Loading...
Loading...
Found 1,429 Skills
Modo de explicação em camadas. Aplica SOMENTE na resposta imediatamente após a invocação — depois volta ao normal automaticamente. A resposta deve ser em manchete (1 frase, no máximo 2), no nível exato da granularidade da pergunta. Não listar itens individuais quando a pergunta foi sobre o conjunto. Não oferecer drill-down nem perguntar se quer detalhar — esperar o usuário pedir. Use SOMENTE quando o usuário invocar explicitamente com "/peel-talk", "peel-talk", "explica no peel-talk", "peel talk", "modo peel", ou variações. NÃO invocar automaticamente em outras tarefas.
One-time setup skill that builds a personalized inbox triage knowledge base via interactive interview. Interviews the user about their email patterns, business context, reply style, and priorities using grill-me discipline (one question at a time, forcing format where possible, dependency-ordered, each question explains why I'm asking), then generates the knowledge base files that power the companion 'inbox-triage' skill. Run this once before using inbox-triage for the first time. Re-run when business, pricing, or priorities change significantly. Triggers: 'set up my inbox', 'configure inbox triage', 'set up my email system', 'configure email triage', 'build my email knowledge base', 'initialize email management', 'set up inbox triage', 'onboard email triage', or any variation where someone wants to get the email triage system running for the first time.
Decompile and analyze IDA functions. Use when asked for pseudocode, ctree AST analysis, local variables, labels, or decompiler-driven cleanup.
Guides pension and retirement fund work—DB vs DC structures, funding policy, liability measurement (PV of benefits, discount rates, mortality), ALM overview, plan design, public and multi-employer pensions, risk transfer (buyouts, annuities, de-risking), US regulatory overview (ERISA, PBGC, DOL, IRS qualified plans), institutional investor role, and fiduciary governance—not legal or tax advice. Use when the user mentions pension fund, retirement plan, defined benefit, defined contribution, 401(k), pension funding, PBGC, ERISA, pension liability, discount rate pension, pension buyout, de-risking pension, or ALM pension—not P&C insurance (property-casualty-insurance), actuarial modeling only (actuary), actuarial engagements (actuarial-consulting), personal IRA advice (financial-analyst), or legal interpretation (commercial-counsel).
Guides property and casualty (P&C) insurance—commercial and personal lines, major LOBs (property, GL, workers comp, commercial auto, umbrella, specialty), underwriting and risk selection, policy triggers (occurrence vs claims-made), limits and exclusions, claims (FNOL, reserving, litigation), reinsurance and catastrophe, distribution (agents, brokers, MGAs), metrics (loss ratio, combined ratio, cat load), and state DOI/rate filing overview—not legal advice. Use for P&C insurance, property and casualty, commercial lines, workers comp, general liability, combined ratio, loss ratio, underwriting, claims-made, occurrence policy, reinsurance, catastrophe, MGA, rate filing, or FNOL—not actuarial modeling (actuary), life/health depth, legal interpretation (commercial-counsel), or GRC controls without insurance context (compliance-engineer).
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
Attach judges to AI Config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.
Use when writing Python that processes biological sequences (DNA/RNA/protein) with the seqpro package — encoding, one-hot, k-mer shuffling, reverse complement, GC content, variable-length sequence batches, or anything involving seqpro's `Ragged` array. Covers the seqpro API surface and the conventions you need to use it correctly.
Use this skill when the user requests to "generate cover", "cover copy", "XHS title", "optimize title", says "help me write a cover", or needs Xiaohongshu cover text and title variants. Based on cognitive psychology and behavioral economics, it identifies content types and authoritative elements, automatically selects driving strategies, and outputs three versions of solutions: aggressive, balanced, and conservative. Each version includes cover copy plus 3 titles, accompanied by four-dimensional ratings and A/B testing suggestions. Do NOT trigger this skill for scenarios like writing video scripts (use li-writer) or optimizing openings (use li-opening).
Use when user explicitly asks Flink/Ververica/Realtime Compute Console workspace operations: 草稿(draft), SQL校验/执行, 部署(deployment), 作业(job), Session Cluster, namespace, 表(table), 成员(member), 变量(variable), 或 checkpoint timeout 诊断, especially with workspace/deployment/job IDs (w-*, d-*, j-*, sc-*, draft-*). Also use when prompt asks to test/verify Flink Console lifecycle flow, safety guardrails, or parameter validation for these operations. This includes prompts such as create draft, deploy draft, list deployments, start/stop job, create/list session cluster, get tables, list variables. Also use when prompt explicitly asks to run `python scripts/flink_ververica_ops.py` for Flink Console workspace operations. Do not trigger for unrelated "workspace" contexts or generic cloud/platform tasks (ECS, OSS, RDS, Kafka, Spark, Kubernetes, billing, weather). Do not trigger for Flink instance lifecycle operations (create/scale/delete/renew); those belong to alibabacloud-flink-instance-manage.
Você é uma Arquiteta de Software Sênior especialista em Clean Code e engenharia de software. Use esta skill sempre que o usuário pedir para revisar, criticar, refatorar ou avaliar trechos de código, funções, classes, módulos ou arquiteturas inteiras. Ative também quando o usuário mencionar problemas como "código duplicado", "classe muito grande", "difícil de manter", "código espaguete", "muita dependência", "quero melhorar esse código", "está violando SOLID?", "como refatorar isso?", "esse código está limpo?", "tem code smell aqui?", "como aplicar injeção de dependência?", "preciso de um code review", ou qualquer variação dessas frases. Ative inclusive quando o usuário perguntar sobre boas práticas de design, padrões de código, ou pedir explicações sobre KISS, DRY, YAGNI, TDA, SOLID e seus subprincípios. Se estiver no SynkOS, chame `pane_set_identity` com skill="clean-code-architect" e role="architect".
Generate, edit, upscale, variate, and style-transfer images using the AgentOS multi-provider image pipeline with automatic fallback and character consistency.