coding-go SKILL.md skill
savant0x/savant-code · .agents/skills/coding-go/SKILL.md · Go naming conventions, concurrency patterns, error handling, and quality overrides for ECHO Protocol.
v0.1.0 · audit A · 12 stars
coding-java SKILL.md skill
savant0x/savant-code · .agents/skills/coding-java/SKILL.md · Java naming conventions, exception hierarchy, import patterns, and quality overrides for ECHO Protocol.
v0.1.0 · audit A · 12 stars
coding-python SKILL.md skill
savant0x/savant-code · .agents/skills/coding-python/SKILL.md · Python naming conventions, type hints, import patterns, and quality overrides for ECHO Protocol.
v0.1.0 · audit A · 12 stars
coding-rust SKILL.md skill
savant0x/savant-code · .agents/skills/coding-rust/SKILL.md · Rust naming conventions, ownership patterns, error handling, and quality overrides for ECHO Protocol.
v0.1.0 · audit A · 12 stars
coding-typescript SKILL.md skill
savant0x/savant-code · .agents/skills/coding-typescript/SKILL.md · TypeScript naming conventions, patterns, anti-patterns, and quality overrides for ECHO Protocol.
v0.1.0 · audit A · 12 stars
fid-gates-unfenced-parser-contract SKILL.md skill
savant0x/savant-code · .agents/skills/fid-gates-unfenced-parser-contract/SKILL.md · FID gate parser strips fences; declare bare - gate: lines
v0.1.1 · audit A · 12 stars
fid-gates-unfenced-parser-contract SKILL.md skill
savant0x/savant-code · .agents/skills/fid-gates-unfenced-parser-contract/versions/v1/SKILL.md · FID gate parser strips fences; declare bare - gate: lines
v0.1.0 · audit A · 12 stars
library-complete-needs-a-named-consumer SKILL.md skill
savant0x/savant-code · .agents/skills/library-complete-needs-a-named-consumer/SKILL.md · library complete needs a named consumer
v0.1.0 · audit A · 12 stars
library-complete-needs-a-named-consumer SKILL.md skill
savant0x/savant-code · .agents/skills/library-complete-needs-a-named-consumer/versions/v1/SKILL.md · Incomplete arguments for tool read_files; retry the tool cal
v0.1.0 · audit A · 12 stars
minisign-pubkey-vs-secret-key SKILL.md skill
savant0x/savant-code · .agents/skills/minisign-pubkey-vs-secret-key/SKILL.md · Decode the base64 comment line to pick the shareable key
v0.1.1 · audit A · 12 stars
minisign-pubkey-vs-secret-key SKILL.md skill
savant0x/savant-code · .agents/skills/minisign-pubkey-vs-secret-key/versions/v1/SKILL.md · Decode the base64 comment line to pick the shareable key
v0.1.0 · audit A · 12 stars

Every file in savant0x/savant-code

Browse by kind, by grade A, or by owner.