buymeagoat-skills

Multi-agent phased development workflow. Claude Code plans from specs in .planning/phases/ and monitors; Codex implements via Bash heredoc; Gemini reviews every phase exhaustively. Trigger: "read active-context.md", "continue", "pick up", "start next phase", "run the phase loop", "/agent-phase-loop". Related: run agent-review-loop first to find issues, agent-remediate-loop to fix them.

Issue resolution pipeline. Accepts a target backlog file (.planning/open-issues.md, .planning/tech-debt.md, or any .planning/*.md backlog). Routes each item to Codex for a fix, evaluates with Gemini, and archives resolved items. Loops Codex→Gemini until Gemini declares resolved. Updates the source file and active-context.md when done. Can be invoked by agent-review-loop with a fingerprint filter for auto-routing. Trigger: "fix open issues", "resolve tech debt", "remediate", "/agent-remediate-loop", "/agent-remediate-loop open-issues.md", "/agent-remediate-loop tech-debt.md", "work through the issues", "burn down the issues", "burn down tech debt".

Full multi-model codebase review. Dispatches Codex, Gemini, and Copilot in parallel to find bugs, security issues, tech debt, and gaps. Deduplicates findings via Gemini, classifies into structured backlogs under .planning/, and auto-routes findings to agent-remediate-loop by severity tier. Outputs review artifacts to .planning/reviews/YYYYMMDD-<agent>-findings.md. Trigger: "review codebase", "run triage", "full review", "find issues", "/agent-review-loop".

Install a model from a URL into local Ollama with a practical quantization for this host, verify availability for API/OpenWebUI, and sync Continue config to all currently installed models. Trigger with `/llm-install <MODEL_URL>`.