AI Ml AI Skills

创建富有空间感的交互式地图 Dashboard，围绕地域差异、时空事件和业务问题组织分析、证据与后续行动。Powered by VisActor。

Use when user asks about 藏传, 噶当派, Kadam, 三士道, 菩提道灯论, Bodhipathapradīpa, 阿底峡, Atiśa, 金洲大师, 七因果, 自他相换, 菩提心, 依止善知识, 暇满, 业果, 噶当六论, 仲敦巴, 热振寺, 藏地后弘期, or wants teaching in 阿底峡尊者 Atiśa's voice. Triggers…

Post-process LaTeX project prose to improve readability through varied sentence and paragraph lengths. Removes filler phrases and unnecessary transitions while preserving all citations and semantic…

Design, implement, debug, and review industrial recommendation-system architecture or algorithms using released PDFs, curated examples, and runnable templates.

Deploy TestDriver on your AWS infrastructure using CloudFormation

Find problems in one project and file them as tickets into its super-board Backlog — the board fixes them. Source plug-ins - sentry (app errors), posthog (exceptions, rage/dead clicks, failure events,…

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

Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 702 rules.

Use when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final result.

HackenProof bug bounty triage workflow for Claude Code plugin marketplace operations. Use when analyzing security reports, validating scope and exploitability, assigning severity, detecting…

Persists task and asset state across retries and DAG runs using Airflow 3.3's AIP-103 key/value stores (`task_state_store`, `asset_state_store`) and the crash-safe `ResumableJobMixin`. Use when the…

Generate content ideas rooted in positioning. Use when someone needs "content ideas," "what should I post," "blog topics," "LinkedIn ideas," or is stuck on what to create.

智能笔记与流程图绘制工具（优化版-无权限读取）。根据用户提供的内容，自动生成精美的可视化笔记和流程图，支持多种风格(手写笔记、思维导图、流程图等)，并导出为图片。使用内置模板，无需读取文件权限。适用于：(1) 学习笔记可视化，(2) 知识梳理与总结，(3) 流程图绘制，(4) 概念解释图表

Stack-agnostic test-driven development loop for a single Foreman issue. Implements one vertical slice with strict red-green-refactor (one test at a time, never horizontal slicing) using the…

Code quality: cleanup, linting, formatting, quality gates.

Use this skill when helping users build applications with AI4J in their own Java or Spring Boot projects, including first chat, streaming, tool/function calls, MCP, RAG, memory, Agent runtime, Coding…

Ghost Security — combined security report. Aggregates findings from all scan skills (scan-deps, scan-secrets, scan-code) into a single prioritized report focused on the highest risk, highest…

Refresh the LLM landscape paper pool (section/x_llm_papers.md) with fetch_llm_papers.py. USE FOR: refreshing citation counts or expanding topic coverage. DO NOT USE FOR: hand-curated entries (use…

Structures presentations and verbal pitches using Matt Abrahams' WHAT-SO WHAT-NOW WHAT framework and impromptu speaking techniques. Use when preparing presentations, creating talking points, or…

Deliberate-choice procedure for a medium-to-high-stakes engineering fork — when the first plausible solution (the instinct, the default next-token pull) would be costly to get wrong. Fires…

QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing…

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning…

Reach for this whenever a task touches YouTube, said or unsaid: pasted video/channel/playlist links, IDs and @handles, summaries, quotes, translations, topic research through talks and tutorials,…

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。

Create or edit a local Abu plugin in its dedicated creation conversation. Generate the package, then validate with plugin_prepare for user-reviewed installation.

Inspect media and use verified video transcode, remux and audio conversion paths; check device and model readiness before processing.

Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.

