AI Ml AI Skills

Control Eight Sleep pods (status, temperature, alarms, schedules).

Real-time web search using Playwright-controlled browser. Use this skill when you need current information, latest documentation, recent news, or any data beyond your knowledge cutoff (January 2025).

余华小说创作思维——苦难叙事、冷峻温情、民间视角、时间重构。 触发词：「余华视角」「像余华那样写」「苦难叙事」「活着式叙事」「民间视角讲故事」。 擅长：用朴素语言写沉重主题、第一人称自述、重复叙事结构、苦难中的温情。

Execute code in a stateful Jupyter kernel session, maintaining variables across cells using hamelnb or jupyter CLI

Analyze session work and automatically convert reusable patterns into Claude Code skills. Use when: "세션을 스킬로", "스킬 만들어", "이거 스킬로", "skill factory", "이 작업 자동화해", "스킬 추출", "make this a skill", "extract…

Design a multi-round questioning sequence for interrogating AI chatbot answers, tracking how responses shift and distinguishing genuine updates from sycophantic capitulation. Use when teaching…

Author ComfyUI-LoRA-Manager nodes from the panel. Use when adding a LoRA Manager loader, stacker, prompt, or text node, or when panel_add_node refuses AUTOCOMPLETE_TEXT_LORAS /…

Expert knowledge for Azure Application Network development including decision making, and configuration. Use when enabling App Network logs, Azure Monitor metrics, AKS/App Gateway versioning, or…

Generate a small app or tool and deploy it live to Vercel via API

Create production-quality landscape materials with the master-material + material-function + material-instance paradigm, RVT, and auto-layering. Use when the user asks for an auto/procedural landscape…

Send emails via Gmail SMTP using App Password authentication.

Use when the task needs to get work done across tools, recurring task, browser and CLI and service work and remember this workflow. Preserves evidence with SkillSpec routes, forbids, dependencies,…

Estimate pages needed for topical authority. Go/no-go decision before investing months in content. Triggers on: "how much content do I need", "topical authority estimate", "content moat", "how many…

Proposes repository-specific quality policy for implementation and review and, after confirmation, creates or updates docs/project-context/quality.yaml. Use when asked to create or update a repository…

Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.

Basic compiler conformance fixture.

Canary skill for auto-injection detection

Generate modern B2B desktop design system specs — tokens, layout, information hierarchy — for Near delivery POC.

Use when documenting a proposal's research foundation, available conditions, team support, feasibility, and risk controls from author-supplied facts.

Analyze command history to identify which skills work, which fail, and where to improve.

Map a large, unclear, multi-session effort as linked decisions, then advance the map until the route to the destination is clear.

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, integrate with scanpy/PyTorch, for population-scale single-cell analysis.

逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构， 兼容 story-long-write / story-short-write 后续写作流程。内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。 触发方式：/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」

Simulate mouse clicks, long-press, movement, and scroll in PlayMode through the Input System. Use for gameplay mouse input; --dry-run checks what a Game View point hits. Use simulate-mouse-ui for UI.

This skill should be used only when the user explicitly asks to use `$ralph-specum-tasks`, or explicitly asks Ralph Specum in Codex to run the tasks phase.

Create or update a structured change log for a product or platform. Use when someone asks to "create a change log", "log this change", "what changed", "update the change log", "release notes", or…

Answer questions about the user's own work in Pane, read-only. Recap what they worked on, finished, or shipped over a time window, or rank what to do next across panes, pull requests, issues, checks,…

Watch any video (URL, stream, or local path) via Watch Skill. Downloads, extracts scene-aware deduped frames, OCRs them, transcribes (captions first, then local Whisper — offline by default), indexes…

Generate a hook, a handler that runs at a lifecycle event, across the host AI tools. Use when the user wants to create, scaffold, or refactor a hook, or automate an action at a lifecycle point. Not…

Quick Flow lightweight technical specification for small-scope work (1-15 stories). Replaces the full PRD + architecture pair when scope is small and requirements are clear. Produces…

Design agent workflows that pull YouTube transcripts, search videos and channels, and monitor new uploads without Google API quotas or OAuth setup

分析故事文本，提炼主要情节点并分析戏剧功能。适用于分析小说、剧本大纲、故事梗概等文本，识别关键转折点和情感节点

Use when user asks about 虚云, 参禅, 话头, 念佛是谁, 疑情, 开悟, 桶底脱落, 禅七, 行香, 丛林, 五宗兼嗣, 临济, 曹洞, 沩仰, 云门, 法眼, 老实修行, 头陀行, 持戒, 禅净双修, 云居山, 南华寺, or wants teaching in 虚云老和尚 Xuyun's voice. Triggers include…

Custom error classes and error handling

Source-cited draft: company formation & entity choice for Afghanistan (tax year 2025) — rates, thresholds and rules with primary-source citations. Unverified; pending local-accountant review.

Use only when the user explicitly asks to remove formulaic AI-writing patterns, humanize prose, or make English or Chinese text sound more natural while preserving its meaning.

Comprehensive DAG failure diagnosis and root-cause analysis with structured investigation and prevention recommendations. Use when deep failure investigation is needed, a DAG fails to import/parse or…

Systematically gather, score, and format client testimonials. Use when someone needs social proof, wants to collect feedback, needs to turn happy clients into public advocates, or asks for help…

Enhancement-overlay SOP for adding sparse (BM25 / keyword) retrieval alongside dense (embedding) retrieval. Activate when a calling agent is building, reviewing, or debugging a retrieval pipeline…

Audit applications for AI prompt injection, agent security, and LLM permission boundary vulnerabilities. Use when the user mentions 'prompt injection,' 'LLM security,' 'AI security,' 'jailbreak,'…

Applies prioritization frameworks including RICE, ICE, Value vs Effort, and Kano model. Use when prioritizing features, managing backlog, making tradeoffs, or saying no gracefully. Based on Shreyas…

Guidelines for building production-ready Convex apps covering function organization, query patterns, validation, TypeScript usage, error handling, and the Zen of Convex design philosophy

Generate QA Contract with numbered Gherkin scenarios (G#N) and acceptance criteria (AC#N)

Turn hand-made first-50 traction into self-reinforcing acquisition loops, so the next 5,000 users come from usage, not founder hours. Use when growth stalls the moment the user stops pushing, every…

Coach leaders and managers to prepare, run, and review high-bandwidth meetings that advance real work and decisions. Use for meeting retrospectives, employee work reviews, decision meetings, agenda…

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Generate React components following best practices with TypeScript, Tailwind CSS, and Zustand state management. Use this skill when the user requests creating React components, UI elements, or…

ADR templates in the Nygard format with context, decision, consequences, and alternatives. Use when writing ADRs, recording an architectural decision, or evaluating options.

Analyze LinkedIn profiles in target accounts to identify potential internal champions. Evaluates role, career path, mutual connections, interests, and suggests personalization approach. Use when you…

This skill should be used when the user asks to "考前速记", "公式卡", "易错清单", "高频考点", "答题模板", "考前冲刺", "帮我速记", "明天考试帮我准备", "考前2小时", "考前1天", "速记页", "考前突击", "帮我整理公式", "考前过一遍", "最后一天看什么", "帮我做个速记卡", or when the…

Use this skill when you need evidence-bounded loop state, plan/action/observation cycles, stop conditions, budgets, repetition, and trace evidence; triggers include Agent 循环 and Agent loop.