其他技能

Socratic ideation and idea routing — think through ideas before committing to plans

中文简介正在准备中。当前显示原文说明。

Create context handoff when pausing work mid-phase

中文简介正在准备中。当前显示原文说明。

Create detailed phase plan (PLAN.md) with verification loop

中文简介正在准备中。当前显示原文说明。

Run all remaining phases autonomously — discuss→plan→execute per phase

中文简介正在准备中。当前显示原文说明。

Archive completed milestone and prepare for next version

中文简介正在准备中。当前显示原文说明。

Detect and search for similar utility/invention patents based on product information. Trigger when users mention utility patent detection, patent infringement risk, patent similarity search, patent screening, invention patent search, patent risk assessment, TRO (Temporary Restraining Order) risk analysis, utility patent, invention patent detection, patent infringement risk, patent search, TRO risk, Ruiguan. Even if the user does not explicitly say "utility patent", trigger this skill whenever their need involves checking whether a product may infringe existing utility/invention patents before selling in a target market.

中文简介正在准备中。当前显示原文说明。

Text trademark detection and infringement risk analysis for e-commerce product listings. Trigger when users mention trademark detection, trademark risk check, brand infringement screening, product title trademark scan, text trademark search, listing compliance check, intellectual property risk assessment, text trademark detection, trademark infringement, brand infringement screening, listing compliance, intellectual property risk, Ruiguan. Even if the user does not explicitly say "trademark", trigger this skill whenever their need involves checking whether product text (titles, descriptions, bullet points) contains potentially infringing trademarks.

中文简介正在准备中。当前显示原文说明。

Query and analyze Google Trends real-time hot topics and trending searches for a specified time range and country/region. Triggered by: Google Trends, hot topics, real-time trending, popular trends, current hot searches, recent trending, viral topics, trending searches, trend discovery, market trends, what's popular, trending now, breakout topics.

中文简介正在准备中。当前显示原文说明。

Search and benchmark public Temu shops through Nexscope.

中文简介正在准备中。当前显示原文说明。

Product AI Visibility & Ranking — evaluate how AI search engines (ChatGPT, Claude, Gemini, DeepSeek) recommend your product when shoppers ask buying questions. Triggers: AI visibility, product AI ranking, AI recommend, AI search, does AI mention my product.

中文简介正在准备中。当前显示原文说明。

Query Amazon is latest policy, regulation, and compliance feed. Supports paginated browsing by marketplace and time range (with AI-generated Chinese summaries), and fetching full article body by record ID. Trigger when users mention Amazon policies & regulations, seller compliance announcements, platform rule changes, policy alerts, FBA/fee policy updates, multi-marketplace policy tracking, policy original text, news details, or similar terms. Even if the user does not explicitly mention "policy feed," trigger this skill whenever the request involves Amazon is officially published policies, regulations, and news for sellers, including their full text.

中文简介正在准备中。当前显示原文说明。

Diagnoses slow services and regressions via profiling and tail-latency math. Use when diagnosing slow services, profiling hot paths, or judging whether an optimization is real.

中文简介正在准备中。当前显示原文说明。

Guides mobile platform selection and delivery across native and cross-platform stacks. Use when planning auth, push, deep links, releases, or app architecture for iOS/Android.

中文简介正在准备中。当前显示原文说明。

Guides native Android development with Kotlin, Jetpack Compose, and Views interop. Use when building, rewriting, or reviewing modern Android apps after establishing runtime truth.

中文简介正在准备中。当前显示原文说明。

Team-theory primitives for cooperative agents: what each subagent sees, when to communicate, aggregation, Shapley credit, coalition topology. Use when organizing subagents.

中文简介正在准备中。当前显示原文说明。

PID/MPC/Kalman/anti-windup control primitives for feedback loops. Use when an autoscaler flaps, a controller overshoots after saturation, or budget pacing overspends at peak.

中文简介正在准备中。当前显示原文说明。

Formulates LP, MILP, CP-SAT models; diagnoses infeasibility and gaps. Use when a MILP is infeasible, shifts need scheduling under capacity, or choosing a solver.

中文简介正在准备中。当前显示原文说明。

Grounding-theory primitives for common ground and repair. Use when deciding whether to ask a clarifying question, confirming a handoff was understood, or fixing multi-turn drift.

中文简介正在准备中。当前显示原文说明。

16 evidence-graded behavioral-economics primitives. Use when asking will this nudge work, is a pricing decoy or dark pattern lawful, or what effect size to expect.

中文简介正在准备中。当前显示原文说明。

Applies planning/search theory (A*, CSP, MCTS, PDDL, HTN) to agents. Use when ordering tool calls, enforcing preconditions before side effects, or validating a plan.

中文简介正在准备中。当前显示原文说明。

Network-science primitives: centrality, influence seeding, communities, contagion vs homophily, GNN failures. Use when seeding a referral campaign or finding critical graph nodes.

中文简介正在准备中。当前显示原文说明。

Sizes queues and worker pools. Use when estimating Kingman G/G/1 mean waiting time, Erlang or Little's Law sizing, p99 under load, retry storms, worker counts.

中文简介正在准备中。当前显示原文说明。

Analyzes hazards in systems or AI agents: STPA, guardrails, safety cases, incident analysis. Use when an agent can take actions or send payments.

中文简介正在准备中。当前显示原文说明。

Builds a GPT and BPE tokenizer from scratch. Use when implementing autograd, attention, a nanoGPT loop, muP hyperparameter transfer, WSD annealing, loss spikes, or mid-training.

中文简介正在准备中。当前显示原文说明。