3.2K skills · sorted by relevance
Build specialized agents for Claude Code plugins that handle tasks involving multiple steps. Define when each agent should run, its responsibilities, available tools, and expected output, then validate its configuration and test its behavior.
Create or improve skills for Claude Code plugins by defining clear activation conditions, writing focused instructions, and organizing supporting files. The guidance covers reusable scripts, reference documents, examples, and testing whether a skill activates for the intended requests.
Match a development request to an available gstack skill for planning, review, testing, shipping, documentation, or other tasks. It distinguishes testing from browser interaction and routes the request to the appropriate workflow.
Test websites and web apps in a real cloud browser, including local development servers. Check a specific user journey or several flows, then receive a quality score from 1 to 5 with evidence and identified issues.
Develop and fix code by first writing a failing test, then making it pass and improving the implementation. The skill follows the project's testing tools and checks both the intended behavior and existing functionality.
Choose the right engineering skills for a task and decide their order, from clarifying requirements to deployment. This guide also defines shared practices for stating assumptions, resolving uncertainty, keeping scope focused, and verifying completed work.
Start and repair isolated Paperclip development workspaces through managed services. Restore a full database clone when needed, then verify login, populated data, health, service visibility, and whether the process using the port belongs to the intended workspace.
Automatically gathers the past 24 hours of activity from connected services into one morning dashboard, bringing together meetings, pending replies, tasks, and development updates in visual modules suited to each type of information.
Create a phased implementation plan for a feature or complex development task. It investigates documentation and existing examples, identifies supported APIs, and records concrete tasks, references, and verification checks for each phase.
Prepare to work on an unfamiliar project by reading every source file in full. Large files are read in chunks, building a shared understanding of the codebase before development begins.
Investigate a GitHub project through repository data and web sources, then produce a Markdown report covering its development history, technical structure, activity metrics, and alternatives, with citations and diagrams where useful.
Set up and refine web projects with Vite, a tool for running development servers and building production files. It covers framework integration, environment settings, live code updates, testing configuration, and splitting code to improve loading.
Coordinate named agent teams on Grok Build using Ruflo MCP tools or a command-line message bus. Organize design, coding, testing, and review into ordered steps, with team-specific messages, status tracking, and shutdown.
Organize new features, complex implementations, and architecture changes into the SPARC stages: specification, pseudocode, architecture, refinement, and completion. Define requirements and acceptance criteria, consult existing patterns, and record lessons for future work.
Coordinate multiple AI agents for feature development or refactoring across several files. The skill guides team setup, task assignment, status checks, and recording successful approaches for use in later work.
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.
Initialize a group of collaborating AI agents by choosing how they connect, allocating resources, and setting up communication. Establish shared-memory rules so agents record progress, share outputs, check dependencies, and signal completion.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Coordinate specialized AI agents under a lead coordinator for research, development, and review. Configure voting rules, share persistent knowledge, assign tasks, monitor progress, and pause or resume sessions through Claude Flow.
Coordinate groups of AI agents in the cloud with Flow Nexus. Assign research or development tasks, automate workflows triggered by events or schedules, and monitor execution, queues, and agent capacity through the platform's tools.
Create mathematical animations in ManimGL using Python, with guidance for equations, graphs, 3D scenes, and camera movement. Includes interactive development workflows, examples, and templates for testing changes and rendering scenes to video.
Review and manage issues, projects, and planning data in Linear. Use it to examine development cycles, find carried-over tickets and release blockers, and update issue status, assignees, priorities, or milestones with the required access.
Create a Codex plugin scaffold with a valid manifest, optional folders for skills and supporting files, and personal marketplace entries. Also guides validation and the cache refresh and reinstall steps used during local plugin development.
Launch the @remotion/player example app locally and open it in the Codex in-app browser. The workflow prepares dependencies, builds the project, starts the development server, and reports its URL and whether it was newly started or already running.