Product & Planning

pku-yuangroup Bundle

Call structural variants (>=50 bp deletions, insertions, inversions, duplications, translocations) from short- or long-read data by reconstructing four orthogonal signals (discordant pairs, split reads via the SA tag, read depth, local assembly). Covers Manta, DELLY, LUMPY/smoove, GRIDSS2, SvABA for short reads and Sniffles2, cuteSV, pbsv, dipcall/PAV for long reads, each mapped to the signals it fuses and the blind spots that follow. Use when choosing an SV caller from its signal set and failure modes, decoding the SVLEN-sign / symbolic-vs-BND / CIPOS VCF representation minefield, force-genotyping a cohort matrix instead of unioning discovery VCFs, merging populations with sequence-aware Truvari vs position-only SURVIVOR, parameterizing a Truvari benchmark, or deciding when short-read insertion recall forces a switch to long reads. Not for pure copy-number dosage (see copy-number/cnvkit-analysis).

pku-yuangroup Bundle

Quality control, filtering, and normalization for spatial transcriptomics (Visium, Visium HD, Xenium, MERFISH/MERSCOPE, CosMx, Slide-seq) with Squidpy and Scanpy. Use when setting QC floors that do NOT delete real low-count imaging cells (an scRNA min_counts=500 floor deletes nearly every Xenium cell, whose vector is tens-to-low-hundreds of transcripts); deciding whether to normalize at all when library size carries spatial biology rather than pure technical depth; choosing cell-volume/area normalization over Pearson residuals for skewed targeted panels; reading negative-control-probe / blank-barcode false-discovery rates; and inspecting QC spatially on the tissue rather than only in violins.

lgrappag Skill

Implement efficient type discovery and inspection systems

jiayaoqijia Bundle

Retrospective trade review + improvement coaching for the user's Senpi trading. Answers "did I sell too early or late", "what did I miss this week", "master my week", "compare my trades to the market / to the best whales", "how could I make more gains", "suggest improvements", "review my trades", "am I getting shaken out too early / how are my exits firing", "what did my own limits block / what couldn't I take", "where am I leaking", "walk me through / explain my [asset] trade", "what am I paying in fees / maker vs taker", "why is [strategy] losing". When the user has NOTHING to review yet, `meta.book_state` routes it: nothing deployed -> read the market (senpi-market-pulse) then shortlist a fit (senpi-strategy-discover); deployed-but-idle -> diagnose THAT strategy, never pitch another. A hidden engine (scripts/review.py) reconstructs every CLOSED trade from discovery, enriches each exit reason + blocked signals from the runtime telemetry event log, computes the honest "if I'd held to now" counterfactual, and

jiayaoqijia Bundle

Discover supported third-party DApps and route protocol-specific requests to OKX plugins without signing or broadcasting. Use for DApp discovery or comparison; a named protocol's operations or analytics; Polymarket/UpDown prediction markets, bets, and positions; protocol-native actions involving HYPE/HLP, stETH/wstETH, CAKE, CRV, COMP, RAY, GHO, or PT/YT; pump.fun writes; and unsupported-DApp alternatives. Supported DApp names include Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound, Pendle, Lido, ether.fi, GMX, Kamino, Orca, Meteora, Clanker, and pump.fun. Requests to find, buy, or subscribe to a signal or signal service are OKX.AI marketplace workflows, even when they name Polymarket or another DApp.

jiayaoqijia Bundle

On-chain trading signals and custom signal strategy management on Binance Web3. Three signal sources: smart money (wallet buy/sell events), platform strategies, and user-created strategies (meme / fomo). Four scenario domains: (A) Reports — daily report, monthly backtest review (BSC vs Solana, protocol comparison); (B) Signal discovery — feed, sort by maxGain or multi-strategy hit, token buyability ("can I still buy"); (C) Analysis — backtest interpretation, strategy comparison by golden/silver/bronze rate, indicator impact (KOL holdings, protocol, liquidity); (D) Management — create/update/delete strategies, enable/disable strategies, trigger/schedule backtests, query credits, auto-scan, copy strategies from the strategy hall. Trigger whenever the user mentions trading signals, smart money, custom signal strategies, backtesting, strategy management, daily or monthly reports, token buyability, or indicator impact analysis — even if they don't say "signal" or "strategy".

