Start a named browser session and preserve its initial screen, page structure, and action history. Keep a trace of site exploration and establish a reusable session for later extraction, form filling, or browser testing.
Coordinate multiple AI agents for research, development, testing, and system analysis using Claude Flow. Choose how agents communicate, assign specialist roles, combine parallel and sequential tasks, and monitor progress through reporting and recovery workflows.
Restructure claude-flow v3 into focused modules using Domain-Driven Design, which groups code by responsibility. Define module boundaries, event communication, and plugin interfaces to support a modular architecture with independently testable business logic.
Coordinate changes across multiple GitHub repositories, align package versions, synchronize documentation, and run integration tests. The skill also guides shared repository templates and organizes AI agents to handle related development tasks.
Improve the MCP server that connects claude-flow v3 to tools. It guides connection reuse, faster tool lookup, request distribution, and communication changes, with monitoring to evaluate response times, errors, memory use, and cache performance.
Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.
Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.
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.
Coordinates multiple AI agents with agentic-flow to run tasks in parallel or through dependent stages. It covers team communication structures, shared memory, workload balancing, failure recovery, and performance monitoring for complex workflows.
Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.
Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.
Search document collections by meaning using embeddings, numerical representations of text. Compare text similarity, route queries among a few predefined patterns, and use a compressed search index when memory is limited.
Delegate complex work through a tree of Claude Code sub-agents. Each level uses its own working context and returns concise summaries, helping the coordinating agent manage research, verification, and synthesis without retaining every intermediate detail.
Analyze performance in Claude Flow swarms, groups of agents working together. Identify delays in communication, processing, memory, and networking, then generate reports and prioritized recommendations. Compare previous runs or apply available automatic optimizations.
Plan and implement a unified AgentDB memory backend for agents. Migrate SQLite and Markdown data, add HNSW indexing for similarity search, and support shared memory and SONA learning patterns while preserving compatibility with existing systems.
Coordinate software releases on GitHub, from version updates and release notes to testing, builds, deployment, and rollback. It describes workflows using multiple AI agents, including coordinated package releases and gradual deployments with monitoring.
Run and manage an agent in Anthropic's cloud for long or asynchronous tasks. Create a session with packages and tools, send work, inspect status and activity, continue with saved files and conversation, then terminate the session.
Review and strengthen security in claude-flow v3 by addressing dependency risks, password hashing, credential generation, input validation, file paths, and command execution. It also guides threat modeling and tests for security-critical code.
Build custom Claude Code skills with clear instructions, reusable templates, and organized supporting files. The skill guides you through YAML metadata, meaning the skill’s name and description, and separates essential steps from detailed references.
Review GitHub pull requests, or proposed code changes, with specialized AI agents covering security, performance, architecture, style, and accessibility. Organize findings, suggest fixes, and post feedback through configurable review workflows.
Modernize the claude-flow v3 command-line interface by splitting large command files, adding interactive prompts, connecting hooks that run on execution events, and organizing multiple commands into automated workflows with progress reporting.
Connect agent tasks in sequence, passing each result into the next step. Build custom workflows or use predefined pipelines for code analysis, refactoring, testing, and optimization, with execution progress, timing, and consolidated results.
Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.
Automate checks, code formatting, agent coordination, and session records around Claude Code operations. Uses hooks, actions triggered before or after work, to preserve context and connect development tasks with shared memory.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)