Agent Skills › katanemo/plano › plano-agent-skills

plano-agent-skills

GitHub

提供Plano智能体应用的综合最佳实践，涵盖配置、路由、编排、过滤链及部署。用于处理跨领域任务，指导代码生成、调试与生产就绪检查。

skills/plano-agent-skills/SKILL.md katanemo/plano

Trigger Scenarios

验证或修复Plano配置文件设计智能体监听架构优化模型路由与降级策略加固过滤器链与安全护栏基于追踪数据调试路由问题准备部署和生产环境就绪性检查

Install

npx skills add katanemo/plano --skill plano-agent-skills -g -y

More Options

Use without installing

npx skills use katanemo/plano@plano-agent-skills

指定 Agent (Claude Code)

npx skills add katanemo/plano --skill plano-agent-skills -a claude-code -g -y

安装 repo 全部 skill

npx skills add katanemo/plano --all -g -y

预览 repo 内 skill

npx skills add katanemo/plano --list

SKILL.md

Frontmatter

{
    "name": "plano-agent-skills",
    "license": "Apache-2.0",
    "metadata": {
        "author": "katanemo",
        "version": "1.0.0"
    },
    "description": "Best practices for building agents and agentic applications with Plano, including configuration, routing, orchestration, guardrails, observability, and deployment."
}

Plano Agent Skills

Comprehensive Plano guidance for coding agents. Use this umbrella skill when a task spans multiple areas (config, routing, orchestration, filters, observability, CLI, deployment).

When To Use

Validating or fixing Plano config.yaml
Designing listener architecture (model, prompt, agent)
Improving model/provider routing quality and fallback behavior
Hardening filter chains and prompt guardrails
Debugging routing with traces and CLI workflows
Preparing deployment and production readiness checks

How To Use

Classify the request by scope (single section vs. cross-cutting).
For focused work, prefer a section-specific skill (for example plano-routing-model-selection).
For broad work, apply this umbrella skill and reference section rules from skills/AGENTS.md.
Produce concrete edits first, then concise reasoning and validation steps.

Operating Workflow

Identify the task area first: config, routing, orchestration, filters, observability, CLI, or deployment.
Apply the smallest correct change that satisfies the requested behavior.
Preserve security and reliability defaults:
- version: v0.3.0
- exactly one default: true model provider
- secrets via $ENV_VAR substitution only
- host.docker.internal for host services from inside Docker
- guardrails before enrichment in filter chains
For debugging, prioritize traces over guesswork (planoai up --with-tracing, planoai trace).
Return concrete diffs and a short validation checklist.

Response Style

Prefer actionable edits over generic advice.
Be explicit about why a config choice is correct.
Call out risky patterns (hardcoded secrets, missing default provider, bad filter ordering).
Keep examples minimal and production-viable.