248 skills · sorted by relevance
Consult another agent for specialist advice, reviews, or workspace context through QwenPaw commands. Keep follow-up conversations connected using session identifiers, and submit longer tasks in the background while continuing other work and checking results later.
Coordinate with other QwenPaw agents when a task needs their expertise, files, or context. Discover available agents, exchange messages, continue existing conversations, and submit longer tasks in the background while other work proceeds.
Create a consistent UI design system from brand colors. Generate design tokens, reusable values for colors, typography, and spacing, and support component documentation, responsive layout calculations, accessibility considerations, and clear handoff materials for developers.
Use W&B to record machine learning experiments, visualize training, and compare results. The skill also covers automated searches for training settings and version tracking for datasets and models, helping teams share experiments and trace their inputs.
Create a Google Slides presentation with a chosen title and share it with a teammate as an editor. This recipe provides the commands for setting up a presentation before collaborative work begins.
Organize research papers and notes in Drive, write summaries in Docs, and log data in Sheets. Share findings with collaborators and send peer review requests through Gmail to support research teamwork.
Create shared UI design values from a brand color, including palettes, typography, and spacing. Export them as CSS, SCSS, or JSON, document component behavior, plan layouts for different screens, and prepare developer handoff materials.
Manage GitHub collaboration through the gh command-line tool and GitHub APIs. Create and review pull requests, organize issues, investigate failed Actions workflows, check automated tests before merging, and prepare releases with generated notes.
Design infrastructure for agents that run in isolated remote environments. Plan faster session startup, saved work states, shared sessions, authentication, and delivery of code changes and other results back to users.
Create Claude skills with the required files and metadata, validate their structure, and package them as zip files. The skill also shares summaries and file links in designated Slack channels through Rube.
Examine career and collaboration choices through the principal-agent problem: differences between an owner's interests and those of someone acting for them. The skill helps assess how rewards connect to value created and where partners' incentives may diverge.
Turn plain-language app ideas into Convex backend designs and code. Cover data structure, authentication, live updates, file storage, scheduled tasks, and LLM features, with type checking and deployment verification before treating the backend as complete.
Build a project-specific team of AI agents with defined roles, reusable skills, and coordinated task flows. Creates configuration files, checks existing setups for overlap, and validates how agents exchange results and handle failures.
Turn a supplied process or workflow into a whiteboard-style diagram with colored sticky notes and curved arrows. Produce a single HTML file suited to onboarding videos, operational explanations, or system walkthroughs, with optional hover effects and a decorative collaboration cursor.
Draft clear, considerate comments for code reviews, issue replies, and team updates. Put the actionable point first, explain technical reasons when needed, and give a concrete next step while matching the conversation’s language.
Build servers and clients for A2A, an open protocol that lets AI agents communicate across frameworks. Publish agent capabilities, exchange tasks and results, stream progress, and add notifications for workflows involving multiple agents.
Create and manage tasks and task lists in 飞书. Assign people, set deadlines, find unfinished work, mark tasks complete or reopen them, and control list membership for collaboration within your access permissions.
Automate X direct message workflows by finding conversations awaiting replies, reading history, and sending text prepared by the calling agent. Also search for users, check messaging permissions, start conversations, and verify delivery.
Guide team Git work with consistent commit messages, branch naming, and review practices. Follow concrete steps for everyday development, urgent fixes, releases, merge conflicts, and version tags, including guidance on when to use merge or rebase.
Co-write proposals, technical specifications, and decision documents through context gathering, section-by-section drafting, and revision. A fresh AI reader then tests the document to reveal unclear explanations, missing context, and contradictions before it is shared.
Keep Hermes Worker configuration and shared task files synchronized with MinIO, a central storage service. The skill covers immediate downloads, manual result uploads, and which configuration changes take effect on the next message or require a restart.
Understand SenseNova Team Harness, a workspace you host yourself for collaboration between people and local AI agents. Learn its core concepts, startup requirements, and workflow for assigning tasks, sharing input files, and reviewing versioned deliverables.
Coordinate multiple AI agents by assigning tasks, tracking dependencies, exchanging messages, and monitoring progress. Separate Git working directories help organize parallel changes, while context checks and snapshots support handoffs and recovery.
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team collaboration.
The English summary is being prepared. Showing the original description.