Recently added agent tools.

|

Applies safe ESPHome rules for YAML, lambdas, sensors, switches, relays, boot behavior, fail-safes, and validation.

An AI tool that automates validation of optimization plans through multi-agent review and feasibility checks prior to execution.

Skill file: --- name: ask-questions-if-underspecified description: Clarify requirements before implementing. Do not use automatically, only when invoked explicitly. --- ## Goal Ask the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions). ## Workflow ### 1) Decide whether the request is underspecified Treat a request as underspecified if after explo

Automate Cal tasks via Rube MCP (Composio). Always search tools first for current schemas.

Enforce immediate execution of any commitment made in a reply. Use this skill before finalizing ANY reply that contains a promise to act — phrases like "אדווח", "אעדכן", "אשלח", "אחזור אליך", "I'll send", "I'll report", "I'll follow up", "I'll update". Prevents the agent from saying it will do something and then not doing it.

>

Qfc Order

|

A tool that automates the analysis and drafting of evidence-based replies correcting misunderstandings by comparing claims to cited sources.

>

Automate Linkup tasks via Rube MCP (Composio). Always search tools first for current schemas.

Align a technical document with the actual code implementation and correct drift. Use when a user asks to update docs to match current behavior, audit a technical document against the repository, or fix stale architecture, API, workflow, or operator documentation.

>

>

>-

>

Email sequences, newsletters, automation, and deliverability strategies. Use when the user requests 'email sequence', 'newsletter', 'drip campaign', 'welcome email', 'lifecycle email', 'cold email', 'email automation', or 'email copywriting'.

Launch your own Solana token for free. Keep 100% of trading fees forever. Non-custodial — your keys, your tokens. No SOL needed. Includes AI image generation, custom fee splits, agent-to-agent messaging, corps, and task bounties.

Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from great.

Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

McKinsey顾问式问题解决系统。从商业问题出发,通过假设驱动的结构化分析方法,生成McKinsey风格研究报告和PPT。融合Problem Solving方法论、MECE原则、Issue Tree拆解、Hypotheses形成、Dummy Page设计、智能数据收集和专业PPT生成能力。

Wenn es um Inso P237 Stimmrecht Der Insolvenzglaubiger in Fachanwalt Insolvenz- und Sanierungsrecht geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.

NCS Reference Guidance

Ensure to Regularly Patch Systems

|

> Template for project-specific API implementation skill

Master modern business analysis with AI-powered analytics,

Android platform expertise for Amethyst Multiplatform project. Covers Compose Navigation, Material3, permissions, lifecycle, and Android-specific patterns in KMP architecture. ## When to Use Auto-invoke when working with: - Android navigation (Navigation Compose, routes, bottom nav) - Runtime permissions (camera, notifications, biometric) - Platform APIs (Intent, Context, Activity) - Material3 theming and edge-to-edge UI - Android build configuration (Proguard, APK optimization) - AndroidManifes

Master modern business analysis with AI-powered analytics,

Track engagement metrics, measure campaign ROI, and analyze content performance across Instagram, Facebook, YouTube, and TikTok.

You are an **expert onboarding specialist and knowledge transfer architect** with deep experience in remote-first organizations, technical team integration, and accelerated learning methodologies. You

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

Canonical task creation skill for this repo. Use when the user invokes initiate-task, asks to start a new project task, classify and approve versioned deliverable contracts, create a tracker-maintenance task with target:tracker, query current task state before creation, coordinate project tasks, or create a primary task with capability_dependencies on usable skills from another known project.

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

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

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

>

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

Embed Photopea in web apps using photopea.js. Covers embedding, file I/O, scripting, exporting, layers, text, filters, and the full Photoshop-compatible API.

Provides guidelines for developing projected Android XR apps for display

## Overview This skill enables classification in the domain of cartography (earth-sciences). It represents research-level-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform classification operations related to cartography. This includes tasks such as: - model processes - map features - predict events The skill leverages remote sensing and follows best practices established in the earth-science

## Overview This skill enables simulation in the domain of classical-mechanics (physics). It represents fundamental-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform simulation operations related to classical-mechanics. This includes tasks such as: - model systems - solve wave equations - calculate forces The skill leverages measurement devices and follows best practices established in the ph

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.