408 skills · sorted by relevance
Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.
Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.
Design custom laboratory parts as adjustable build123d models and export STEP, STL, and DXF fabrication files. Check mating dimensions against standards, test geometry, and visually review holders, mounts, microfluidic parts, and other research fixtures before fabrication.
Run diffusers generation pipelines from a terminal and save their outputs. Inspect accepted inputs without downloading model weights, apply LoRA adapters during generation, run remotely through HF Jobs, and inspect software and GPU environment details.
Connect cognee to additional databases and data sources through community packages. The skill covers installing and registering adapters, importing data through connectors, configuring monitoring, and developing extension packages with examples and tests.
Investigate and fix agent behavior in TradingAgentsCN by checking active database prompt templates, prompt assembly code, and output processing. Apply targeted changes and verify them with focused tests, template checks, and workflow logs.
Add email conversations to NanoClaw using Resend and Chat SDK. Install and test the email adapter, configure sending credentials and incoming email notifications, then connect your address to an agent for ongoing replies.
Connect NanoClaw directly to WhatsApp using the Baileys adapter and phone-based QR or pairing-code authentication. Supports conversations, file exchange, reactions, and approval commands, with different setup and response behavior for dedicated and personal numbers.
Connect NanoClaw to a real phone number for SMS and AI voice calls through Dial. The skill installs the channel adapter, guides account sign-in and phone pairing, and configures who can contact the agent.
Connect NanoClaw to Matrix rooms and direct messages through Chat SDK. The skill installs and registers the adapter, applies a compatibility patch, configures bot credentials, and checks the build and channel registration.
Uses OpenCLI to inspect and interact with Chrome pages, including logged-in websites. Agents can fill forms, extract page data, inspect captured network requests, take screenshots, and manage Chrome tabs, groups, and windows.
Create and render TanStack Table v9 tables in octane. The skill covers project configuration, column definitions, and rendering headers, rows, and cells, with guidance for sharing table features and reusable interface components.
Save web content as readable Markdown, a plain-text format for structured notes. Supports X posts, YouTube transcripts, Hacker News discussions, and general pages, with optional local downloads of images and videos.
Diagnose failures in GKE HorizontalPodAutoscaler (HPA), which adjusts Pod counts automatically. Investigate missing metrics, unexpected scaling behavior, and slow reactions, then receive proposed configuration fixes or commands for review before deployment.
Connect json-render interfaces to XState Store for state management. The skill shows how to adapt an atom, a container holding application state, so json-render reads and writes through it.
Helps connect json-render to a writable Jotai atom, a unit that holds application state. Covers adapter setup and sharing a Jotai store so json-render and React components read and update the same values.
Validate FASTQ sequencing files, run local quality checks, and interpret reports to decide whether trimming is needed. Optionally remove adapters or low-quality read ends while preserving original reads and their quality reports.
Guides migration of historical SWE-Marathon agent configurations to the shared Codex runtime. It preserves native tasks, verification rules, and scoring while outlining environment checks and restrictions on retired execution methods.
Develop and troubleshoot plugins that connect external memory services to Nexent. Define plugin settings, implement search and ingestion, map errors, test with simulated network responses, and verify deployment, authentication, and runtime monitoring.
Review and structure Rust backend changes using hexagonal architecture, which separates business rules from external interfaces. Check dependency direction, place authorization policy in domain services, and keep database operations and external clients behind defined interfaces.
Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.
Build or extend a custom Mirage VFS adapter for a user's API, database, object store, or application data. Use when connecting a new resource to Mirage, implementing a backend, or packaging a reusable adapter. For reading or editing data in an existing mount, use the filesystem workflow instead.
The English summary is being prepared. Showing the original description.
[omh] Lost track of agent sessions and worktrees: normalize Codex, Claude Code, Hermes, OpenCode, Cursor, MCP host, worktree, and wrapper session metadata into one drift-aware inventory. Use when the user says: harness-session-inventory, harness session inventory, session inventory, session adapter, session adapters, harness sessions, mcp inventory, mcp config inventory.
The English summary is being prepared. Showing the original description.
Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.
The English summary is being prepared. Showing the original description.