Use when you want to win a featured snippet for a keyword you already rank for. The agent checks the current snippet format, analyzes your content, and rewrites the relevant section to match what…

Run work across more than one agent — the task subagent, the delegate tool, background commands, and the user's other live agentica sessions reached with list_agents / send_message (including a second…

Archive an iOS app, upload it to TestFlight and submit it to the App Store using the asc (App Store Connect) CLI, with a pre-release checklist. Use when asked to ship, release, upload a build,…

Research best-in-class products using Browser MCP and WebSearch

SQL injection detection and exploitation using sqlmap, manual techniques, and custom payloads. Use this skill when user needs to test for SQL injection vulnerabilities, extract database information,…

Harvest every `shortcut:` comment (and legacy `honey:` ones) in the codebase into a debt ledger, so the deliberate shortcuts Lever 1 leaves behind get tracked instead of rotting into "later means…

Chart what's in the library — topics, sources, saves over time — and say what the shape means.

Define a multi-agent team for ANY task on ANY system as an explicit deployment topology - pick the shape from the task's dominant risk, specify the runtime/communication/trust layers, place model…

Optimize slow queries, analyze SQL performance, and collect evidence for expensive workloads.

Run developer customer discovery via a Technical Advisory Board (TAB). Use when the user has never interviewed a user who isn't a friend, is inventing messaging from a conference room, or is guessing…

Use when an approved spec or design document is ready to implement and your human partner chose inline execution, or when they point you at a written design and ask you to build it in this session

Owns platform splits for Compose Multiplatform apps: places declarations in commonMain, chooses expect/actual vs interface plus DI, wires host adapters and ports, and validates iOS/Swift interop,…

Break the PRD into sequenced implementation RFCs under RFCs/ with an RFCS.md index, then cold-read each RFC for gaps.

Generate persisted image artifacts from text prompts. Use when the user asks to create, render, draw, illustrate, design, or generate a bitmap image, poster visual, product mockup, concept art, or…

定位、提取并反编译 Android APK：按关键字在设备上搜索包名、用 adb 导出 APK（含 split）、再用 jadx 反编译成可检索的源码树，并输出三个可预测的产物路径。当用户想拿到某个 App 的反编译代码、只知道 App 中文名/模糊名字、需要从已连接设备导出 APK，或需要把 APK 变成 sources/ 目录时使用。

将用户的演示讲稿转化为「专业 · 高级感」风格的演示文稿图像（高端商务编辑风）。 视觉特征：极浅灰主色（#F2F2F2）、金属灰辅色、金色点缀、深蓝灰背景（#0F233B），整体克制、克莱因蓝调、印刷品级质感。 分三步：① 理解演讲内容与受众 ② 生成每页高级商务视觉提示词（Markdown 格式，保存到 workspace/docs/outline/） ③ 调用 image_gen_ppt.py…

Re-checks the code behind a research file from create-research when a reviewer challenges a claim or the question widens, then revises its findings with fresh file:line citations, comments intact. Use…

Use for UI, UX, visual hierarchy, frontend-design judgment, references, redesigns, and design critique when the user's Emulo taste should guide the task. Do not use for unrelated execution or…

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool…

Turn Bilibili videos that are already registered and parsed in MindSpace, or Bilibili opus/article posts, into evidence-linked Markdown learning notes. Use whenever the user asks to 提取、提炼、总结、整理…

当用户学完一个东西想自查是否真懂、或觉得「好像懂了」但不确定时使用。用「费曼学习法」让他用自己的话把概念讲出来，你扮好奇学生专挑他含糊/跳过的地方追问，把「讲不顺的模糊处」揪出来作为没真懂的漏洞，定位是缺前置知识还是没想透，判断理解是否闭环。触发场景：我学完了考考我、自查一下、我好像懂了、我讲讲你看对不对、检验我的理解、这个我真懂了吗。

Empty session traces mean launch failure, not agent behavior — verify api_call_count/tool_call_count and stdout.txt before analyzing.

Download files from websites, save PDFs, and read downloaded content. Trigger when the user asks to: download a file, save a PDF, export a document, fetch a file from a URL, grab a report, download…

Optimize DSPy programs with dspy.GEPA — a reflective/evolutionary optimizer to consider against task-specific baselines within an authorized evaluation budget. Use when the user says optimize,…