ldangelo

Obsidian Vault Integration — Automatically save session logs to your Obsidian vault. Enables persistent AI agent memory across pi sessions.

Show this user guide for Pi coding agent. Use when: user asks how to use pi, pi configuration, available skills, extensions, commands, or needs help getting started.

orchestrate comprehensive repository assessment using parallel specialist analysis

assess AI tool adoption and usage patterns in the team

analyze code review participation and quality by developer

orchestrate comprehensive team assessment using parallel specialist analysis

analyze documentation contributions and patterns by developer

analyze incident response patterns and production contributions by developer

Use when changing Foreman's Node/Pi worker bridge, detached worker config/env, Pi SDK sessions, custom tools, tool policy, observability, worker terminal events, or sandboxed Pi resource paths.

Use when a Foreman change may affect documentation, commands, workflows, prompts, setup, troubleshooting, operator expectations, or skill inventory/package behavior.

Use when changing Foreman's Elixir/OTP backend under packages/foreman_server: event store, projections, scheduler, run/phase actors, worker protocol, PR/VCS reconciliation, operations, auth, or storage/test isolation.

Use when a Foreman run appears stuck, has missing artifacts, stale projections, failed PR gates, confusing inbox/debug output, or potentially missing phase reports.

Use when deciding between Foreman retry, reset, doctor --fix, worktree clean, abandon, or clean-state for failed/stuck/obsolete runs, branches, worktrees, or PRs.

Use when changing Foreman's Git/Jujutsu support, VcsBackend abstraction, worktree/workspace handling, finalize/rebase/merge/push commands, or workflow/project VCS configuration.

Use when editing or diagnosing Foreman workflow YAML, bundled prompts, pipeline executor behavior, phase artifacts, retries, command/bash/builtin phases, PR gates, or stale runtime prompt/workflow copies.

Use when working in this repo to load and maintain project expertise with the `mulch` CLI: session priming, recording learnings, searching conventions, and validating `.mulch/` records.

Create a new Product Requirements Document from a product description

Refine and improve an existing PRD based on feedback