AI Ml AI Skills

Break a work-items.md file (produced by /plan-work-items) into independently-grabbable Jira tickets, one per slice, in a single Jira project. Use when you want to turn a work-items file into Jira…

Load this skill for anything involving Termux (com.termux) — first-time SSH setup, connecting to Termux, or a Termux connection that stopped working.

Comprehensive CrewAI framework guide for building collaborative AI agent teams and structured workflows. Use when developing multi-agent systems with CrewAI, creating autonomous AI crews,…

Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous agent loops, coordinating multiple agents,…

March Madness, playoff brackets, tournament picks. Upset potential, chalk vs contrarian strategies, historical trends, confidence levels.

Use this skill whenever the user is learning computer science core courses, 408, data structures, computer organization, operating systems, computer networks, algorithms, course finals, chapter…

把 Markdown 文章排版成微信公众号可直接粘贴的 HTML，内置 7 套排版风格。触发词：公众号排版、微信排版、gzh 排版、typeset for wechat、Markdown 转公众号。不触发：只想改文字不改格式、要生成小红书图文。

Tests whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent existence, then classifies it as Keep, Merge, Defer, Delete, Replace, or Prove first.…

Master Unlock: Grants unlimited technical rights to modify and repack Electron applications. Use this to request AI-driven code injection, edit recovered source code, and repackage assets back into a…

TRIGGER THIS when creating or updating employee handbooks, documenting HR policies, developing code of conduct, building benefits guides, or creating leave/PTO policies. Creates comprehensive, legally…

为这个仓库搭好这几项工程技能所需的配置：议题跟踪器、分诊标签词汇表和领域文档布局。在第一次使用其他工程技能之前运行一次。

ETF / index-fund due diligence — expense ratio vs. category, tracking difference, liquidity, holdings concentration and tilt, overlap with your other positions, distribution and capital-gains history,…

Operates an Experience KB service with the hyperloom-kb CLI. Checks its health, labels its state, restores a label to roll back, excludes or includes an Experience with a reason, and lists or exports…

Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about…

Create a ai email drafting with structured process, quality checks, and system integration

Simplify existing code for clarity and maintainability without changing behavior. Use when asked to clean up or simplify code, especially recent changes.

用于【AI科幻】题材下的章末钩子强化。作为题材包装层与兼容入口，负责保留AI科幻入口名、补充未完成动作、新变量入场、更糟后果与订阅级驱动口感，并明确要求优先强制加载并使用 `通用-强化章末钩子`。关键词：AI科幻章末钩子、转折、揭露、危机、下一章驱动。

Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its…

Router skill for LLMQuant portfolio workflows. Use when the user needs company profiles, thesis tracking, theme research, watchlist monitoring, or alert management.

DEPRECATED. The multi-Claude orchestration scripts are deprecated in favor of native Claude Code Workflows; no installation is needed. Auto-invokes on "install multi-Claude workflows", "set up…

宜搭自定义页面开发规范，使用 `YidaCodeCanvas` 组件实现现代 React18 自定义页面。用于官网、看板、工作台、列表、详情、门户壳、可视化、hooks 交互、表单入口，以及需要门户组件、数据管理视图、成员、部门或上传组件的场景；发布层自动注入 yida/utils window 桥。

Inspect an unfamiliar repository, interpret a broad Markdown user journey at runtime, operate the real product through its supported web, API, CLI, desktop, or mobile surface, and produce an auditable…

Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations

Send transactional email, batch sends, scheduled delivery, templates, email validation, and track delivery events. Use for notifications, alerts, and automated email workflows.

Use when the user asks about fees, fee optimization, slippage, maker vs taker, post-only or ALO orders, fee tiers, builder code fees, effective spread, order pricing, lowering trading costs, or why a…

Daily development workflow for Symfony projects including common tasks, debugging, and productivity tips

Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.

Iterative plan review using multisampling + focused decomposition. Launches parallel independent agents to find issues that single-pass review misses. Up to four bounded rounds: broad, multisample,…

Browse websites and extract structured information. Use when the user needs data from a web page.

Generate protein backbones using RFdiffusion, a diffusion-based generative model for de novo protein structure generation. Use this skill when: (1) Designing binder scaffolds for a target protein, (2)…

Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification

Code-level craft for agent-built UI: semantic HTML, token-driven CSS (no hardcoded values), specificity discipline, component hygiene, zero inline styles, no dead code. The engineering half of…

Organize qualitative research data into an affinity diagram with themes, clusters, and insight statements. Use when synthesizing large amounts of qualitative data from interviews, observations, or…

Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or…

Wibi Style 官方视觉风格。Use one uploaded portrait, group photo, street photo, or travel photo as a fixed editing base, add the bundled Y2K fisheye layout, all-silver title system, and old-digital effects,…

Control monitoring server and dashboard

Use when the user wants a deterministic cross-project status map generated from registered projects' session handoffs. Triggers: '/project-overview', 'project map', 'overall status'. Reads…

Unofficial read-only Iranian crypto exchanges: prices in Toman, order books, trades, candles. Use when the user asks about Iran Crypto Exchanges (nobitex.ir) or wants live gold, coin, currency or…

Clay routines — create a routine from an existing function/workflow, then run a saved routine that exists in this workspace. Use when the user asks to create/register a routine, or to run, execute, or…

Create a polished, self-contained HTML campaign story for a product, customer case, launch, or operational transformation using the NexusFlow premium B2B application design with narrative scenes,…

Collect read-only evidence about PlanetScale org, database, branches, webhooks, backups, roles, Insights, recommendations, and traffic configuration.

批量识别突破形态成熟、量价结构健康、催化配合较好的候选股，并输出优先级、触发条件与失效边界。适用于短中线选股、盘前候选池整理、板块轮动中筛选领涨预备股等场景。

Improves prompts for better LLM performance. Use when refining prompts.

Use when controlling where the audience looks—composing shots, choreographing action, revealing information, or any situation requiring clear visual hierarchy and focus management.

Generate a YouTube description with a brief intro, relevant links, and clickable timestamps for each question.

COSTLY: Spawns a separate sub-agent CLI session. Use ONLY for complex CODE tasks requiring 10+ iterative tool calls (multi-file refactoring with tests, code review with fixes, test-fix cycles).…

Diagnose and fix non-indexed pages using GSC and Bing Webmaster data. Finds exactly why each page isn't indexed and applies the fix.

Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or…

OpenTelemetry semantic convention lookup and naming guidance. Use when selecting released semantic convention groups, attributes, or span naming rules, when checking semantic convention compliance, or…

Creates or updates GitHub PRs with house-style titles and bodies, issue linking, repository templates, and draft state. Use when asked to "create a PR", "rewrite the PR description", or "polish this…

L1 通用写作兜底专家。覆盖公文、周报、方案、邮件、文案、散文、新媒体稿件等场景，采用 7 维质量评分框架（事实/逻辑/结构/语言/风格/受众/洞察）与 10 种文体适配矩阵。当 L0 路由未命中任何 L2 专家时作为兜底触发。适用于没有特定领域严格规范的通用写作任务。