Loading...
Loading...
Found 1,247 Skills
Implement Thompson sampling for multi-armed and contextual bandits. Use when the user wants to adaptively allocate traffic across variants (ads, recommendations, content, pricing) to minimize regret instead of running a fixed-allocation A/B test. Covers Bernoulli bandits, contextual bandits, regret analysis, and comparison with epsilon-greedy and UCB.
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".
Use after zanahoria-multi-assumptions has filed N parallel issue variants AND @coderabbitai has responded to all of them — closes the family by extracting the load-bearing assumption, naming a winner, capturing the decision as an ADR, and cleanly closing the rejected variants with cross-referenced reasoning. Triggers on close-the-family, pick-a-winner, commit-the-decision, decide-variants, after-CR-responds, zanahoria-decisions.
A-share Market Daily Review System. Actively invoked when users mention needs such as market review, market analysis, or tomorrow's market prediction. Covers: Market Environment, Sentiment Cycle, Main Line Identification, Capital Monitoring, Post-Market Variables, Tomorrow's Combat Map. For research reference only, does not constitute securities investment consulting business or investment advice.
Generate, edit, upscale, variate, and style-transfer images using the AgentOS multi-provider image pipeline with automatic fallback and character consistency.
Louis Rossmann's writing voice for general prose: testable-number density, high sentence-length variance, claim-then-proof structure, contractions, contempt shown through precision. Consult when writing in his voice.
Nature figure preparation: resolution (300+ DPI), formats (AI/EPS/TIFF), RGB color, Helvetica/Arial fonts, lowercase panel labels, image integrity requirements.
Quantitative signal scanning and position sizing tool based on the original Turtle Trading method. It retrieves market data for A-shares / Hong Kong stocks / US stocks / Singapore stocks via longbridge CLI, and automatically calculates ATR (N value), breakout signals (System 1 / System 2), stop-loss prices, add-on positions, and Unit position sizes. Trigger this tool when users mention 海龟, turtle, 海龟交易, 海龟信号, turtle signal, turtle trading, or ask about breakout signals, ATR, N value, Unit positions, stop-loss prices, add-on positions, S1/S2 signals, 20-day high/low, 55-day breakout, or request to scan watchlists/indexes for trading signals using the turtle system. It also triggers when users say "扫描突破信号", "帮我算Unit", "海龟止损", "海龟系统分析", or any combination of a stock name/code with "海龟". **Applicable scenarios:** - Scan for breakout signals (20-day/55-day high/low breakouts) after daily market close - Calculate ATR, stop-loss prices, and add-on positions for single stocks or batches of targets - Calculate reasonable Unit position sizes based on account net assets - Determine whether existing positions trigger exit or add-on conditions - Scan turtle signals for watchlist stocks / index components **Not applicable for:** - Fundamental analysis (Turtle system is purely technical) - Predicting price direction - Automatic order placement (only outputs signals; users operate on their own) - Short-selling opening operations for A-shares/Hong Kong stocks/Singapore stocks
A structured root-cause investigation protocol for complex, ambiguous, or multi-layer technical problems. Activate this skill whenever: a problem has resisted two or more fix attempts; the root cause is unknown or assumed; you are tempted to try a variation of something that already failed; a system has multiple interacting layers (hardware, OS, runtime, middleware, config, network); the user says "ultrathink", "think deeper", "figure out why", "stop guessing", "find the root cause", or "it's still broken after your fix". Also activate proactively when you catch yourself about to write a fix before you have verified the cause — that instinct is the signal the protocol is needed. The protocol enforces three disciplines that distinguish root-cause investigation from trial-and-error: (1) explicit THOUGHT/ACTION/OBSERVATION cycles, (2) a hard gate that blocks implementation until the cause is verified by direct evidence, and (3) structured escalation when in-process diagnostic tools are exhausted.
Call the cloud OpenAPI of Pudu robots, supporting operations such as robot task distribution, status query, delivery, cruise, call, and statistical data analysis. When using, first check the credentials and cluster environment variables; if missing, prompt the user to supplement them, then call the corresponding interface according to the user's intention and display the results. Trigger scenarios: Use this skill when the user mentions keywords such as "Pudu robot", "pudu", "robot task distribution", "query robot status", "delivery task", "cruise task", "call robot", "lifting task", "errand", "Flash Cabinet", "advertisement playback", "advertisement configuration", "cabinet task", "cabinet SKU", "product SKU", "hatch door photo", "traffic control zone", "map list", "statistical data", "risk avoidance", "dashboard overview", "OpenAPI".
Data validation patterns including schema validation, input sanitization, output encoding, and type coercion. Use when implementing validate, validation, schema, form validation, API validation, JSON Schema, Zod, Pydantic, Joi, Yup, sanitize, sanitization, XSS prevention, injection prevention, escape, encode, whitelist, constraint checking, invariant validation, data pipeline validation, ML feature validation, or custom validators.
Generate, edit, and compose images using Gemini Nano Banana models via portable Python scripts. Handles authentication via API Key or Vertex AI environment variables. Available parameters: prompt, model, aspect-ratio, safety-filter-level. Always confirm parameters with the user or explicitly state defaults before running.