Skip to content
View zl190's full-sized avatar
8 followers · 14 following

Achievements

Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Achievements

Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Highlights

  • Pro

Block or report zl190

Report abuse

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

Report abuse
zl190/README.md

AI Engineer → Agent Reliability

Building infrastructure that makes AI agents trustworthy — enforcement hooks, quality gates, empirical ablation studies. Tested across 60,000+ agent interactions.

High-stakes ML background (FDA 510(k)).

Contributor to last30days-skill GitHub stars.

Pinned Loading

  1. md-slides md-slides Public

    Claude Code skill for MD → Slides; AI makes Markdown great again!

    7

  2. agent-cockpit agent-cockpit Public

    Terminal dashboard that shows whether your AI agent is behaving, not just spending.

    Python

  3. claude-code-harness claude-code-harness Public

    Hooks that block dangerous operations in Claude Code, with audited evidence

    Shell

  4. nano-agent-anatomy nano-agent-anatomy Public

    Python

  5. noglaze noglaze Public

    🚫🍯 Output quality audit with hook enforcement. Stops your AI from glazing you. Companion to tanweai/pua.

    Shell

  6. pipeline-ops pipeline-ops Public

    Operator pattern for AI pipelines — validated with 24 tests

    Python