pibo

Use when designing, specifying, implementing, or reviewing a modular system built around Pi Coding Agent / Pi Agent as an embedded agent engine. Trigger for Pi Agent docking, createAgentSession, custom tools, SessionManager, ResourceLoader, ExtensionRunner, Pi events, OpenClaw-style harnesses, plugin ecosystems, web chat channels, MCP/tool adapters, system prompt stewardship, policy layers, or minimal runtimes around packages/coding-agent.

Use this skill when a user asks to graph, map, or visualize a codebase/workspace with Graphify and inspect the generated graphify-out/graph.html, graphify-out/graph.json, or graphify-out/GRAPH_REPORT.md artifacts.

Use the Pibo local auth gateway, both on the host and inside Docker workers. Use this when you need authenticated access to the Chat Web App without configuring Google OAuth, when you want to test against a local gateway on a developer laptop, or when you are working inside a Docker worker and need a fast authenticated session.

Defines how Pibo specs are written, structured, reviewed, and split into proposals, capability specs, phase specs, designs, and tasks. Use this whenever the user asks to create, review, rewrite, compare, or implement a spec; mentions requirements, acceptance criteria, scope, roadmap, proposal, design plan, tasks, OpenSpec, Spec Kit, GSD, or spec-driven development; or asks where project documentation should live.

Plan, create, run, monitor, and review Ralph implementation loops with reusable Docker workers, git worktrees, PRD batches, stop policies, maxIterations, progress files, commits, and safe agent instructions. Use whenever the user wants to start a Ralph job, run an implementation loop, prepare autonomous PRD execution, monitor Ralph, debug Ralph job behavior, or capture the standard Ralph loop workflow.

Use this skill for Pibo Docker Compute System work, isolated implementation, worker worktrees, Chat Web or gateway testing, worker dev auth, browser/CDP validation, resource cleanup, and when coordinating Docker worker use with the github-server-flow strategy.

Convert Markdown PRDs and feature specs into Ralph prd.json story batches. Use whenever the user asks to convert a PRD for Ralph, create Ralph JSON, split a PRD into executable stories, prepare PRD story files, or mentions prd.json for autonomous implementation.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use whenever you need to develop, modify, test, or debug the Pibo codebase. This includes building new features, fixing bugs, refactoring code, running tests, starting the gateway, building web UIs, or using browser automation to verify changes. Always use this skill when the task involves editing Pibo source files or running Pibo processes that could crash the live host gateway. Also trigger when the user asks to work on Pibo, improve Pibo, fix something in Pibo, or test Pibo changes in isolation.

Analyze existing product screens, UI code, design artifacts, and visual references to synthesize a semantic design system into DESIGN.md files.

Create or maintain a shared glossary for a project, feature, plan, document, or discussion so humans and AI agents use consistent wording and avoid misunderstandings. Use when the user wants to define terms, align language, resolve ambiguous wording, or keep terminology consistent.

Improve code quality by finding and implementing architectural refactorings that create clear interfaces and deep modules. Use when the user wants better architecture, cleaner boundaries, simpler call sites, more testable code, or a codebase review focused on module design.