Skip to content
View zhjai's full-sized avatar
3 followers · 1 following
  • China
  • 03:57 (UTC +08:00)

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Highlights

  • Pro

Block or report zhjai

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
zhjai/README.md

Hi there 👋

Popular repositories Loading

  1. agent-arena agent-arena Public

    Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decis…

    25 5

  2. groundcheck groundcheck Public

    Single-agent, evidence-grounded claim verification to catch LLM hallucinations — a pluggable fact-gate for agent-arena and any multi-agent system (CrewAI, AutoGen, LangGraph).

    2

  3. agent-completion-gate agent-completion-gate Public

    Make AI coding agents prove they're done. A fail-closed completion gate: the agent only proposes done; CI reads the real artifacts and grants 'complete'. For Claude Code, Codex & any agent.

    Python 2

  4. MyAndroidApp MyAndroidApp Public

    Java 1

  5. grill-all grill-all Public

    Source-aware plan-review skill for Claude Code, Codex, and AI coding agents.

    Shell 1

  6. shipping-skills shipping-skills Public

    Meta-skill: the end-to-end pipeline to create AND publish an Agent Skill to GitHub — SKILL.md authoring, trigger-description tuning, naming, cross-file consistency, gh releases, and getting discove…

    1