yo-steven

CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

Install cuOpt for Python, C, or as a server (pip, conda, Docker) — system requirements, install commands, and verification. Use when the user wants to install or verify cuOpt for any user-facing interface. For building cuOpt from source or contributing to…

LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.

LP, MILP, and QP (beta) with cuOpt — CLI only (MPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from MPS via command line.

Solve Linear Programming (LP), Mixed-Integer Linear Programming (MILP), and Quadratic Programming (QP, beta) with the Python API. Use when the user asks about optimization with linear or quadratic objectives, linear constraints, integer variables, scheduling,…

Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.

cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.

Chrome DevTools MCP automation for the existing Chrome tabs; no AppleScript.

Release the clawpatch TypeScript CLI to npm and GitHub. Use when asked to publish, ship, or verify a clawpatch version: version/changelog prep, local proof, CI/CodeQL watch, npm publish, GitHub tag/release, release verification, and post-release changelog…

ClawSweeper status: recent URLs, workflow health, active workers, ops snapshot.

ClickClack ops: hosted chat app, Hetzner prod deploy, DNS/docs/app surfaces, clean Docker rollout.

Cloudflare Registrar via mcporter: domain availability, prices, registration.

Codex source debugging: ~/Projects/codex, codex-rs core/tui/exec/cli/app-server/config.

Codex code review closeout: local dirty changes, PR branch vs main, parallel tests.

Discord-backed OpenClaw agent/session relay; not archive search.

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+…

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+…

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+…

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+…

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+…

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+…

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+…

Manus-style file-based planning for complex tasks. Creates and maintains task_plan.md, findings.md, and progress.md under .kiro/plan/. Use when planning, breaking down work, resuming a multi-step task, tracking phases, or restoring context after compaction.…

Use when answering a question that needs data from a KTX-connected database - investigating, analyzing, "how many", "show me", "what's the breakdown of", finding records by value, exploring tables, comparing periods, explaining metrics, or any data-analysis…

Map dbt `schema.yml` / `properties.yml` models and sources into KTX semantic-layer overlays and column notes. Covers `sources:` vs `models:`, column `data_tests` (not_null, unique, accepted_values, relationships), and how bundle-time writes complement…

Extract durable KTX knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard, Look, and explore JSON. Load for WorkUnits whose raw files are under explores/, dashboards/, or looks/.

Map a LookML view/model/explore into KTX semantic layer sources. Covers the LookML to KTX primitive table, provenance tagging, and three worked examples (overlay, standalone from derived_table, standalone with sql_always_where). Load when the turn contains…

Convert Metabase questions, models, and metrics into KTX Semantic Layer source definitions. Covers result-metadata to KSL column type mapping, FK/PK detection, near-duplicate deduplication, pre-aggregation decomposition, join-graph connectivity, and how to…

Map a MetricFlow semantic_model or metric into KTX semantic layer sources. Covers the MetricFlow to KTX primitive table, `extends:` inheritance flattening, metric-type handling (simple / derived / ratio / cumulative / conversion), `model: ref('x')`…

Synthesize durable KTX wiki pages and semantic-layer sources from staged Notion pages, databases, data-source rows, and clustered Notion evidence. Load when a WorkUnit contains Notion raw files or Notion evidence chunks.

How to capture new reusable patterns into KTX's semantic layer - when a measure, segment, or join belongs in the catalog and how to write it generically so it stays small and useful over time. Loaded by the post-turn memory-agent only. The research agent does…

AI与MCP安全评估 — Prompt注入、工具滥用、MCP信任边界、Agent权限逃逸、数据泄露、模型风险、GAARM风险矩阵

客户端逆向与Burp重放 — 复杂客户端签名恢复、加密还原、请求链追踪、稳定重放，适用于已授权安卓App渗透测试、浏览器JS签名、桌面客户端逆向

CTF密码学攻击知识库 — RSA攻击（小指数/共模/Wiener/Coppersmith）、AES攻击（Padding Oracle/ECB字节翻转/GCM nonce重用）、ECC攻击、LFSR/LCG/PRNG攻击、古典密码、LWE格攻击

CTF Web攻击知识库 — PHP弱比较绕过、命令注入空格绕过、eval回显技巧、SSTI注入链、反序列化利用链、PHP代码审计checklist、常见flag位置

内网渗透高级 — 横向移动、凭据窃取、提权、持久化、隧道代理、AD攻击、ADCS滥用、Exchange/SharePoint攻击

OSINT 开源情报收集知识库 — 四维信息收集模型（服务器→网站→域名→人员），维度四（人员信息）条件触发

渗透工具速查 — 编码解码、反向Shell、红队工具、漏洞利用、密码攻击、内网工具、凭据窃取、提权、隧道代理、系统命令、信息收集、域渗透、Web工具、Windows工具

渗透速查与Payload — 快速Payload家族、绕过提醒、验证顺序、常见测试卡片，适用于已知测试方向后快速查找

Provide system alias mapping for Search CLI. Invoke this skill when user mentions "Search CLI", "search_cli", or tries to execute search_cli commands.

