agent-skills

Agent Skills

Production-grade engineering skills for AI coding agents — plus a thin-context multi-agent harness for pi.

Skills encode the workflows, quality gates, and best practices that senior engineers use when building software, packaged so AI agents follow them consistently across every phase of development. On pi, the agent-hub harness runs those skills and personas as a live team of specialist subagents — while keeping the dispatcher's context thin.

This is a fork of addyosmani/agent-skills, focused on Claude Code, OpenCode, and pi and adding a pi runtime layer plus npm packaging. See FORK.md for what's added, what's dropped, and how it compares.

  DEFINE          PLAN           BUILD          VERIFY         REVIEW          SHIP
 ┌──────┐      ┌──────┐      ┌──────┐      ┌──────┐      ┌──────┐      ┌──────┐
 │ Idea │ ───▶ │ Spec │ ───▶ │ Code │ ───▶ │ Test │ ───▶ │  QA  │ ───▶ │  Go  │
 │Refine│      │  PRD │      │ Impl │      │Debug │      │ Gate │      │ Live │
 └──────┘      └──────┘      └──────┘      └──────┘      └──────┘      └──────┘
  /spec          /plan          /build        /test         /review       /ship

---

Commands

8 slash commands that map to the development lifecycle. Each one activates the right skills automatically.

What you're doing	Command	Key principle
Define what to build	/spec	Spec before code
Plan how to build it	/plan	Small, atomic tasks
Build incrementally	/build	One slice at a time
Prove it works	/test	Tests are proof
Review before merge	/review	Improve code health
Audit web performance	/webperf	Measure before you optimize
Simplify the code	/code-simplify	Clarity over cleverness
Ship to production	/ship	Faster is safer
Orchestrate a team	/orchestrate	Main session drives subagents

/orchestrate turns the main session into an orchestrator that drives a config-defined team of subagents (default planner + builder, no reviewer), routing them as a runtime roster and handling the NEEDS_RESEARCH / PLAN_FILE handoffs. The named teams live in .claude/orchestrate-teams.yaml (mirroring pi's .pi/agents/teams.yaml) and are switchable at runtime: /orchestrate <team> "<task>". It ships for claude-code and opencode (/as-orchestrate); pi orchestrates via the agent-hub harness instead.

Want fewer manual steps once the spec exists? /build auto generates the plan and implements every task in a single approved pass — you approve the plan once, then it runs autonomously. It removes the human stepping between tasks, not the verification: every task is still test-driven and committed individually, and it pauses on failures or risky steps.

Skills also activate automatically based on what you're doing — designing an API triggers api-and-interface-design, building UI triggers frontend-ui-engineering, and so on.

---

agent-hub: a multi-agent harness for pi

agent-hub turns a single pi session into a dispatcher that drives a live team of specialist subagents — planner, builder, reviewer, test-engineer, documenter — with read-only research helpers fanning out beneath them, peer-to-peer coms messaging embedded, and a damage-control guardrail on every tool call.

What makes it different is what it doesn't put in front of the dispatcher LLM.

Thin dispatcher context

Multi-agent setups usually drown the orchestrator: every subagent's output, every research dump, every verification note flows back into one context window until it compacts and forgets. agent-hub is built the other way around: