Development

Enforces safe Go concurrency — every goroutine has a known stop condition, context propagates cancellation, channel ownership and direction are explicit, and shared state is protected or not shared. Use when writing or reviewing Go that starts goroutines, uses channels, sync primitives, or context, and when the user mentions goroutine leaks, deadlock, data race, WaitGroup, errgroup, select, mutex, worker pool, "-race", or asks "is this concurrent code safe", "why does this hang".

Enforces Go package and API design — small exported surfaces, packages named for what they provide, functional options instead of growing constructors, context first, no init side effects, and changes that stay backward compatible. Use when creating or restructuring Go packages, designing an exported API or library, or reviewing a public interface, and when the user mentions package layout, internal/, functional options, breaking changes, semantic import versioning, or asks "how should I stru...

Selects, applies, and pushes back on the 23 Gang of Four design patterns. Covers intent, fit, trade-offs, and the cheaper alternative that usually wins. Use when choosing between patterns, naming an existing structure, or refactoring toward one — and when the user says "which pattern", "what pattern should I use", "design pattern", "GoF", "factory", "strategy", "observer", "decorator", "adapter", "singleton", "visitor", or describes a shape a pattern solves: swappable algorithms, notifying su...

Plans and implements comprehensive unit tests for the PABX monorepo — Angular frontend (Jest + jest-preset-angular, .spec.ts) and Node.js backend (Jest, apps/backend/__tests__/unit/). Runs interactively (3 phases with an approval checkpoint) when called by a user, or autonomously (no pause) when dispatched by implement-feature/evaluator. Also runs in correction mode to fix a specific failing test flagged by the evaluator. Enforces PABX rules (real component imports, manual service instantiati...

Audits unit tests in the PABX monorepo (Angular frontend .spec.ts + Node.js backend __tests__/unit/) against the unit-test-writer rules, producing a compliance report with a PASS/FAIL/PASS WITH WARNINGS verdict, per-violation severity, and fix suggestions. Read-only — never writes or fixes tests. Dispatched by the evaluator to confirm a corrected test conforms before resuming evaluation, or run directly by a user.

Generates technical implementation spec, plan, AND an operational contract for one or more features based on PRD, codebase analysis, and iterative clarification. Produces contract.md (environment contract, quality gates, coverage manifest, observable criteria) consumed by implement-feature and evaluator. Supports batch mode for generating multiple features from the same wave in parallel.

Generate complete PRDs (Product Requirements Documents) through iterative clarification. Use when: (1) Starting a new project and need structured requirements, (2) Creating product specifications with 9-section PRD format, (3) Defining product scope from a description or context files. Keywords: "prd", "product requirements", "create PRD", "generate PRD", "new product", "requirements document".

Fonte-da-verdade do design system do DRCALL PABX (Angular Material M3, aesthetic compacto/profissional). Use ao criar ou revisar qualquer UI do frontend — páginas, tabelas, dashboards, formulários, diálogos — para seguir tipografia, espaçamento, tokens de cor, padrões de página/tabela/dashboard e os anti-padrões proibidos. É também a base do gate styles-frontend e da verificação visual.

Audits PABX monorepo unit tests (node-express, node-worker, python-fastapi apps outside apps/backend and apps/frontend) against the monorepo-unit-test-writer rules, auto-detecting the stack and producing a compliance report with a PASS/FAIL/PASS WITH WARNINGS verdict, per-violation severity, and fix suggestions. Read-only — never writes or fixes tests. Dispatched by the evaluator to confirm a corrected test conforms before resuming evaluation, or run directly by a user.

Implements a feature autonomously based on its spec, plan, AND contract.md, committing one commit per phase, satisfying the contract's quality gates and observable criteria, writing progress.json, and reporting results against the feature's acceptance criteria. Delegates test writing to the matching test-writer skill (unit/integration/monorepo/e2e) by path/stack when the project fits, and falls back to writing tests itself otherwise.

Builds the deterministic quality-gate infrastructure for a project (typecheck, lint with zero-warnings, dependency/architecture checks, tests, dead-code, and a single runGate entry point) from the Deep Analysis Report (+ Architecture Analysis Report). Auto-detects greenfield vs. brownfield, proposes a gate plan for confirmation, then writes the configs/scripts and verifies each gate runs. The gates it builds are later declared in each feature's contract.md by spec-writer.

Performs an exhaustive, item-by-item deep analysis of every module, service, component, or endpoint listed in the Architecture Analysis Report (REQUIRED as input). Maps every implementation detail, data flow, contract, and failure mode, and produces a structured Deep Analysis Report. Analysis/reporting only — never modifies the codebase. In the SDD flow it runs after architecture-analyzer and feeds gate-builder.

