Results for “orchestrate”

Develop a broad research interest into evaluated project options. Specialized agents generate ideas, assess feasibility and competition, and draft abstracts and conclusions, helping researchers decide what to pursue, postpone, or drop and which assumption to test first.

• Turn a broad research interest into project ideas
• Compare the novelty and feasibility of research proposals
• Check competing work before choosing a direction

Revise formulaic academic prose through staged vocabulary and structure edits while checking that citations, statistics, and technical terms remain intact. Choose sections and editing intensity, compare changes, and review progress before accepting the revised manuscript.

• Revising formulaic wording in an academic draft
• Editing only the discussion and conclusion
• Checking that citations and statistics survive revisions

Run a five-stage finishing workflow for a drafted LaTeX paper: polish, revise, adapt its structure to a target journal, polish again, and verify references. Receive updated files, stage backups, a reference audit spreadsheet, and a final report.

• Running a complete finishing workflow on a first draft
• Adapting a paper's structure to a target journal
• Auditing references after manuscript revisions

Coordinate AI research from literature review to paper drafting. The skill alternates focused experiments with broader reviews of findings, tracks hypotheses and decisions, and uses specialist skills to carry out research tasks and prepare progress reports.

• Starting a research project from a question
• Testing and comparing multiple hypotheses
• Reassessing direction when experiments stall

Organize large coding tasks with Claude Fable directing lower-cost subagents. Delegate bounded research, edits, and tests, then have Fable verify evidence, resolve conflicting findings, integrate changes, and review the final result.

• Split a large codebase investigation across subagents
• Delegate independent, narrowly scoped code edits
• Distribute targeted tests and log summaries

Coordinate multiple AI agents with agentic-flow to run tasks in parallel or through ordered stages. Configure shared memory, team structure, workload distribution, retries, and task reassignment, then monitor how the group performs.

• Run API, interface, and test work in parallel
• Build a design-to-review workflow with ordered stages
• Share specifications and state across agents

Coordinate 15 agents implementing claude-flow v3 across security, core systems, integration, testing, performance, and release work. Provides role assignments, task dependencies, GitHub tracking examples, and a four-phase schedule spanning 14 weeks.

• Assign claude-flow v3 work across 15 agents
• Run tasks in parallel while respecting dependencies
• Track milestones and progress through GitHub issues

Research complex topics across multiple sources using available external AI providers, then combine the findings. Choose the depth, focus, and output format to receive a detailed report, concise summary, comparison table, or recommendations.

• Researching implementation patterns and APIs
• Comparing tools and alternative approaches
• Summarizing best practices from multiple sources

Compare technical choices through structured discussions among available AI providers. Use independent reviews or rounds of cross-critique to examine risks and trade-offs, then receive a synthesis of agreement, disagreement, recommended decisions, and concrete next steps.

• Comparing technology options before making a decision
• Reviewing authentication code for risks
• Examining database schema design from multiple perspectives

Gather advice from multiple language models assigned different roles, then combine their proposals and critiques into a recommendation. Set budget and depth limits while retaining disagreements, minority views, and risks for decisions or implementation planning.

• Comparing options before a decision
• Reviewing code or strategy from several perspectives
• Preparing an implementation plan with risks

Reviews code for common security weaknesses, authentication problems, exposed credentials, and unsafe configuration. It adjusts review depth to the changes and offers an adversarial workflow, where defensive and attacking perspectives guide fixes and subsequent verification.

• Checking changed code before committing
• Reviewing authentication and API access controls
• Finding credentials left in Git history

Finish a development branch by running tests and reviewing changes, then choose whether to create a pull request, merge locally, keep the branch, or discard it. Optional version and changelog updates support release preparation.

• Create a pull request after implementation is complete
• Merge a tested branch into the base branch locally
• Update the version and changelog before shipping

Run a build-and-evaluation pipeline from a natural-language specification. Generate scenarios, implement the project, test scenarios withheld during implementation, and report scores against a target with failures and suggested next steps.

• Generating a project from a natural-language specification
• Evaluating implementation with withheld scenarios
• Checking scores against a specification target

Coordinates multiple AI providers to research, define, implement, and validate development tasks. It supports parallel task decomposition, comparison of proposed solutions, cross-model critique, and quality checks that feed into combined reports and final deliverables.

• Sharing migration or refactoring work across AI agents
• Developing a feature from research through validation
• Comparing AI proposals for an architecture decision

Finalize a completed Claude Octopus project by checking readiness, running a multi-AI security audit, recording lessons, archiving project state, and creating a Git checkpoint. Produce a delivery summary and mark the project as shipped.

• Finalizing a completed project for delivery
• Running a required security audit before delivery
• Recording project lessons for future work

Assess how a pull request affects documentation, classify the required updates, and coordinate writing, technical verification, and editorial review. The result is an advisory comment with proposed changes for affected pages or document structure.

• Finding documentation gaps caused by code changes
• Drafting targeted corrections for existing documentation
• Planning new pages or table of contents changes

Prepare research data figures for journal submission with consistent layouts, error bars showing uncertainty, and accessible colors. Adjust figure dimensions, typography, resolution, and export formats using matplotlib, seaborn, and plotly.

• Preparing figures for journal submission
• Combining multiple plots into one consistent figure
• Improving color and grayscale readability

Coordinate large code refactors or rewrites across multiple agents. It organizes parallel analysis, assigns clear file ownership, schedules work around dependencies, and checks individual changes and their integration against agreed requirements.

• Refactoring code across many files
• Dividing implementation work among multiple agents
• Planning changes across dependent modules

Coordinate code migrations and repeated implementations through specialized agents. Use test-driven development, writing failing tests before code, then run builds, quality checks, reviews, and comparisons with a reference pattern to validate the resulting implementation.

• Port existing code from Python to TypeScript
• Create several adapters following an existing pattern
• Migrate a module to a new architecture

Understand how OPC coordinates multiple Claude Code processes through event hooks, skills, scripts, files, and a database. It explains child-agent startup, process tracking, output storage, and completion reporting, helping readers follow the system's architecture.

• Understanding the components of OPC
• Tracing how child agents start and finish
• Locating hook settings and agent output files

Orchestrates multi-agent forensic investigations on public GitHub repositories, coordinating parallel evidence collection, hypothesis formation, verification, and report generation.

The English summary is being prepared. Showing the original description.

Review tutti git diffs for project structure, layering, module ownership, and duplicate event-center infrastructure by planning focused architecture review tasks, then having the main agent orchestrate sub-agents for only the changed areas.

The English summary is being prepared. Showing the original description.

Entry point for an AI agent's ethos.md: a durable snapshot of what the agent is for, what it must not do, and what success looks like. Routes a request to explore and capture intent (ethos-explore), or write or edit the file (ethos-write), including renaming an Eval Author 0.1.0 ETHOS.md. Owns the standard every ethos sub-flow follows. Use when the user asks "help me write an ethos.md", "does my agent have an ethos.md?", "update my agent's ethos.md", or when you need to pick between the ethos sub-flows.

The English summary is being prepared. Showing the original description.

Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.

The English summary is being prepared. Showing the original description.