prose

Validate all LLM-accelerated GitHub issues through systematic QA testing via Circuit Electron.

Human-in-the-loop QA loop for verifying a large feature or refactor against the locally-running app before merge/release. Use when automated tests (e2e, web-e2e) don't cover the behavioral/UX surface and you need a structured, interactive "you drive / I observe" verification pass with in-session bug fixes. Complements qa-pr (automated, Circuit) and qa-web (Playwright).

Automated QA testing for Prose PRs using Circuit Electron. Use when testing pull requests before merge.

Implement one solo-ist/prose GitHub issue end-to-end and open a PR ready for review. Use when an Oz child agent is assigned exactly one issue to fix or build in this repo.

Reference and checklist for building and maintaining CI/CD workflows, inter-workflow communication, dispatch scripts, and cloud agent infrastructure. Use when modifying any workflow YAML, dispatch script, or sentinel-based communication.

Merge scorer and PE signals to route PRs. Applies routing matrix (hitl-light / hitl-full) based on score thresholds and risk levels.

Principal Engineer architectural risk analysis for PRs. Assesses blast radius, hidden coupling, and privilege boundary concerns. Outputs LOW-CRITICAL risk rating.

Score PR review findings using a quantitative rubric. Outputs a 1-10 composite score across 6 dimensions to inform auto-fix vs human-review routing.

Generate the README hero + Mac App Store marketing screenshots (retina, Prose theme, light/dark) via Playwright.

Analyze the project board and open issues to recommend what to work on next, with rationale.

Audit open issues and project board. Flags done-but-open issues, board drift, and stale items for bulk cleanup.

Reference and checklist for building and maintaining CI/CD workflows, inter-workflow communication, dispatch scripts, and cloud agent infrastructure. Use when modifying any workflow YAML, dispatch script, or sentinel-based communication.

Merge scorer and PE signals to route PRs. Applies routing matrix (auto-fix / auto-fix-verify / hitl-light / hitl-full) based on score thresholds and risk levels.

Principal Engineer architectural risk analysis for PRs. Assesses blast radius, hidden coupling, and privilege boundary concerns. Outputs LOW-CRITICAL risk rating.

Score PR review findings using a quantitative rubric. Outputs a 1-10 composite score across 6 dimensions to inform auto-fix vs human-review routing.

Validate all LLM-accelerated GitHub issues through systematic QA testing via Circuit Electron.

Automated QA testing for Prose PRs using Circuit Electron. Use when testing pull requests before merge.

Validate Prose features against the web mode build using Playwright. Use for CI-compatible QA that doesn't require Electron or a display server.

Create a new Prose release with automated testing, GitHub release, and local verification.

Pragmatic analysis of PR feedback. Validates issues, assesses severity, and recommends actions (fix, defer, or dismiss).

Analyze the project board and open issues to recommend what to work on next, with rationale.

Audit open issues and project board. Flags done-but-open issues, board drift, and stale items for bulk cleanup.

Systematic security audit for Electron apps. Scans attack surfaces, produces severity-tagged findings, generates implementation plan, and guides hardening.

Drives Prose for markdown work. For ANY markdown content the user wants to draft, write, create, or edit in the conversation (a README, draft, essay, blog post, article, note, file, or any longform writing), render the inlined prose-editor widget via visualize:show_widget — NOT as a Document · MD / "Presented file" artifact. The widget replaces the built-in markdown artifact for this skill — Document · MD is read-only, the prose-editor widget is editable AND has an Open-in-Prose button that hands the draft off to the Prose desktop app via sendPrompt → create_and_open_file MCP. For documents the user has open in Prose, use Prose's MCP tools (get_outline, read_document, suggest_edit, open_file, create_and_open_file) instead. Activates whenever the user asks to draft, write, create, edit, restructure, summarize, outline, read, tighten, or polish markdown — or when Prose MCP tools are available in the session.

Create a new Prose release with automated testing, GitHub release, and local verification.

Systematic security audit for Electron apps. Scans attack surfaces, produces severity-tagged findings, generates implementation plan, and guides hardening.