tslateman

Review what agents accomplished, surface loose ends across sessions

Reflect on recent work—capture learnings and surface what to think about next

Post-op check for artifacts, damage, and stale references after agent work

Survey the project and choose what to play next

Create Excalidraw diagrams programmatically. Use when the user wants architecture diagrams, system designs, flowcharts, or any visual diagram with a hand-drawn aesthetic. Outputs editable .excalidraw JSON files. Best for architecture overviews and presentations where the hand-drawn style and drag-and-drop editing add value over Mermaid's text-only approach.

Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, or any of 24+ diagram types. Supports CLI rendering to SVG/PNG/PDF, theming, and configuration. Essential for inline documentation diagrams that render natively on GitHub.

Judgment linter for vibe-coded output — reads the energy of the code, not just correctness. Use when the user says "vibe check", "check this vibe code", "does this hold up", "sanity check this AI code", or after a fast generation session before committing.

Systematic debugging that applies the scientific method to failures. Use when the user says "debug this", "why is this failing", "help me find the bug", "this doesn't work", "track down the issue", or is stuck on a problem and thrashing without progress.

Product interrogation before commitment. Challenges whether you're solving the right problem for the right user at the right time. Use when starting a feature, exploring an idea, or before writing a spec. Triggers: "should I build this", "office hours", "is this worth building", "product check", "challenge this idea".

Find-fix-verify-regress loop for web apps using Chrome MCP. Use when asked to "qa this", "test the app", "find bugs", "does this work in the browser", "check the UI", "smoke test". Navigates the app, finds bugs, fixes code, verifies fixes, writes regression tests.

Trace how a change in one orchestration stack project (Ralph, Flow, Bach) affects the others. Invoke when editing contract-adjacent code — signal handling, state.json writes, task envelopes, worker dispatch, or iteration logic.

Apply Strunk's writing rules to prose—documentation, commits, error messages, UI text. Clearer, stronger, more professional.

This skill should be used when the user asks to "research X", "investigate Y", "look into Z", "find out about", "what are the options for", "compare X vs Y", "how does X work", or requests technical investigation of libraries, APIs, frameworks, or architectural approaches.

Framework for code review that captures context future maintainers need—concerns raised, alternatives rejected, risks accepted. Use for PRs, local changes, or architecture review when the decision matters more than the diff. Produces structured feedback with must-address issues, suggestions, and observations "for the record."

Use when a project spans multiple phases with review gates between them — architecture then implementation then integration, for example

Use when facing complex tasks that benefit from decomposition into focused subtasks delegated to specialist workers

How to create custom specialist workers for the orchestration system

Execute multi-project workflows through agent teams. Reads workflow definitions from workflows/ and project interfaces from registry/, then spawns a team to run the steps. Use when asked to "forge", "run workflow", "dispatch fleet", "orchestrate", or to execute any cross-project chain.

Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.