jiayaoqijia Bundle

Wallet tracking and monitoring on Binance Web3. Monitor token/trade activity for private groups or public Smart Money/KOL data. Four domains: (A) Discovery — consensus, pioneer, leaderboard diff, token buyer lookup, time-window summaries, similar wallets; (B) Evaluation — token risk (tokenRiskLevel ≥ 3), group rhythm, follow list assessment, token heat; (C) Replay — 4h summary, Accumulation/Distribution, sector rotation, anomaly orders, round-trip, first-mover/leader-follower, wake-up, bot-like; (D) Management — group create/rename, batch import, label update, link, follow list; (E) Real-time — WebSocket push for Smart Money, KOL, wallet-level, and address-level trade events. Trigger on: wallet tracker, monitoring, consensus, pioneer, accumulation, Distribution, Sector Rotation, Anomaly Large Order, round-trip, first-mover, wake-up, bot-like, token risk, token heat, group profile, similar wallets, group management, address import, follow list, real-time push, WebSocket — even without "tracker" explicitly.

rudironsoni Skill

Discovers available MCP servers from registries and validates compatibility. Auto-discovers MCP servers from official registries, community sources, and local definitions. Triggers on: mcp discovery, find mcp servers, discover mcp, mcp registry, mcp catalog.

yigityildiz0 Bundle

Discover and route broad requests across the currently installed skill library when no single specialist is obvious. Use for current capability discovery, installed-skill lookup, or Turkish intents such as ‘hangi skill uygun’, ‘hangi beceriyi kullan’, ‘kurulu becerilerde ara’, ‘uygun iş akışına yönlendir’. Do not intercept a clean specialist match or search the archived full library; use skill-library-router for an archived or uninstalled workflow.

yigityildiz0 Bundle

Select and load relevant installed skills before substantial work when the user names a skill, a catalog description clearly matches the task, or several specialist workflows must be coordinated. Use for skill discovery/routing and Turkish intents such as “uygun skillleri kullan”, “hangi beceri gerekli”, “skill seç ve uygula”. Do not auto-load for greetings, trivial one-step questions, or a speculative 1% match; user, system, safety, permission, and host instructions always take precedence.

pku-yuangroup Bundle

Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.

jesusgarciafernandez Bundle

El Clustering con K-means (v2.0) es la competencia de aprendizaje no supervisado para agrupar entidades similares. No es solo "hacer grupos"; es Ingeniería del Descubrimiento de Patrones. Úsala para tareas de Datos y Analítica: clustering, k-means, unsupervised-learning, customer-segmentation, behavioral-patterns, dimensionality-reduction.

jesusgarciafernandez Skill

Habilidad estratégica y operativa para diseñar e implementar el marco de trabajo OKR (Objectives and Key Results), permitiendo a las organizaciones establecer metas ambiciosas y medibles que alineen el esfuerzo de todos los equipos hacia una dirección común. Úsala para tareas de Proyectos y Colaboración: okr, objectives, key-results, focus, alignment, strategy-execution.

jesusgarciafernandez Bundle

La Comunicación Corporativa e Comms Ops (v2.0) es la competencia de "Dominar la arquitectura de la información institucional para garantizar la coherencia y el éxito de Jesús García Fernández". Úsala para tareas de Comunicación y Marca Digital: comms-ops, corporate-communication, internal-comms, stakeholder-engagement, brand-voice, transparency.

jesusgarciafernandez Bundle

La Responsabilidad Social Corporativa (v2.0) es la competencia de "Devolver a la sociedad parte de lo que el éxito técnico del negocio permite ganar". Úsala para tareas de Legal y Cumplimiento: CSR, sustainability, social-impact, corporate-citizenship, philanthropy, stakeholder-engagement.

jesusgarciafernandez Bundle

Upselling y Cross-selling (v2.0) es la disciplina de maximizar el valor de cada relación comercial mediante la oferta ética y oportuna de versiones superiores (Upsell) o productos complementarios (Cross-sell). No es "vender más por vender"; es Ingeniería del Crecimiento del Cliente. Úsala para tareas de Ventas y Comercio Electrónico: upselling, cross-selling, revenue-expansion, aov-optimization, customer-success, value-bundling.

