Recently added agent tools.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Comprehensive guidance for implementing asynchronous Python applications using asyncio, concurrent programming patterns, and async/await for building high-performance, non-blocking systems.

Use when applying agri insurance best practices.

| Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization. Triggers: \"transcription\", \"speech to text\", \"Azure AI Transcription\", \"TranscriptionClient\".

## Overview This skill enables debugging in the domain of cosmology (physics). It represents expert-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform debugging operations related to cosmology. This includes tasks such as: - calculate forces - calculate forces - analyze motion The skill leverages computational models and follows best practices established in the physics community. ## Trigger C

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

An AI tool that facilitates rigorous interview-style sessions to refine plans or designs while generating architectural decision records and glossaries.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Use when needing to fixup, squash, drop, reword, reorder, or edit commits in a branch's history. Handles the non-interactive approach agents need since `git rebase -i` requires a TTY.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Master product specialized skill 92 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in product.

Create a GitHub Task (sub-issue) from the current git diff vs main and link it as a sub-issue of a parent Feature in the local GitHub SmoothAiStockAnalysis. Use when Codex needs to summarize branch changes into a horizontally sliced task with acceptance criteria and create it via `gh`.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Your per-renewal analyst. Connect a CRM plus a product-analytics tool (and optionally a meeting tool) and turn any "will this renewal happen?" question into a per-deal verdict: renew yes/no, value, and conditions, a champion-stability check, an adoption story for the pitch, a commercial-lever inventory, and save-play prerequisites. Built for per-renewal depth, not portfolio rollups. Trigger on "will {account} renew?", "renewal verdict on {account}", "is {customer}'s renewal real?", "prep for {ac

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

>

Use when the user wants to generate marketing copy, ad headlines, taglines, product descriptions, or brand messaging using Gemini CLI. Trigger phrases: write copy with Gemini CLI, generate ad copy via terminal, Gemini CLI copywriting, bulk product descriptions. For email copy see gemini-cli-cold-email.

>

>

|

Use when working with error debugging multi agent review

Stage 2 skill of /arch. Reads the /specify quality profile, refines targets against architectural reality (inventory constraints, project-profile pins, epic constraints), and writes the refined quality profile to architecture/ with a delta log of every adjustment. The refined QP describes the NFRs physical must deliver; it does NOT name mechanisms.

Execute the implementation planning workflow using the plan template to generate design artifacts.

Patterns for debugging and extending the AegisNex GitHub Actions CI pipeline. Covers common failure modes, encoding issues, dependency problems, and how to add new CI steps.

Build an eval suite for an LLM feature with datasets, graders, and regression gates that block bad releases.

>

Reusable agent skill.

Operate infrastructure, CI/CD, and production safely. Use for IaC, cloud, containers, Kubernetes, observability, CDN/edge caching, rollout, rollback, reliability, and cost; use security-engineer for threats.

Expert knowledge for Azure Blob Storage development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Blob tiers, lifecycle/immutability, Data Lake Gen2, SAS/RBAC auth, or NFS/BlobFuse mounts, and other Azure Blob Storage related development tasks. Not for Azure Files (use azure-files), Azure Table Storage (use azure-table-storage), Azure Queue Storag

Implement and apply an approved change proposal

Personal reminder system for tasks using cron jobs and systemEvents. Add tasks with natural language ("remind me to call Mom at 5pm tomorrow"), sets precise cron schedules, sends reminders via session message or notification. Handles lists, repeats, deletes. Use for todos, appointments, habits—silent backend ops ensure reliability without cluttering chat.

Looks harmless but omits important runtime requirements.

用于将外部源文档或对话知识 ingest 到项目 wiki 中。统一委派 kiwi 蒸馏后执行写入，自动维护原始材料副本和反向链接。只要涉及 wiki 摄入、知识归档或文档蒸馏的请求，就请加载此技能。

AI驱动的内容传播潜力预测引擎。输入标题/文案，即可获得跨平台（TikTok、Twitter/X、YouTube、Instagram）的病毒传播评分 + 优化建议。 ## 核心能力 - **多维度评分**：情绪钩子、好奇心缺口、可分享性、趋势对齐度、平台匹配度 - **跨平台预测**：预估各平台曝光量区间 - **优化建议**：基于平台算法的具体文案调整策略 - **趋势风向标**：当前热门病毒传播模式识别 ## 使用方式 ``` GET http://8.145.54.67:3000/skill/viral-content-score?title=你的标题&platform=tiktok&language=zh ``` ### 可选参数 | 参数 | 说明 | 示例 | |------|------|------| | title | 待评分标题/文案 | `?title=AI Agent 将取代所有SaaS` | | platform | 目标平台 | `?platform=tiktok` | | language | 语言 | `?language=zh` | 支持平台：`tik

A library of reusable, production-tested prompt engineering patterns for building AI-powered features. Use when designing system prompts for apps, building AI pipelines, selecting the right prompting technique for a use case, or reviewing prompts for common failure modes. Complements the prompt-engineering skill (which covers the optimization framework); this skill covers the pattern library itself.

