Desenvolvimento

Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.

Maintain short, focused Markdown files per subsystem to provide agents with isolated context.

Automated app improvement cycles. Assesses each app's health, prioritizes by staleness and debt, consumes recall/metrics/evolve findings from cron, then runs targeted fix pipelines per app. Fully autonomous — runs unattended via cron or manually. Triggers: tend my apps, improve my apps, app maintenance, run improvement cycle, garden, maintain apps.

Strategic architecture review from the perspective of a Senior Architecture Review Board. Manual invocation only via /architect — do not invoke this skill automatically. Use when the user explicitly asks for an architecture review, design assessment, technology selection review, or strategic technical direction evaluation. Supports focused deep-dives: /architect deps, /architect ops, /architect <t

Profile and audit mobile app performance -- cold/warm/hot startup time, memory leaks, battery drain, network efficiency, frame rate jank, and binary size. Covers Flutter, React Native, Swift, and Kotlin apps. Detects image memory issues, undisposed controllers, polling without backoff, missing virtualized lists, and unused asset bloat. Use when diagnosing slow launches, investigating ANRs, reducin

Analyze manufacturing defect detection and quality control systems — computer vision inspection pipelines, SPC control charts, Six Sigma process capability (Cp/Cpk), defect classification taxonomies, root cause analysis tooling, and measurement system analysis. Audit QC codebases for detection accuracy, false reject rates, statistical rigor, and traceability compliance.

Audit adaptive learning and student personalization systems for pedagogical quality. Use when you need to evaluate learning path algorithms (branching, remediation, acceleration), mastery detection models (Bayesian, IRT, threshold-based), knowledge graph prerequisite accuracy, recommendation engine fairness and bias, spaced repetition and interleaving, WCAG 2.1 AA and Section 508 accessibility com

Full autonomous execution from idea to working code

当需要用 lark-cli 操作飞书多维表格（Base）时调用：搜索 Base、建表、字段管理、记录读写、记录分享链接、视图配置、历史查询，以及角色/表单/仪表盘管理/工作流；也适用于把旧的 +table / +field / +record 写法改成当前命令写法。涉及字段设计、公式字段、查找引用、跨表计算、行级派生指标、数据分析需求时也必须使用本 skill。

Audits and implements mandatory image resizing and compression for all uploaded user images to reduce storage costs while preserving visual quality.

Use when the user provides a URL to a standard web page and clean Markdown extraction with Defuddle would reduce clutter and token cost.

Analyze behavioral segmentation systems for RFM scoring, cohort tracking, churn propensity, engagement scoring, persona clustering, and journey mapping using behavioral economics frameworks. USE THIS SKILL WHEN: user mentions customer segmentation, RFM analysis, cohort analysis, churn prediction, engagement scoring, customer personas, journey mapping, retention analysis, customer lifetime value, o