github▌

Turn the current conversation context into a PRD and submit it as a GitHub issue.

YC Office Hours with two modes. Startup mode asks six forcing questions around demand reality, status quo, specificity, wedge, observation, and future-fit. Builder mode is for side projects and open source. It saves a design doc and is intended to run before implementation work.

Launches a visible AI-controlled browser window with the GStack sidebar and anti-bot behavior for live observation and control.

Analyze current repository context and suggest relevant Agent Skills from the GitHub awesome-copilot repository that are not already available in this repository. Agent Skills are self-contained folders located in the skills folder of the awesome-copilot repository, each containing a SKILL.md file with instructions and optional bundled assets.

Break a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices.

Engineering-manager style review that hardens the plan around architecture, boundaries, state transitions, edge cases, tests, and diagrams before coding starts.

Interactive QA session where users report bugs conversationally, and the agent files GitHub issues while exploring the codebase for context.

GitHub repository operations via gh CLI for issues, PRs, CI runs, and API queries. \n \n Covers PR and issue workflows: list, create, view, comment, merge, and close operations \n Includes CI/workflow run inspection with log filtering, status checks, and failed job re-runs \n Supports structured JSON output with --jq filtering for programmatic data extraction and querying \n Requires gh CLI authentication (one-time setup via gh auth login ) and works best within git directories or with explicit

PDF generation skill for turning markdown documents into publication-style PDFs with proper layout, TOC, pagination, and print polish.

Orchestrates CEO, design, eng, and DX reviews from disk and applies internal decision principles to auto-progress the plan, surfacing only taste-sensitive decisions at the end.