AI Ml AI Skills

从思想性、艺术性、观赏性三维度评估影视剧本并打分。适用于剧本开发质量评估、修改方向确定、项目立项前审查

用 HTML/CSS 制作小红书、抖音的杂志图文，支持新闻资讯、人物生平、穿搭解析、旅行攻略、时序故事、观点解读与概念科普。按场景模板生成可编辑 HTML 与 PNG；穿搭优先使用用户照片，制作统一中性背景的多套组合与单套拆解组图。

Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe…

Use when user asks about 律宗, 南山律, 四分律, 戒律, 持戒, 受戒, 戒体, 戒法, 戒相, 止持, 作持, 持犯, 羯磨, 五戒, 八关斋, 忏悔, 理忏, 事忏, 行事钞, 威仪, or wants teaching in 道宣律师 Daoxuan's voice. Triggers include phrases like…

Design an industrial recommendation system or subsystem with explicit scale, latency, freshness, consistency, availability, privacy, cost, degradation, observability, and rollout constraints.

Product updates and announcements

Andorra non-resident income tax and cross-border working papers for individuals, companies and permanent establishments in tax year 2026. Covers residence and source tests, services, royalties,…

Comprehensive smart contract security audit framework with multi-expert analysis. Use for full audits of Ethereum / EVM Solidity and Vyper, Solana / SVM Anchor Rust, TON / FunC / Tact, or Sui / Move…

Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators…

产品经理 Agent — 产品规划、需求分析、用户研究、路线图制定、竞品分析

Headless self-verification gate a Foreman worker runs before it claims an issue is done. Re-run the real commands, read the actual output, and only then write the FOREMAN-SUMMARY — evidence before…

Validate content framing on joy-grievance spectrum.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ...

Ghost Security - Secrets and credentials scanner. Scans codebase for leaked API keys, tokens, passwords, and sensitive data. Detects hardcoded secrets and generates findings with severity and…

Structures difficult decisions using Annie Duke's probabilistic thinking and Ben Horowitz's hard decisions frameworks. Use when facing tough choices, applying expected value thinking, or reducing…

PostgreSQL-specific code review assistant focusing on PostgreSQL best practices, anti-patterns, and unique quality standards. Covers JSONB operations, array usage, custom types, schema design,…

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or…

Reach for this when a YouTube channel is the subject: a pasted @handle or channel URL, a creator's recent uploads, their full catalogue, or a search inside one channel. Also good for keeping an eye on…

用户用自然语言描述交易风格，自动创建加密货币交易Bot并运行本地回测。支持周期反思进化。可选连接外部平台进行验证和模拟交易。

生成可交互的 HTML 可视化组件 — 算法动画、数据图表、概念演示、交互式教程等。当用户需要交互式演示、动画解释、数据探索、UI 原型等场景时触发，直接输出 html 代码块，前端会在安全沙箱中渲染为可交互组件。

Use when planning link acquisition. Classifies the site's authority phase from site age and visible signals, then recommends phase-appropriate tactics from the bundled tactic playbook library. No…

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research

Capture patine (decision wisdom) at Gates when KO or challenge occurs

Directory and file enumeration using ffuf, gobuster, dirsearch, and feroxbuster. Use this skill when user needs to discover hidden directories, enumerate files, find backup files, or map application…

Show Honey's benchmark scoreboard — the committed quality and token results per task tier (code, user-facing, agent-to-agent) from bench/. Reports only the reproducible committed figures, never…

Rules for charts and visualization. Use when the user asks for charts, graphs, plots, or visual representations (line, bar, pie, timeseries).

Write a developer value proposition that is specific, provable, and free of puffery. Use when the messaging leans on "powerful," "better," "seamless," or "best-in-class," when claims have no proof, or…

Use when implementing any feature or bugfix, before writing implementation code

从学生上传的课件/大纲/老师勾的重点/真题，一键初始化并验证备考工作区：解析 PDF、DOCX、PPTX、 XLSX、常见独立图片与 txt/md，建立分章节 LLM Wiki、标准题库、结构化接管队列与进度状态；仅在 Python 确实无法运行时 明确降级为手动写盘。当工作区尚未建立、资料发生变化、或建库 readiness 被阻断时使用。

Use this skill first for any Jetpack Compose or Compose Multiplatform task: a new feature or screen, a change to existing code, a bug fix, a review, making code follow the kit, project or build setup,…

Assess a requirement change mid-project against the rules and past decisions, then update every affected artifact together.

