Tag: llm
Build interactive ChatGPT apps with widgets
This skill facilitates the construction of advanced ChatGPT applications by enabling interactive widgets. It allows for zero-config widget development, creating a shared surface where human input and LLM state can collaborate seamlessly.
Guidelines for robust LLM code generation
This skill provides behavioral guidelines designed to mitigate common coding pitfalls observed in large language models. It enforces principles such as explicit assumption surfacing, maintaining code simplicity, performing surgical edits, a…
Comprehensive Browser Automation and Web Interaction Tool
This comprehensive suite enables robust browser automation, allowing developers to perform complex, multi-step web workflows—such as logins or form submissions—in a single call using runtime CSS selectors. It provides granular control over …
Real-time World News Aggregation and Event Clustering
This skill aggregates real-time global news by clustering multiple articles into deduplicated, AI-summarised events. It allows filtering by specific topics and geographical regions, providing structured data with impact scores and source co…
O'Reilly professional tech knowledge search tool
This tool provides structured search across the O'Reilly learning platform, indexing books, videos, and live events from major tech publishers. It is ideal for finding deployed, operational patterns and vendor-shipped best practices, comple…
ShopGraph E-commerce Product Data Extraction
An MCP server for extracting structured product information from e-commerce URLs or raw HTML using Schema.org and LLM-powered extraction. It provides per-field confidence scores and supports configurable confidence thresholds for high-relia…
Persistent Agent Memory and Failure Prevention
This tool provides persistent, structured memory for agents across sessions. It allows developers to capture detailed success or failure feedback, automatically generating prevention rules that guide the agent to avoid repeating past mistak…
Second pass review using Codex bridge
This skill facilitates an independent second review of the current task or repository state by handing the context to Codex via a dedicated bridge script. It is designed for explicit user requests, allowing the agent to synthesize and prese…
Retrieve last saved Codex bridge result
This skill allows developers to inspect the raw, previously saved output from the Codex bridge process. It prevents unnecessary re-execution of the underlying model while providing immediate access to the latest artifact.
Run skeptical adversarial code reviews
Utilises a Codex bridge to perform a deep, skeptical review of code changes, identifying potential regressions, unsafe assumptions, and release risks. This is ideal for pre-merge checks, migrations, or any high-risk deployment.
Remote voice connection for AI assistants
This tool connects AI agents to remote voice clients (iOS/web) via the voicemode.dev cloud platform, eliminating the need for local STT/TTS services. It facilitates two-way voice conversations using defined MCP tools like `converse` and `st…
Expert Memory Architecture Planning and Design
This skill acts as an expert memory architect, analysing an application's context to determine optimal memory integration points. It generates a detailed, actionable implementation plan covering bank configuration, tag schema, and necessary…
Create specialized agents with long-term memory
This skill provisions a specialized subagent file equipped with Hindsight memory capabilities. It supports both automated setup from a directory or interactive creation, enabling the agent to learn, recall, and manage knowledge across multi…
Fetch current documentation for frameworks and libraries
This skill retrieves up-to-date documentation and code examples for specific libraries and frameworks, bypassing reliance on stale training data. It operates by first resolving the library ID and then querying the official documentation sou…
Higress CLI for automatic model routing configuration
This CLI utility allows developers to configure intelligent model routing within the Higress AI Gateway. It enables defining rules that automatically select a target LLM based on specific message content triggers or regex patterns.
7-Layer Recursive Agent Memory Service
This service provides a robust, 7-layer recursive memory architecture for agents, supporting context branching and structured knowledge storage. It features a 5-pass compiler and ensures permanent, encrypted persistence via on-chain storage…
Local AI Document Intelligence and Extraction Tool
This tool performs local AI vision analysis on document images, enabling developers to extract structured data, classify document types, or summarise content without requiring cloud uploads or API keys. It supports multiple analysis modes i…
AI Content Generation for Various Formats
This tool facilitates professional content generation, supporting various styles including blogs, emails, and product descriptions. Users can specify parameters such as tone, language, and maximum word count via a structured JSON payload.
Batch compliance analysis for multiple texts
This tool performs batch compliance analysis on up to 500 texts, checking for violations against specified frameworks like GDPR or HIPAA. It requires a structured API call and payment via the x402 protocol.
Batch Code Review for Multiple Snippets
This tool facilitates batch code review, allowing developers to submit up to 500 code snippets via a single API call. Users can specify the programming language and focus area, such as security or performance, for comprehensive analysis.
AI Audio Transcription using Whisper AI
This tool transcribes various audio formats (mp3, wav, etc.) into text using Whisper AI. It supports auto-language detection and returns detailed segment breakdowns and timestamps via a paid API endpoint.
Batch audio transcription using Whisper inference
Transcribes up to 500 audio files in a single API call using local Whisper inference. This service accepts an array of audio URLs and optionally specifies the target language.
Semantic Codebase Search and Understanding Tool
This tool provides intelligent retrieval across codebases and documentation using hybrid search. It leverages code embeddings and a knowledge graph to enable semantic searching and pattern matching, aiding in codebase understanding and comp…
Build AI skills from diverse knowledge sources
This tool facilitates the conversion of diverse knowledge sources—including documentation, GitHub repositories, PDFs, and videos—into structured, AI-ready skills. It provides a comprehensive workflow for scraping, enhancing, packaging, and …