Skip to content
View glichtenthal's full-sized avatar

Block or report glichtenthal

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
glichtenthal/README.md

Greg Lichtenthal

I build portable AI skills and applied systems that help people think through hard problems while keeping the decision with the person. The four core skills form a judgment loop, and AI Project Steward carries the same principles into AI-assisted implementation.

20+ years driving enterprise revenue and GTM strategy at Google, Meta, and Twitter. Heavy AI user long before it was a job requirement. Now building in the open.

Human-led means AI can organize the context and push back on the reasoning, but the person makes the decision.

Start here

If you have... Use...
Messy notes, transcripts, research, or context The Briefing Room
A claim, plan, draft, or idea that needs honest critique Ground Truth
A consequential decision with real trade-offs The Quorum
An idea, claim, or decision that needs a small test before commitment Test Drive

New to this? Start Here has copy/paste prompts for each skill and shows how they work as a loop. Full docs, demos, and worked examples: Judgment Infrastructure for Human-Led AI.

Install

The four skills follow a loop: brief the context, critique the thinking, weigh the trade-offs, test before trusting. Each works alone, and each repo includes install instructions for Claude and Codex.

Applied Judgment Systems

Applied Judgment Systems carry human-led judgment into a particular domain or stage of work. Some are portable skills, while others are complete applications.

AI Project Steward is a portable operating skill for stronger human–AI collaboration across the whole build. Use it independently whenever AI is helping you build an app, prototype, automation, integration, deployment, or other technical workflow. It can also follow the judgment loop, carrying clarified context, tested assumptions, and accepted decisions into implementation with visible choices, realistic guidance, clear approval boundaries, recorded decisions, and verified results. Review the latest release.

Media, Tech & AI Executive Recruiter GPT is a domain-specific application of the same principles for recruiter-style coaching across media, technology, ad-tech, and AI business-side roles.

Pinned Loading

  1. ground-truth ground-truth Public

    Calibrated honesty and anti-sycophancy for Claude and Codex agent workflows.

    2

  2. the-quorum the-quorum Public

    A five-member expert council that pressure-tests consequential decisions for Claude and Codex.

    HTML 1

  3. briefing-room briefing-room Public

    Turn messy context into a brief you can think with for Claude and Codex.

    1

  4. test-drive test-drive Public

    Test an idea, claim, or decision before trusting it with Claude and Codex.

    1

  5. agent-skills agent-skills Public

    Judgment infrastructure for human-led AI: portable Claude and Codex skills.

    HTML 1

  6. awesome-judgment-infrastructure awesome-judgment-infrastructure Public

    A curated map of judgment infrastructure for human-led AI.

    1