Create and revise source-grounded research briefs, comparison reports and decision recommendations with matching HTML, Markdown and requested Word/PDF exports. Use for research and work deliverables…

Use when the user wants to release a new Zafiro version — drafting bilingual release notes, deciding the next version number, bumping app/build.gradle.kts, tagging, and publishing to GitHub (main…

Use for execution, debugging, verification, planning, and shipping when the user's Emulo working profile should guide the task. Do not use for design/UI/UX work, marketing or social writing, or Emulo…

Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think through options, choose an approach, evaluate…

Generate animated videos and motion graphics from natural language descriptions. Creates a standalone Vite + React project with Framer Motion scenes that auto-play in the browser. Use when the user…

公务员考试专项刷题与错题重练助手。当用户说“刷题”“来10道资料分析”“逐题做判断推理”“按某省真题练习”“从我上传的PDF/题库里抽题”“先别给答案”“限时练一组”“错题重做”“再来几道同类题”“针对薄弱点出题”时，应使用本…

当用户要做/研究一个东西、想提升某个技能、或觉得某个产出不够好想改进时使用。用「改良主义」先逼出一个最垃圾但能跑的原型，再引导他自己洞察缺陷、提出问题，提改良假说→实践检验→迭代，信奉「洞察缺陷 > 如何优化 > 最终答案」，并把每次改进的方法本身沉淀成方法论。触发场景：要做 X、研究 X、提升 X、X 做得不好想改进、怎么优化 X、不知从哪下手做。

Consolidate traces into the persistent wiki (WikiSkill).

Extract structured data from websites, scrape page content, and collect information across multiple pages. Trigger when the user asks to: extract data from a website, scrape a page, collect…

Identify and bypass binary mitigations (ASLR, PIE, NX/DEP, stack canary, RELRO, FORTIFY, CET, MTE) on ELF binaries. Activate after anti-debug is cleared and before binary-patcher when standard JE/JNE…

Strict anti-over-engineering enforcement. Activates on ANY code change to verify scope: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers…

ACTIVATE when developing long-term strategy, setting OKRs, creating vision statements, building SWOT analyses, designing strategic frameworks, defining company direction, planning multi-year…

就某个方案、决定或想法不留情面地盘问用户。当用户想对自己的思路做压力测试，或用了任何带 'grill' 的触发词时使用。

Guides use of the Qdrant Migration Tool CLI to move vectors, metadata, and sparse embeddings from another vector database into Qdrant. Use when someone asks 'how do I migrate from…

Generate professional financial charts in Mermaid, ASCII, or HTML/Chart.js — MA lines, histograms, candlestick, volume, RSI/MACD, and more for markdown reports

Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM. Use when the user wants a medium-length Hyperloom demo on the local AMD ROCm environment.

JeecgBoot Online表单（cgform）全生命周期管理——通过API自动创建/编辑数据库表和表单配置， 支持单表、主子表、树表，26种控件类型，以及JS/Java/SQL增强、权限配置、数据CRUD、积木报表集成。 只要用户意图涉及「Online表单」就必须使用本技能，包括但不限于：…

Machine learning and LLM engineering judgment, distilled from a stronger model - invoke when DECIDING whether/how to use ML or an LLM for a task (prompt vs RAG vs fine-tune vs classical); working with…

用于审阅AI科幻人物传记。作为题材包装层与兼容入口，负责补充可证据化秘密、事件性关系网与镜头抓手等题材裁判口径，并明确要求优先强制加载并使用 `通用-审阅人物传记`。关键词：AI科幻人物审阅、可证据化秘密、关系网、心理弧线。

Use when instrumenting product or web analytics — GA4/PostHog SDK wiring, event taxonomy, funnels, double-counted events, consent gating, PII scrubbing. NOT charting that data (that is dashboard), NOT…