Jonmagic Skills

Complete operating system for jonmagic's second brain — search, create, capture, commit, and maintain Brain content. Use for any Brain operation: search, daily projects, bookmarks, weekly notes, meetings, sessions, catch-ups, commits, frontmatter, and context loading.

Prepare GitHub pull requests for review and follow up on PR review comments. Use before any PR creation or update, including "open a PR", "create a PR", "make a pull request", `gh pr create`, writing/updating a PR body, requesting review, handling Copilot or human review feedback, resolving comments, or asking whether a branch is ready to review. Includes rubber ducking, semantic commits, PR body/review guidance, 5-minute Copilot feedback follow-up scheduling, and work-repo vs personal-project boundaries.

Run an explicitly requested multi-model review or adjudicate a consequential disagreement between a driver and reviewer. Uses one different-provider reviewer by default and a third provider only when direct verification cannot resolve the dispute. Not for routine ambiguity or fleet mode.

Create, modify, and render D2 diagrams using the d2 CLI. Use when the user asks for diagrams, architecture visuals, ERDs, sequence diagrams, flowcharts, grid layouts, or any declarative diagramming task. Trigger phrases include "d2 diagram", "create a diagram", "architecture diagram", "sequence diagram", "ERD", "flowchart", "draw", "visualize".

Generate images locally using Ollama's x/z-image-turbo model. Use when the user asks to generate an image, create art, make a picture, or produce a visual. Trigger phrases include "generate an image", "create a picture", "make art", "image of", "draw me", "visualize", "photo of", "illustration of".

Generate semantic commit messages from staged changes. Use when committing code to produce consistent, well-structured commit messages following conventional commit format.

Stress-test plans, designs, proposals, and implementation strategies by interviewing the user one decision at a time. Use when the user says "stress test this", "interview me", "improve this plan", "challenge this plan", "poke holes in this", or wants plan refinement.

Prevents unnecessary dependency installation and audits unavoidable packages. Use before adding, installing, upgrading, or recommending dependencies, packages, libraries, gems, npm modules, pip packages, crates, GitHub Actions, CLIs, or package-manager commands.

Create formal executive summaries from GitHub conversations or meeting transcripts. Use when generating leadership-ready summaries that distill key decisions, alternatives, outcomes, and next steps from complex conversations or meetings. Supports GitHub issues/PRs and transcript URIs (Zoom, Teams, etc.). Outputs are saved to Executive Summaries/ with date-organized structure, and source inputs are archived to Transcripts/ with matching naming.

Runs bounded, evidence-first reviews of old or confusing GitHub issues with complete primary-artifact research, current-state corroboration, conversational approval, exact writes, and verification. Use when deciding whether to keep, update, connect, consolidate, deprecate, close, or escalate lingering issues. Do not use for ordinary sprint triage, creating issues, or bulk stale automation.

Generate an AI art prompt for a blog post or GitHub discussion header image. Interactive skill that reads the content, interviews the user about their vision, and produces a ready-to-use prompt for any AI image generation tool. Use when the user says "header image", "create a header", "generate art for my post", or similar.

Use this skill when the user asks to evaluate a software design, architecture, API, service boundary, platform abstraction, planning tradeoff, or code-quality question against named software engineering laws or explicit design principles such as Conway's Law, Hyrum's Law, Brooks's Law, YAGNI, Gall's Law, Postel's Law, CAP, or leaky abstractions. Do not use for ordinary PR review or generic critique unless named laws/principles are requested or principal-engineer-review explicitly composes it as a design lens.

Use this skill when auditing, validating, evaluating, or maintaining a fleet of agent skills. Covers structural validation, trigger tests, with-skill versus without-skill output comparisons, upstream freshness snapshots, and evidence reports. Do not use for ordinary single-skill tasks unless fleet health or eval quality is in scope.

Reviews and explains PRs, local diffs, implementation plans, and code-adjacent designs through a principal engineer lens. Use when the user asks to review or understand a change, build enough context to review it, assess readiness, check MVP scope or maintainability, receive high-signal critique, or invoke `/principal-engineer-review next`. Requires an explicit request to review work that already exists. Do not use for implementation work.