jesusgarciafernandez Bundle

La Gestión de Bases de Datos con Airtable (v2.0) es la competencia de diseñar herramientas de gestión a medida utilizando plataformas relacionales no-code. No es solo "hacer una tabla"; es Ingeniería de Operaciones Digitales. Úsala para tareas de Productividad y Operaciones: airtable, database-design, workflow-automation, no-code, productivity-ops, relational-data.

jesusgarciafernandez Bundle

La Estrategia de Consultoría y Arquitectura de Soluciones es la capacidad de diseñar el "Blueprint" técnico y estratégico de una organización digital. No es solo "elegir herramientas"; es Ingeniería del Futuro Corporativo. Úsala para tareas de Estrategia y Operaciones: consultoría-estratégica, arquitectura-soluciones, roadmap-tecnológico, diagnóstico-digital, estrategia-it, product-strategy.

whyzsm Bundle

Use this skill when users need to search academic papers, download research documents, extract citations, or gather scholarly information. Triggers include: requests to "find papers on", "search research about", "download academic articles", "get citations for", or any request involving academic databases like arXiv, PubMed, Semantic Scholar, or Google Scholar. Also use for literature reviews, bibliography generation, and research discovery. Requires OpenClawCLI installation from clawhub.ai.

whyzsm Bundle

Product strategy expert-team router for product management work: PRD and feature specs, requirement analysis, user research synthesis, competitive analysis, product metrics review, roadmap planning, sprint planning, stakeholder updates, and end-to-end product strategy delivery. Coordinates requirement analysis, user research, competitive intelligence, product data analysis, and roadmap planning.

whyzsm Bundle

软件产品经理/软件开发经理知识技能。当用户需要产品经理级别的专业支持时触发，包括： 需求分析、PRD撰写、产品设计、产品路线图规划、竞品分析、数据分析； 或用户询问产品经理职责、如何成为产品经理、产品经理技能要求； 或需要产品架构图、流程图、时序图、甘特图等 Mermaid 图表； 或需要从0到1输出PRD文档并自动生成可交互H5原型图； 或需要将PRD文档导出为Markdown(.md)或Word(.docx)格式。 注意：本 skill 采用主动式产品咨询流程。流程：确认需求 → 提问澄清 → 网络搜索 + RAG搜索 → 产品规划 → 方案对比 → 技术选型 → 需求确认 → PRD文档 + Mermaid图表 → 导出格式 → H5原型图（可选）。

whyzsm Bundle

End-to-end PRD writing workflow. Use when the user wants a complete product requirements workflow that spans requirement discovery, EPIC/user-story decomposition, prioritization, professional PRD drafting, PRD-to-design handoff, and PRD review/scoring. This skill coordinates the companion skills requirements-analysis, software-manager-skill, prd, prd-writer-pro, prd-to-design-doc, and prd-reviewer.

whyzsm Bundle

Generate structured compliance audits for SOC 2, ISO 27001, GDPR, HIPAA, PCI DSS, SOX, and CCPA with readiness scoring, gap analysis, remediation roadmap, and evidence checklist.

whyzsm Bundle

UI 原型设计智能体。用于从产品想法、PRD、截图、Figma 或 Sketch 设计稿出发，串联 PRD 分析、设计稿解析、设计系统制定、UI 审查、线框图绘制和高保真 HTML/Tailwind 原型生成，交付完整 UI 原型设计包。

whyzsm Bundle

需求发现教练。用于训练销售掌握深度需求挖掘技巧，发现真正的业务痛点。来源于 WorkBuddy 销售商务卡片，并转换为 Codex 可安装的专家入口格式。

whyzsm Bundle

产品战略专家团。用于从产品想法、问题陈述、用户研究、竞品材料或业务指标出发，完成产品机会探索、PRD/功能规格、路线图规划、利益相关者沟通、竞品分析、指标审查、产品头脑风暴和冲刺规划。来源于 WorkBuddy product-management 团队能力，并转换为 Codex 可安装的专家团入口格式。

vivy-yi Skill

将合同审查结果转化为业务相关方实际会阅读的摘要。 不是法律备忘录——而是"我能签吗，我需要知道什么"的2分钟回答。 适用情形：用户说"给业务做个摘要"、"写给[利益相关方]"、 "解释给采购"、"非法律人员摘要"，或审查完成后需要发给法律部门以外的人。

ndpvt-web Skill

Build multi-agent systems that discover causal rules from event sequences using specialized agents (causal discovery, contextual information, orchestrator). Use when asked to: 'find causal patterns in event logs', 'build a multi-agent diagnostic system', 'automate rule discovery from sequences', 'generate Boolean fault rules from data', 'create an agent pipeline for causal reasoning', 'detect error patterns in time-series events'.

