Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI agents, AGENTS.md or CLAUDE.md creation, harness engineering questions, making agents work better on a codebase. ALSO triggers when users are frustrated or complaining about agent quality — e.g. 'the agent keeps ignoring conventions', 'it never follows instructions', 'why does it keep doing X', 'the agent is broken' — because poor agent output almost always signals harness gaps, not model problems. Covers: context engineering, architectural constraints, multi-agent coordination, evaluation, long-running agent harness, and diagnosis of agent quality issues.
Building LLM agents with mlld — tool agents (MCP tools), event-driven agents (routers and dispatchers), and workflow agents (stateless jobs). Use when creating agents, exposing tools, or building event-driven systems.
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
创建和修改 Agent 的指南。当用户想要创建新的 Agent 或修改现有 Agent 时使用此 Skill。Agent 是定义 AI 角色、行为准则和工作流程的 Markdown 文件，存放在 marketplace 的 atoms/agents 目录下。
- 📄 checklist.md
- 📄 examples.md
- 📄 security-checklist.md
Review standards for code-reviewer agent. Auto-loaded via agent frontmatter when code-reviewer runs (Phase 4). Covers: severity classification (BLOCKER/MAJOR/MINOR/NIT), decision matrix (APPROVED/APPROVED_WITH_COMMENTS/CHANGES_REQUESTED), auto-escalation rules, grep search patterns for automated checks.
Create and configure Neuron AI agents with providers, tools, instructions, and memory. Use this skill whenever the user mentions building agents, creating AI assistants, setting up LLM-powered chat bots, configuring chat agents, or wants to create an agent that can talk, use tools, or handle conversations. Also trigger for any task involving agent configuration, provider setup, tool integration, or chat history management in Neuron AI.
- 📄 LICENSE
- 📄 README.md
- 📄 SKILL.md
Creates and improves Claude Code subagents interactively — scaffolds new agents from descriptions, refines existing agent definitions, tunes frontmatter, tools, model, and prompts. Triggers: create agent, new agent, claude code agent, make a subagent, improve agent, update agent, fix agent description, refactor agent, agent frontmatter, agent prompt, scaffold agent.
- 📁 .codex/
- 📁 docs/
- 📁 providers/
- 📄 SKILL.md
Employee agent lifecycle management system. Use when working with agents/ directory employee agents - starting, stopping, monitoring, or assigning tasks to Dev/QA agents running in tmux sessions. Completely independent of CAO, uses only tmux + Python.
- 📁 assets/
- 📁 evals/
- 📁 references/
- 📄 AGENTS.md
- 📄 checkpoints.yaml
- 📄 CLAUDE.md
Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Installs, configures, audits, and operates Agent Package Manager (APM) in repositories. Use when initializing apm.yml, installing or updating packages, validating manifests, managing lockfiles, compiling agent context, browsing MCP servers, setting up runtimes, or packaging resolved context for CI and team distribution. Don't use for writing a single skill by hand, generic package managers like npm or pip, or non-APM agent configuration systems.
Full agent verification suite. Runs security, patterns, quality, and language-specific checks. Use when asked to "verify agent", "verify my agent", "audit agent", or "full verification".
Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.
- 📁 references/
- 📄 .gitignore
- 📄 README.md
- 📄 README_EN.md
Production-grade Agent development methodology extracted from Claude Code. 7-dimension framework covering tool design, system prompts, permission & safety, multi-agent orchestration, token economy, memory/state, and extensibility. Supports architecture design, implementation guidance, and agent review. Trigger on "Agent design", "build an agent", "AI agent", "tool design", "system prompt architecture", "agent review", "multi-agent", or any agent development concern.
