Skill: Agnost AI Integration
by Agnost AI
Walks a coding agent through wiring Agnost AI conversation analytics into a Python or TypeScript app — inspecting existing OpenTelemetry first and only adding an SDK when the traces are not usable.
ElevenLabs' official skill for generating speech from text with the ElevenLabs API, SDKs and CLI: model choice, voices, voice settings, language codes, audio effects, streaming and errors.
ElevenLabs Text to Speech is the official ElevenLabs agent skill for turning text into speech, from the elevenlabs/skills repository. It helps a coding agent generate voiceovers, add speech to an app or build voice features with the ElevenLabs API, and requires internet access and an ELEVENLABS_API_KEY; if the key is missing it tells the agent to run the ElevenLabs CLI's onboarding first.
Quick starts show the same request in Python, JavaScript (with the stream bridged to a file in Node) and the CLI, where elevenlabs say plays text immediately and the text-to-speech convert command sets parameters directly. A model table compares Eleven v4 (the default in its examples, 90+ languages), v4 Turbo for real-time use, the Flash v2.5 and v2 models for the lowest latency and cost, and the previous Multilingual v2 and v3 models, with notes on what v4 does not support, such as SSML and style or speed settings.
Further sections cover choosing voices (pre-made voices work on free plans, while Voice Library voices return a 402 there), voice settings such as stability and similarity boost, enforcing a language with ISO 639-1 codes, text normalisation of numbers and dates, audio effects (filter presets, distance, reverb environments, background noise beds and panning), request stitching to avoid pops, pauses and tone shifts where long audio is split across requests, output formats, streaming, error handling and tracking costs. MIT licensed.
The instructions your agent loads, as published by ElevenLabs.
by Agnost AI
Walks a coding agent through wiring Agnost AI conversation analytics into a Python or TypeScript app — inspecting existing OpenTelemetry first and only adding an SDK when the traces are not usable.
by Anthropic
Anthropic's guide for building high-quality MCP servers end to end — research, tool design, implementation in TypeScript or Python, testing, and a 10-question evaluation suite.
Official AWS skill for authoring, deploying and debugging CDK stacks — construct patterns, bootstrap, drift, resource import and the CloudFormation errors that trap people.
Astral's official skill that teaches coding agents to use uv for Python scripts, projects, tools and type checking, and to migrate pip, pipx and pyenv commands to their uv equivalents.