ndpvt-web Skill

Implement the EXPERIGEN agentic framework for automated hypothesis generation and empirical validation on datasets. Uses a Bayesian-optimization-inspired Generator-Experimenter loop to discover statistically significant, novel hypotheses from data. Trigger phrases: 'generate hypotheses from this dataset', 'discover patterns in social data', 'run EXPERIGEN on this data', 'automated hypothesis testing', 'find significant predictors in this dataset', 'data-driven hypothesis discovery'.

ndpvt-web Skill

Build multi-stage search pipelines that separate recall from precision for discovering datasets, documents, or resources from heterogeneous metadata catalogs. Uses intent classification, hybrid retrieval (BM25 + embeddings + abbreviation expansion), and LLM reranking. Trigger phrases: 'build a dataset discovery pipeline', 'multi-stage search system', 'find relevant datasets for my research goal', 'scientific data search', 'hybrid retrieval with reranking', 'intent-aware search pipeline'

ndpvt-web Skill

Detect and extract pairwise causal relationships from text using structured prompting strategies (zero-shot, CoT, few-shot ICL, Least-to-Most, ReAct). Built on the unified evaluation framework from Anuyah et al. (2026) covering 12 datasets across biomedical and multi-domain contexts. Use when the user asks to "find causal relationships in text", "extract cause and effect from sentences", "detect causation vs correlation", "build a causal extraction pipeline", "benchmark causal reasoning", or "annotate causal links in a corpus".

ndpvt-web Skill

Evolve compiler optimization heuristics by coupling LLM code generation with evolutionary search and autotuning. Synthesizes executable C++ decision logic that integrates directly into LLVM or other compilers, replacing hand-crafted rules with empirically validated policies. Use when: 'optimize LLVM inlining heuristic', 'evolve compiler pass logic', 'synthesize register allocation priority', 'automate compiler heuristic design', 'generate C++ optimization policy', 'replace hand-tuned compiler rules with learned ones'.

ndpvt-web Skill

Proactive bug discovery through documentation-driven test generation. Generates tests that find latent bugs by comparing code implementations against documentation-derived intent, rather than treating existing code as ground truth. Use when: "find bugs in this codebase", "write tests that catch real defects", "proactive testing against the docs", "generate bug-finding tests", "test this repo for hidden bugs", "audit code against its specification"

ndpvt-web Skill

Build closed-loop discovery benchmarks where an agent iteratively proposes, evaluates, and refines candidates under a fixed oracle budget. Use when: 'build a materials discovery benchmark', 'create a closed-loop optimization pipeline', 'benchmark an iterative search agent', 'set up a discovery loop with budget constraints', 'evaluate a generative pipeline with oracle feedback', 'compare discovery agents on convex hull stability'.

ndpvt-web Skill

Design and evaluate multi-server MCP tool-use benchmarks using claims-based scoring rubrics. Use when: 'benchmark my MCP agent', 'evaluate tool-use across servers', 'build a claims-based rubric for tool calls', 'test multi-step MCP workflows', 'score agent tool discovery', 'diagnose tool-use failures'.

ndpvt-web Skill

Implements the AGEA framework for budget-constrained extraction of knowledge graphs from GraphRAG systems using novelty-guided adaptive querying, external graph memory, and a two-stage discovery-then-filter pipeline. Use this skill when the user says: "extract the knowledge graph from this RAG system", "audit GraphRAG for data leakage", "test if my GraphRAG API exposes its graph structure", "reconstruct the entity-relation graph behind this endpoint", "red-team my GraphRAG system for extraction attacks", "assess knowledge graph leakage risk in my RAG pipeline".