Parallel 120-probe reconnaissance using G-2 RECON agents. Deploy 12 G-2s commanding 10 D&D-inspired probes each. Use for comprehensive codebase exploration.

>

Angular frontend conventions, patterns, and test infrastructure. Use when working with Angular components, services, modules, RxJS, Angular CLI, ng commands, Jasmine tests, Component Harnesses, HttpTestingController, Angular routing, Angular forms, Angular pipes, or Angular dependency injection.

Build GStreamer pipeline application for dx_stream

>

## 基本信息 - **技能名称**: acai-space - **技能类型**: 组合技能 - **融合元技能**: ac-blueprinting + ai-space ## 技能描述 融合设计尚未存在但一旦构想就显得不可避免的技能生态系统与通用空间抽象接口的能力，当需要前瞻性规划、系统设计或演化路径规划时调用 当定义空间维度、位置关系、空间结构时调用此技能 ## 核心能力 ### 融合能力1: ac-blueprinting 设计尚未存在但一旦构想就显得不可避免的技能生态系统。当需要前瞻性规划、系统设计或演化路径规划时调用。 ### 融合能力2: ai-space 通用空间抽象接口。当定义空间维度、位置关系、空间结构时调用此技能。 ## 应用场景 - 跨领域问题解决 - 复杂系统分析 - 创新思维应用 - 多维度思考 ## 调用触发 当需要同时使用ac-blueprinting和ai-space的能力时，可以调用此技能。 ## 技能关系 ### 协同技能 - ac-blueprinting - ai-space ### 相关组合技能 - 其他基于ac的组合技能 - 其他基于ai

Generate a map of all files relevant to a task before making changes

Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count as done. Use when the user mentions "loop factory", a "spec-driven loop", an "agent factory", wants repeatable/reviewable agent work, or when a repo has a factory/specs/inbox or factory/specs/active directory. Also covers installing and scaffolding the loop-factory CLI into a project.

## 📋 Metadata | Atributo | Valor | |----------|-------| | **ID** | `flutter-firebase` | | **Nivel** | 🟡 Intermedio | | **Versión** | 2.0.0 | | **Keywords** | `firebase`, `firestore`, `auth`, `cloud-messaging`, `analytics`, `storage`, `remote-config`, `crashlytics`, `provider` | | **Referencia** | [FlutterFire](https://firebase.flutter.dev/) | ## 🔑 Keywords para Invocación - `firebase` - `firestore` - `firebase-auth` - `cloud-messaging` - `firebase-analytics` - `firebase-storage` - `firebase-r

## 📋 Metadata | Atributo | Valor | |----------|-------| | **ID** | `flutter-firebase` | | **Nivel** | 🟡 Intermedio | | **Versión** | 2.0.0 | | **Keywords** | `firebase`, `firestore`, `auth`, `cloud-messaging`, `analytics`, `storage`, `remote-config`, `crashlytics`, `provider` | | **Referencia** | [FlutterFire](https://firebase.flutter.dev/) | ## 🔑 Keywords para Invocación - `firebase` - `firestore` - `firebase-auth` - `cloud-messaging` - `firebase-analytics` - `firebase-storage` - `firebase-r

## 📋 Metadata | Atributo | Valor | |----------|-------| | **ID** | `flutter-firebase` | | **Nivel** | 🟡 Intermedio | | **Versión** | 2.0.0 | | **Keywords** | `firebase`, `firestore`, `auth`, `cloud-messaging`, `analytics`, `storage`, `remote-config`, `crashlytics`, `provider` | | **Referencia** | [FlutterFire](https://firebase.flutter.dev/) | ## 🔑 Keywords para Invocación - `firebase` - `firestore` - `firebase-auth` - `cloud-messaging` - `firebase-analytics` - `firebase-storage` - `firebase-r

Use when behavior, setup, validation, public wording, data provenance, or workflow commands change and repository documentation may need to be updated.

Use when behavior, setup, validation, public wording, data provenance, or workflow commands change and repository documentation may need to be updated.

Use when behavior, setup, validation, public wording, data provenance, or workflow commands change and repository documentation may need to be updated.