dotfiles

Orchestrates the full idea-to-ship workflow. Use when the user has a new idea, feature, or project and wants guided step-by-step progress. Triggers on "I have an idea", "let's build", "new feature", "start a project", or when the user wants to follow the complete workflow from concept to code.

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Self-driving version of grill-with-docs. Runs an auto-grill loop (auto-selects recommended options without asking) while creating ADRs and glossary entries via domain-modeling as decisions resolve. Use when the user says "auto-grill with docs", "grill and decide with docs", or invokes /grill-with-docs-auto.

Long-running iterative development loops with pacing control and verifiable progress. Uses .scratch/<plan>/ structure where each plan has a PRD.md and issues/. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Self-driving version of grill-me. Interrogates a plan or design one question at a time, but for each question offers three answers (A/B/C) with one marked Recommended, then answers it itself by taking the recommended option — looping down the decision tree until the plan is fully resolved. Use when the user wants a plan stress-tested and auto-decided, says "auto-grill", "auto-grill this plan", "grill it and decide", or invokes /auto-grill.

Use the codebase knowledge graph for structural code queries. Triggers on; explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher query examples, edge types, how to use search_graph.

GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.

Review existing requirements or convert raw context into requirements that meet 18 quality characteristics (unambiguous, clear, cohesive, consistent, conformant, current, modifiable, traceable, relevant, unique, categorised, complete, correct, concise, testable, implementation-independent, owned, feasible). Use whenever the user mentions requirements, PRDs, specs, user stories, acceptance criteria, requirements review, requirements audit, BRD, FRD, requirements quality, requirements catalogue, requirements traceability, "are my requirements any good", "turn this into requirements", "make these requirements better", or shares meeting notes, interview transcripts, stakeholder input, or feature ideas that need to be formalised. Trigger even when the user does not use the word "requirement" if the artifact they share is functionally a requirement (e.g., "the system should let users export to PDF", "we need a way for admins to revoke access").

Source-first external repository research using durable, human-findable local clones. Use when the user asks about an open-source repo, GitHub/GitLab URL, library internals, framework behavior, architecture, implementation details, or examples grounded in source code.

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, border radius, optical alignment, font smoothing, tabular numbers, image outlines, box shadows.

Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to nicobailon/visual-explainer.

Converts grill-with-docs output — CONTEXT.md glossaries, ADRs, and approved domain decisions — into typed architecture. Use after grill-with-docs when the user wants domain types, seams, adapters, errors, call stacks, and dependency rules expressed in code before business behavior.

Double check / critique implementation plan with fresh eyes

Double check / review implementation with fresh eyes

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Finalize repository work safely — commit changes and push the current branch. Use when the user says "done", "wrap up", "finalize work", or invokes /done.

Review the current session and code changes for anything worth codifying in AGENTS.md or README.md. Use before committing/opening a PR, or when the user asks "anything learned?", "anything to note?", "should we update AGENTS.md?", "update the docs with what we learned", or similar.

Generate a concise pull request changelog from commits. Use when asked to summarize PR changes, generate a quick PR changelog, list commit summaries grouped by type, or produce a brief PR description without full verification/metrics.

Generate a comprehensive pull request description with verification and impact details. Use when asked to create a detailed PR, write PR descriptions, prepare PRs for review, or generate PR documentation with change categorization, verification results, and impact analysis.

Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal and expects build/tests to verify behavior.

Refactor code safely in small, verifiable steps while preserving external behavior. Use when user says "refactor", "clean up this code", "simplify", "improve readability", "remove dead code", or asks to restructure without changing functionality.