
from AgentOps311
Orchestrates a three-phase RPI lifecycle (discovery → implementation → validation) for autonomous agent workflows, including complexity classification, routing,
RPI is a meta-orchestrator that runs a complete three-phase lifecycle: discovery, implementation (crank), and validation. It delegates work to dedicated phase skills and enforces strict delegation, complexity classification, execution gates, and automated retry loops so agents run full end-to-end tasks autonomously. Concrete use: run /rpi "<goal>" to convert a high-level objective into a research plan, implement waves of changes, and validate results with post-mortem and retro.
Use RPI when you need a hands-off, full-stack execution of a development or research objective that requires planning, iterative implementation, and validation. Ideal for feature builds, migrations, or cross-cutting refactors where you want repeatable phase gates, automated retries, and reportable artifacts.
Designed for general coding-agent runners (Claude Code, Codex runners, Cursor integrations) and executor environments that support skill delegation and filesystem artifacts.
RPI (Research-Plan-Implement lifecycle orchestrator) is a meta-skill that delegates to discovery, crank, and validation phases. SKILL.md is thorough with clear phase contracts, complexity scaling, and retry logic. The bundled validate.sh script runs but fails all checks because it expects the full skill directory structure (references/, SKILL.md) that isn't available in the isolated temp execution environment. No security concerns found — no network calls, no credentials, no destructive commands.
Well-structured meta-orchestration skill. The validate.sh is a structural linter for the skill's own directory — clever self-check pattern but fails in isolation. No security issues whatsoever.