Binds a dataset to an application with reviewed field config inference. Invoke when using `vs app dataset bind` and searchable/filter/suggest fields must be inferred and confirmed first.

Conversational search runtime: send messages, keep sessions consistent, and verify retrieval behavior and responses.

General item-level onboarding: understand structured item data, generate schema and config plans, create datasets, and create or bind apps only when the user explicitly asks for app-level setup.

Recommend runtime and scene management: run recommendation requests, manage recommend scenes, and verify the basic recommendation path.

Search runtime and scene management: run queries, inspect scenes, debug app readiness, and diagnose recall or config issues.

Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.

Shared SearchCLI setup: install, authenticate, run doctor, and verify the local environment.

Use this skill for genetics, genome source, variant, gene, phenotype, disease, screen, pharmacogenomics, and Genomi install/setup maintenance questions.

Register, parse, and digitize private genome source files into a local Active Genome Index and supporting evidence stores. Use when the session explicitly supplies a VCF/gVCF, BAM, genome.computer .genome/1.0 bundle, 23andMe raw genotype export, AncestryDNA…

Build and inspect ClinVar exact-match evidence and candidate inventories. Use for clinical labels, VUS/conflict, carrier context, and drug-response rows.

Activate this skill for "/genomi decode", "decode my genome", "decode my DNA", "show me the dashboard", "the Genomi dashboard", "full report", "one-shot rundown", or any all-at-once request that asks Genomi to compose every capability's findings into a single…

Answer drug-response, medication, PharmGKB-style, PGxDB, ATC, DrugBank, gene-drug, and variant-drug questions using public PGx evidence plus local sample genotype support when an Active Genome Index is selected.

Plan rare disease, hereditary disease, and cancer risk source investigation from public targets or selected active genome evidence.

Answer specific rsID, allele, gene, region, genotype, and absence/callability questions using explicit session context or public evidence.

Run red-team attacks and generate a report for an agent target.

Set up an agent or chatbot target for Opfor red-teaming.

Run red-team attacks and generate a report for an MCP server target.

Set up an MCP server target for Opfor red-teaming.

Distill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion, Linear, Google Docs, and more — without manual paste. Use when the user wants a…

Walk through a UI flow once manually and capture a durable interaction map — which DOM elements to click, which network requests they trigger, and what field shapes they expose. Produces a reusable selector+endpoint reference for automation scripts. Use…

Distill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion, Linear, Google Docs, and more — without manual paste. Use when the user wants a…

Walk through a UI flow once manually and capture a durable interaction map — which DOM elements to click, which network requests they trigger, and what field shapes they expose. Produces a reusable selector+endpoint reference for automation scripts. Use…

Create reusable black-background white-text opening animations for new videos. Use when the user asks for "黑底白字开场", "纯黑加白字", "白色文字逐渐出来", "一个个字出来", "打字效果", "打字音效", "字体变化开头", "opening title animation", "kinetic text opener", or a short black-and-white intro…

Create dark cinematic SaaS/product motion videos in the Presenton-like "magic UI" style: black starfield stage, bottom purple glow, large kinetic type, cyan-to-magenta CTA buttons, prompt cards, floating UI templates, integration badges, model rings, export…

Analyze and verify reference-video replication. Use when the user asks to recreate, copy, match, align, pixel-align, or compare a video against a reference; when a remake is judged "not aligned"; or when a video needs frame-by-frame breakdown, side-by-side…

AI Niuma（数字员工生产基地）：把企业核心人员已有的工作痕迹（聊天记录、会议录音/转写、方案文档等） 蒸馏成可被团队调用的 AI 员工。用户输入 /niuma，或提到“数字员工生产基地”“数字员工工坊” “蒸馏AI员工”“企业数字分身”“使用成品AI员工”“加强已有AI员工”，或想把管理者/核心员工的判断方法 沉淀为团队助理、教练、数字分身时，必须使用本 Skill。用户提到“质检”“检查”“测试”“质量评估”…

可公开演示的 HRBP 数字员工样例。所有场景、人物、组织和数据均为合成示例，仅用于展示 AI-niuma 生成结果的结构与使用方式。

Obsidian 知识库全生命周期管理：三层架构、素材入库(ABC分级)、健康检查、GBrain/GraphRAG/LLM Wiki 三件套集成、目录整理

微信公众号文章 → Markdown 提取 + A层观点提取 + B层问题链生成。 支持直接链接抓取和 PDF 提取两种方式。