203 skills · sorted by relevance
Generate sound effects and ambient audio from written descriptions using ElevenLabs. Create cinematic impacts, app notification sounds, or background textures, with controls for duration, seamless looping, and how closely the sound follows the description.
Build Claude applications using guidance for the official Anthropic SDK. Choose an integration approach, implement streaming and tool use, and follow workflows for model migration, prompt audits, evaluation, and cost optimization.
Support product planning for Auri, a voice assistant combining Alexa and Claude. Covers product vision, the Vitoria Neural persona, AWS architecture, service tiers, a four-phase roadmap, market launch planning, success metrics, and competitive analysis.
Restructure raw article text stored in gbrain into summaries, exact quotes, key insights, and links to related pages. Preserve the original text and connect the article's significance to projects and interests already recorded in gbrain.
Turn a development goal into a focused ralph-loop command through conversation and codebase research. Define context, setup steps, ordered tasks, and testing criteria, then produce a complete command ready to copy.
Query Prometheus metrics through Grafana and manage dashboards as JSON files. Use it to investigate current values and trends, add or adjust panels, and preview dashboard updates before applying them.
Create and run tests for interactive command-line tools and terminal interfaces using @microsoft/tui-test. Simulate keyboard input, check visible text, and compare screen snapshots in a separate terminal environment for each test.
Develop a product or side-project idea through guided questions and premise checks. Startup discussions examine evidence of demand, while builder discussions explore possibilities and scope, producing a design document before implementation begins.
Set up and run Happy components locally, including its CLI, server, mobile app, and desktop app. The guide covers building, testing, checking logs, and separating development data using pnpm, the project's package management tool.
Automate real browser tasks to test websites, complete forms, and collect page information. The skill guides agents through identifying clickable elements, interacting with pages, comparing page states, and saving screenshots or PDFs.
Trace application behavior and explain data structures using compact text tree diagrams. The diagrams connect user actions to real functions, data types, state changes, and the components that render again as a result.
Guide releases of Happy's CLI, mobile app, web app, and server. Choose versions and release channels, follow build and test checks, publish through the designated services, and verify the resulting packages or app updates.
Search past coding sessions across Claude Code, Codex, and Cursor to recover earlier attempts, failed approaches, decisions, and findings. It filters history by topic and time, then summarizes technical details relevant to the question.
Send and reply to Lark messages, search conversation history, and retrieve attachments through an agent. The skill also supports creating group chats, managing members, and organizing important messages and conversations with bookmarks and pinned chats.
Create a short launch video from the current website or app project using Hyperframes. The skill reads the code, plans scenes, adds music and optional narration, checks and renders the video, and prepares a poster and share copy.
Turn a project directory or website URL into a short launch video using its real interface and visual assets. Create the storyboard, motion, music, sound effects, poster image, and share copy with tools available on the machine.
Review GitHub pull requests with specialized agents that check for clear bugs and violations of project instructions in CLAUDE.md. Validate bug findings before posting focused comments on the affected lines, with fix suggestions where appropriate.
Upgrade the chat app’s fast or good model slot across Rust backend code and the frontend. Updates model definitions, selection logic, generated types, and display names, then checks compilation and consistency.
Collect papers across research databases, turn research questions into targeted search queries, remove duplicate records, and extract available PDF links. Useful for preparing systematic literature reviews, with database selection and access checks before retrieval.
Draft and check a systematic literature review using PRISMA 2020, a reporting guideline for transparent reviews. Organize methods and findings into a Word manuscript, create a study selection flow diagram, and format references in APA 7th Edition style.
Organize multi-step work into tasks, track dependencies and status, and save progress checkpoints. Record completed work, unfinished steps, and decision context so an agent can review the saved state and continue in a later session.
Turn a multi-step feature into an implementation plan that another engineer can follow without prior context. The plan includes exact file paths, complete code, test commands, expected results, and small, verifiable steps.
Turn an agreed plan into small work tickets, each covering a complete, testable feature across the necessary layers. Identify dependencies and available starting points so people or future agent sessions can pick up clearly bounded work.
Turn a technical choice into a structured debate between different AI model families. Assign explicit positions, launch the discussion, and summarize agreement, disagreement, and a recommendation supported by the strongest argument that survives the debate.