lossyrob

Transforms evaluation findings into structured review comments with comprehensive rationale. Handles both initial draft generation and critique response iteration.

Posts finalized review comments to GitHub, leaving the review pending by default or submitting it under explicit verified authorization.

Analyzes PR changes to create ReviewContext.md and DerivedSpec.md artifacts. Handles both initial analysis and resumption after baseline research.

Orchestrates the PAW Review workflow, coordinating activity skills to analyze PRs and generate comprehensive review feedback.

Shared git mechanics for PAW activity skills including branch naming conventions, strategy-based branching logic, and selective staging discipline.

Bootstrap skill for PAW workflow initialization. Creates WorkflowContext.md, directory structure, and git branch. Runs before workflow skill is loaded.

Workflow status activity skill for PAW workflow. Diagnoses workflow state, recommends next steps, explains PAW process, and optionally posts updates to Issues/PRs.

Pre-PR review activity skill for PAW workflow. Reviews implementation against spec before Final PR creation with configurable single-model, multi-model, or society-of-thought execution.

Drive a backlog of GitHub issues to PRs autonomously and sequentially. The loaded session becomes an orchestrator that triages issues into S/M/L tiers, spawns PAW implementer (and optional PAW Review) worker terminals that coordinate over telex instead of…

Launch a new terminal running Copilot CLI with a requested title, color label, and working directory. Supports macOS iTerm2/Terminal.app and Windows Terminal, prompt-driven sessions, existing-session resume, explicit terminal selection, and new/current window…

Convene a bounded multi-model, multi-perspective deliberation to produce a recommendation with confidence, preserved dissent, and a transcript. Use on "council", "panel", "deliberate", "multi-agent review", "advisory council", "get diverse perspectives", or…

Operate PAW implementer and reviewer GitHub PR lifecycle loops, including PR discovery, review response, post-approval sentry, re-review requests, and merge-readiness monitoring.

Repeatedly run a check command or script on a configurable interval until a condition is met, a timeout is reached, or an actionable exit code is returned. Use when the user asks to loop, wait, poll, watch, retry, check periodically, wait for CI, wait for…

Open a gated, multi-round critique episode with a different-model subagent that attacks your assumptions before you commit to a consequential, uncertain decision. Use on "pair", "spar", "rubber duck", "get a second opinion", "discuss amongst yourselves", or…

Branch the current session, creating a new session that inherits conversation history up to the current point while preserving the original session intact. This skill should be used when the user wants to create a new session branch for experimentation or…

Convert ODT (OpenDocument Text) files to Markdown, with a separate threaded comments file. Extracts document body via pandoc and comment threads (with anchor text and reply grouping) via Python XML parsing. Also extracts embedded images and Visio diagrams…

Coordinate messages between AI agent sessions with telex.

Coordinate messages between AI agent sessions by attaching a session to a durable address, sending and receiving typed messages (delivered as turns in Copilot CLI), and recording auditable disposition. Use when the operator gives you a telex address or tells…

Draft first-pass chord charts into SessionBook session work documents (`Sessions/*_session_work.md`) using session order plus web research, then regenerate canonical `content/tunes`, `content/sets`, and `content/sessions`. Use when Claude needs to initialize…

Render SessionBook session work documents (`Sessions/*_session_work.md`) to printable PDF using the repo-owned renderer and print model. Use when Claude needs to generate or re-render a rehearsal PDF, include alternate parts with a flag, or troubleshoot PDF…