kevmoo

Autonomous pull request review loop that pushes code, polls for AI/bot review comments (e.g., Gemini Code Assist), surgically remediates feedback, commits, pushes, comments `/gemini review`, and loops until zero feedback remains. Requires the `github-pr-triage` skill.

Triage open PR comments/reviews and associated CI/CD workflow failures using the `triage.dart` helper script and formulate an actionable plan.

Intake multi-step tasks by clarifying ambiguities, summarizing understanding, and confirming readiness via ask_question before executing code changes.

Analyzes unstructured artifacts (proposals, design docs, issues, notes) to identify gaps, contradictions, and implicit assumptions, and interviews the user via a structured quiz to distill a definitive strategy and trade-off matrix. Use when resolving competing architectural proposals, clarifying ambiguous project goals, identifying blind spots in early design documents, or synthesizing consensus from fragmented team notes. Don't use for simple text summarization without strategic synthesis, writing code solutions directly, or managing task lists without strategic decision-making.

Apply the "Encapsulated Method Object" refactoring pattern to simplify functions with deeply nested scopes, bloated closures, and heavy shared local state.

Best practices for managing stacked changelists (CLs) in Gerrit using depot_tools, avoiding common pitfalls with Change-Ids.

Use gob-curl and Buildbucket tools to inspect the status, tryjobs, and CI results of a Gerrit CL.

Brainstorm architectural designs, explore potential solutions, and weigh implementation tradeoffs collaboratively without making code changes.

Profile Dart command-line applications using the VM Service protocol to capture CPU samples and identify performance bottlenecks. Helps agents automate CPU profiling, generate function call breakdown summaries, and export JSON profiles without a browser or DevTools.

General best practices for Dart development. Covers code style, effective Dart, and language features.

Best practices for validating Dart documentation comments. Covers using `dart doc` to catch unresolved references and macros.

Guidelines for handling long lines in Dart code to adhere to the 80-column rule. The `lines_longer_than_80_chars` lint.

Best practices for using `expect` and `package:matcher`. Focuses on readable assertions, proper matcher selection, and avoiding common pitfalls.

Guidelines for using modern Dart features (v3.0 - v3.10) such as Records, Pattern Matching, Switch Expressions, Extension Types, Class Modifiers, Wildcards, Null-Aware Elements, and Dot Shorthands.

Guidelines and best practices for refactoring consecutive prints, single-line string concatenations, and complex output blocks into triple-quoted multi-line string literals (''' or """) in Dart.

Guidelines for maintaining external Dart packages, covering versioning, publishing workflows, and pull request management. Use when updating Dart packages, preparing for a release, or managing collaborative changes in a repository.

Ponder architectural designs, explore potential solutions, weigh tradeoffs, or analyze the impact of proposed codebase changes without making code changes. Always outputs the analysis to a Markdown artifact.

Autonomous pull request review loop that pushes code, polls for AI/bot review comments (e.g., Gemini Code Assist), surgically remediates feedback, commits, pushes, comments `/gemini review`, and loops until zero feedback remains. Requires the `github-pr-triage` skill.

Introspects conversation history to suggest new tools, skills, MCP servers, or identify context window hogs and optimization opportunities.

Analyze the current agent conversation transcript to estimate the number of input, output, and cumulative tokens consumed, including caching estimates.

Synthesizes conversation history and active tasks into a visual hierarchy map (`sidequest.md`) to prevent context drift and cognitive overload across long sessions. Supports multiple sequential and concurrent main quests, sub-quests, and side-quests. Use when the user invokes `/sidequest`, asks where we are, what we were doing, or what's on our stack, or when the conversation branches across multiple topics, blockers, or digressions. Don't use for simple one-off questions that don't involve multi-step work or task hierarchy management.

Intake multi-step tasks by clarifying ambiguities, summarizing understanding, and confirming readiness via ask_question before executing code changes.

Use gob-curl and Buildbucket tools to inspect the status, tryjobs, and CI results of a Gerrit CL.

Use the `sem` CLI to view semantic codebase diffs, evaluate dependency graphs, perform impact analysis, and investigate code history without formatting noise. Use instead of standard git diff/log when analyzing structural code changes.

Runs pre-flight checks and deep code reviews on local commits of a feature branch before push or PR creation.

Post-merge cleanup protocol for Dart SDK Bazel thread task worktrees, beads issue closing, and remote sync.

MANDATORY skill when working on Bazel thread tasks (sdk-5m4.*, etc.), updating task status in beads, managing PR alignment lifecycle, or syncing the Dolt task DB.

Orchestrates long-running or recurring patrols of the Dart SDK Bazel test completion matrix. Discovers test targets, runs automated watchdog timers (default 5m/300s), bypasses blocking test suites or configs, regenerates canonical completion reports (TEST_COMPLETION_MATRIX.md), and synchronizes findings with the Beads issue backlog. Use when the user asks to run all Bazel tests, check test completion matrix health, audit migration test gaps, or leave overnight test patrols running.

Import, test, and export upstream Gerrit CLs or GitHub PRs in the Bazel workspace.

Inspect new activity, commits, and pub releases across Kevin's personal projects since the last review session using tool/triage_projects.dart.