Automação

Performance profiler — analyzes DB queries (any ORM), API call chains, memory usage, bundle sizes, network waterfalls, and frontend rendering. Produces ranked optimization recommendations with estimated impact. Trigger words: performance, slow, optimize, profiling, bottleneck, latency, memory leak, bundle size, network waterfall.

Analyze an insurance claims processing system for lifecycle completeness, straight-through processing automation, fraud detection coverage, reserve estimation methodology, subrogation recovery workflows, and regulatory compliance with state prompt payment laws. Use when building or auditing claims platforms (auto, property, liability, workers comp, health), evaluating FNOL intake, or assessing SIU

Analyze volunteer management platforms for skill-based matching algorithms, shift scheduling optimization, availability tracking, and retention analysis. Evaluates training compliance workflows, background check integration, communication channel efficiency, engagement scoring, churn prediction, impact reporting, and recognition systems for nonprofits, disaster response, healthcare, and community

Evaluate edtech tools for their real impact on teacher time and administrative burden. Analyzes grading automation (auto-scoring, rubric-based feedback, batch workflows), lesson planning efficiency (template reuse, standards auto-tagging, pacing guide integration), parent communication systems (automated notifications, translation, conference scheduling), administrative task reduction (single-entr

Audit patient-facing healthcare software for portal feature completeness, secure messaging, health literacy, telehealth readiness, consent management, and HIPAA compliance. Covers health records access, appointment scheduling, bill pay, patient forms, notification PHI safety, WCAG accessibility, multilingual support, video visit integration, remote patient monitoring, and consent workflows. Use wh

Workflow for authoring or revising any Claude Code configuration — skills (SKILL.md), CLAUDE.md guardrails, settings.json (permissions, hooks, env, model), sub-agents, slash commands, MCP server entries, plugins, and the install or sync scripts around them. Operates from working knowledge of LLMs, agent harnesses, and context engineering so the configuration it produces leverages how Claude Code a

Use when first setting up lark-cli, running auth login, switching user/bot identity (--as), handling permission denied or scope errors, needing to update lark-cli, or seeing _notice in JSON output.

Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.

Analyze medication adherence and management platforms including dose tracking accuracy (MPR, PDC metrics), drug-drug and drug-food interaction checking completeness, refill prediction algorithms, dosage schedule optimization with conflict detection, caregiver notification escalation workflows, pharmacy system integration (NCPDP, HL7 FHIR), adverse event signal detection, smart dispenser integratio

Orquestrador para o desenvolvimento de scripts DayZ Enforce. Ele busca dinamicamente APIs de classes, referências de scripts e documentação de mods, suportando o desenvolvimento vanilla, Community Framework e Expansion para DayZ 1.28+.

Audit emergency and crisis triage systems for call prioritization accuracy, resource dispatching algorithm quality, severity classification model evaluation, response time optimization, geographic coverage analysis, mutual aid protocol readiness, and post-incident review workflows. Covers CAD integration, GIS spatial indexing, queue management under resource constraints, demand forecasting, NFIRS/

飞书 / Lark 通讯录,用于按姓名 / 邮箱把员工解析成 open_id,以及按 open_id 反查员工的姓名 / 部门 / 邮箱 / 联系方式。当用户说出某人姓名而下一步需要发消息 / 加群 / 排日程时,先用本 skill 把姓名换成 ID;当输出里出现 open_id 需要展示成姓名给用户看,或用户直接询问某人的部门 / 邮箱 / 联系方式时,用本 skill 查。不负责部门树遍历、按部门列员工、组织架构图,这类需求走原生 OpenAPI。