718 skills · sorted by relevance
Define success criteria before AI coding, then assess new capabilities and check that existing behavior still works using code, rules, models, or human review. Track repeated-attempt success metrics and reports to compare prompt changes, agent changes, or model versions.
Turn an unclear feature idea into a structured specification with goals, boundaries, and testable success criteria. Split broader requests into independent modules when needed, then move through planning, task breakdown, and implementation with human review.
Use image generation through the Venice.ai API and explore available styles. This skill helps an agent identify the relevant image generation capabilities when planning an image creation task.
Prepare media assets required by an existing OD Next plan. Reuse verified capabilities and suitable assets, acquire files, measure dimensions, and retrieve background job results while preserving required content, licensing constraints, and quality conditions.
Work on advanced RuView sensing with signals from multiple WiFi nodes. Explore position estimation, three-dimensional occupancy reconstruction, changes in movement patterns over time, and defenses against suspicious signals, with guidance on implementation modules and validation.
Investigate a Homecore capability by tracing relevant source files, tests, and accepted architecture decisions. Check documented status and limitations before proposing code, while keeping implementation presence separate from deployment compatibility or claims of Home Assistant parity.
Find installable agent skills for a task you want help with. Search using relevant keywords, explain matching options with installation commands and detail links, and install a chosen skill through the provided script when requested.
Build MCP servers, which let Claude call external tools and read data through a shared protocol. Follow Python or TypeScript examples to implement tools, connect services, configure Claude, and test server behavior.
Design and build AI agents for business, research, operations, or creative work. Define essential actions and knowledge, start with a simple execution loop, and add progress tracking or separate child agents as needs emerge.
Query OmniRoute through A2A, a protocol for communication between agents. Get provider and model recommendations, check remaining quotas, find providers with required features, estimate request costs, and review system health.
Connect agents and automated workflows to VoiceStudio to generate speech with saved or designed voices, transcribe recordings, create subtitles, and manage dubbing or narration. It uses the running backend and checks available models and capabilities.
Create or improve Claude skills that package specialized knowledge, repeatable workflows, and tool instructions. The guide covers planning SKILL.md and supporting files, generating a starter folder, validating the structure, and packaging the result as a distributable ZIP.
Help design quorum management for distributed systems, where multiple nodes must agree on decisions. Covers adapting participation thresholds and voting weights to network conditions, performance, and failures, plus membership changes, validation, and rollback.
Organize complex work across specialized agents with claude-flow. Start and stop agents, check their status and metrics, and manage groups by role, using shared memory to coordinate tasks such as development, reviews, and security checks.
Compare ruflo and HAL systems for running the GAIA benchmark, an AI evaluation. Examine differences in code execution, browsing, file handling, memory, and model selection to prioritize improvements by expected impact and effort.
Create a custom offline page and configure a service worker, a browser background script, to cache it in advance. Show it when page navigation fails, and review resource dependencies and fallback conditions.
Update main OpenSpec specifications from a change's delta specs, which describe specification changes. The skill merges requirement additions, edits, removals, and renames while preserving unrelated content, validates the results, and leaves the change active.
Review a reusable Agent Skill package before implementation. Validate its identity fields, separate instructions from external capabilities and execution timing, and receive a validation report with a minimal set of building blocks and reasons for each choice.
Discover what a paired phone or wearable currently supports, then run the requested device, app, camera, media, or smart-home action. Check each device's published capabilities and permissions, and report the actual outcome or any execution errors.
Prepare and privately submit feedback to the Muse team after user approval. It covers missing connections, feature requests, recurring failures, and praise, and helps users view or withdraw reports they have already filed.
Answer questions about an agent's capabilities, memory, connected services, rules, and previous work by inspecting its actual files and workspace. Distinguish observed facts from inference and explain when evidence is missing, outdated, or incomplete.
Start video and animation work by matching the request and project state to an appropriate HyperFrames workflow. It coordinates new productions, edits, captions, previews, validation, and rendering, using HTML files to define the video.
Review which actions are available in each of four Remotion Studio modes. Use these distinctions when implementing or checking interface controls, so actions that depend on a server are hidden or disabled where the mode cannot support them.
Extract text and its page coordinates locally from PDFs, Office documents, and images. Use OCR to read scans, export structured JSON or Markdown, process document folders, and render pages as PNG images for agents that analyze visual content.