Answers which files to refactor first to reduce systemic risk, by crossing blast radius (how many modules stop working if this one breaks) against size. On first use it asks permission, installs its own tooling and writes a config by reading the project; on every run after that it executes a versioned script and reads only that script's JSON output, never the source tree again. Produces a standalone HTML report with a scatter chart, a ranked queue and structural detectors. Unlike architecture...

Performs a comprehensive surface-area analysis of any codebase scope (a component, module, service, layer, or the full project). Inventories every entry point, dependency, pattern, and integration, scores complexity, and produces a structured Architecture Analysis Report consumed by the deep-analyzer skill. Analysis/reporting only — never modifies the codebase. In the SDD flow this is the first setup step for an existing (brownfield) project; it feeds deep-analyzer and then gate-builder.

Show what a 100% human-driven engineering team would have cost for this session — the full receipt with line items, coordination tax, grand total and per-role breakdown, or an export to pdf/png/html/md.

Show what a 100% human-driven engineering team would have cost for this session. Use /realistic-cost for the full receipt (line items, coordination tax, grand total, per-role breakdown), or /realistic-cost export pdf|png|html|md to export it.

Inspect and address Codex CLI sessions from inside Claude Code. Use when the user asks what Codex is doing, whether it is stuck or idle, how far along it is, what its rate limits are, which Codex sessions exist or are running, what a session was asked to do, what model or reasoning effort it is using, or asks to tell/instruct/message a Codex session. Sessions can be found by uuid, by working directory, or by words in their opening prompt. Also use for 'check on codex', 'is codex still running...

投稿定位与期刊/会议匹配。当用户问投哪个期刊/会议、要评估录用可能性/录用概率、做投稿规划时使用。根据论文质量、方向、创新程度、实验完整性、语言水平、作者背景和预算，推荐中文/英文期刊、SCI/SSCI/EI/CCF/核心、国际/国内会议。分析投稿难度、方向匹配度、审稿周期、版面费、以可核查信号做录用可能性定性分级(高/中/低,不编百分比)、是否适合本科生/弱导师资源、预警风险，给出冲刺/稳妥/保底分层选择。

工具选择与多工具协同。根据任务自动判断适合用什么工具——搜索、Python、R、MATLAB、LaTeX、Word、Excel、PowerPoint、Visio、Origin、数据库、Git、前端/后端框架、绘图工具、文献管理工具等（常驻，所有任务后台生效）。不盲目用工具，而是按实际任务选最高效、最稳定、最专业的实现方式。

后端系统设计与数据库能力。当任务涉及系统架构、数据库设计、接口设计、权限/日志/异常/性能/部署时使用。设计 ER 图、数据表结构、接口文档、用户权限、数据流转、模块划分、API 规范、数据库索引、安全策略、部署方案，尤其适合科研系统、管理系统、数据分析平台、可视化平台、竞赛作品与软著项目。

规范整洁的项目文件夹整理。当任务涉及新建项目、整理已有项目结构、规整文件命名与版本时使用。规划 data、src、models、results、figures、docs、paper、ppt、patent、software-copyright、experiments、logs、configs、references、assets、notebooks 等目录，保证结构清晰、命名规范、版本可追踪，便于写论文、答辩、申请软著专利与复现实验。

独特吸睛、审美好、有特色、美观全面的前端设计。当任务涉及前端界面、项目展示页、系统演示、大屏可视化、可视化平台、微信小程序 UI、移动端界面、设计系统、Tailwind v4、shadcn/ui、Next.js、React、Vite、可访问性、动效、重设计审计时使用。不只是能用，而是好看、统一、清晰、有亮点、有视觉记忆点，适合展示/答辩/演示/落地。按主题选风格：科技感、学术感、农业智慧化、数据可视化、极简、玻璃拟态、卡片式、大屏、管理系统、移动端、小程序等。

后端代码编写、逻辑强、安全性高、可读性好、版本控制、代码审查。当任务需要写实验代码、模型代码、数据处理代码、可视化代码、后端接口或系统逻辑时使用。要求逻辑清晰、安全、可读、可维护、便于复现/扩展/部署。支持 Git 版本管理、代码审查、注释规范、README、依赖管理、环境配置、运行说明与项目结构整理。

Reclaim disk space and RAM on Apple Silicon macOS, safely — for developers AND creative pros. Use when the user is low on disk, asks what is eating space or memory, wants to clear caches for developer tools (gradle, npm, pnpm, yarn, brew, uv, pip, cargo, go, CocoaPods, Xcode, Android NDK/emulators, Docker/colima) OR creative apps (Final Cut, Premiere, After Effects, DaVinci Resolve, Lightroom, Photoshop, Capture One, Logic, Ableton, Pro Tools, Blender, Houdini, Cinema 4D, Unreal, browsers), o...