gabrielmoreira

Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked for review; report-only by default, with explicit local apply available for user-directed fix workflows.

Document a recently solved problem as a durable repo learning, or capture project vocabulary in CONCEPTS.md. Use when capturing a learning after work.

Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged to main, and emit an `lfg`-ready plan. First run sets up sources; supports mode:headless for scheduled runs.

Generate a small set of independent candidate solutions, judge them against one explicit rubric, and return the strongest verified result.

Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy, 審查論文, 論文審查, 模擬審查, 同儕審查, 幫我審這篇, 以審查人角度評估, 審查者校準, 논문 심사, 동료 심사, 모의 심사, 심사자 관점에서 평가, 심사자 보정.

Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.

Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.

Babysits or watches an open GitHub PR until merge-ready, continuously reacting to review comments, CI failures, and routine base movement throughout the PR's life. Use when asked to 'babysit the PR', 'watch the PR', monitor, or keep an eye on a PR over time — not a one-shot request to resolve review comments or debug one CI failure (those are separate skills). GitHub only, including GitHub Enterprise.

Use when designing, reviewing, refactoring, or implementing code that should stay simple, testable, readable, and sustainable. Applies principles for investigating before changes, keeping few layers, making I/O explicit, using dependencies deliberately, organizing by feature, naming consistently, and presenting plans progressively.

Makes answers easier to start reading, scan, resume, and understand without losing important detail. Uses useful-answer-first structure, short paragraphs, clear literal headings, simple language, preserved nuance, natural voice, and small ASCII diagrams when they clarify structure or flow.

Use when working on TypeScript code and needing to choose the smallest focused TypeScript skill for coding standards, boundaries, composition, configs, async control, error handling, observability, security, or testing.

Use when TypeScript code coordinates async work — Promise.all vs sequential, bounded concurrency, AbortSignal cancellation, cleanup/teardown, or process lifecycle (SIGTERM, graceful shutdown).

Use when TypeScript code moves provider, SDK, API, request, response, generated, or raw input shapes across owned application boundaries.

Use when TypeScript work involves naming, abstractions, classes, local reasoning, semantic centers, full cutovers, type assertions, or design cleanup.

Use when TypeScript work involves dependency construction, composition roots, factories, lifecycle, scope, singletons, caching, or runtime provider selection.

Use when TypeScript work involves env values, config parsing, contextual config objects, config defaults, validation boundaries, or migration from legacy config reads.