678 个 · 按相关度排序
Explore how coordinating agents can pass relevant working state to workers through KV cache, a model's internal attention memory. Covers task-specific selection, runtime requirements, and comparisons of accuracy, token use, and processing overhead.
中文简介正在准备中。当前显示英语简介。
Design tools that agents can select and call correctly. Clarify descriptions, input rules, response formats, and recovery messages, then review overlapping tools and naming conventions using examples of successful and failed calls.
中文简介正在准备中。当前显示英语简介。
Test polly's coordination of coding agents using a scripted mock language model and live command-line tools. Check startup, task dispatch, safety rules, parallel delegation, and whether real agents make appropriate orchestration decisions.
中文简介正在准备中。当前显示英语简介。
Simulate a decision meeting with three to five AI roles with different expertise and personalities. Follow their debate and receive a meeting record covering conclusions, supporting arguments, risks, and suggested next actions.
中文简介正在准备中。当前显示英语简介。
Design an OpenRig agent team around a project goal. Create team and agent specifications, role guidance, and collaboration rules, then validate the setup and diagnose problems with startup instructions or agent coordination.
中文简介正在准备中。当前显示英语简介。
Design workflows where specialized AI agents share recurring product management tasks. Define each agent’s role, required information, handoffs, and human review points, then create monitoring and evaluation plans for the overall workflow.
中文简介正在准备中。当前显示英语简介。
Use a panel of three to five agents to decide between options or assess a plan. Independent initial opinions and anonymous deliberation lead to one verdict with confidence, preserved dissent, a validation test, and a next action.
中文简介正在准备中。当前显示英语简介。
Stress-test an idea, plan, or proposal through focused critique. The skill examines assumptions, opposing arguments, failure scenarios, attacks, or evidence, then uses your responses to refine the position and identify unresolved trade-offs and risky assumptions.
中文简介正在准备中。当前显示英语简介。
Build and deploy TypeScript agents on OpenServ that run custom tools, call APIs, or generate content. The skill covers capability definitions, platform registration, local development, task logging, and deployment, including platform-managed AI calls.
中文简介正在准备中。当前显示英语简介。
Clean up DeepChat's specification-driven development documents after implementation and validation. Review feature, issue, and architecture files, remove completed or obsolete material when evidence supports deletion, and preserve maintained specifications while checking references.
中文简介正在准备中。当前显示英语简介。
Find API patterns and examples for coding agents with ADK, the Agent Development Kit. Covers tools, state, callbacks, multi-agent coordination, and graph workflows, with Python and Go references plus guidance on studying existing implementations.
中文简介正在准备中。当前显示英语简介。
Supports development with code quality and security checks, change impact analysis, documentation templates, and coordination across multiple agents. It defines checkpoints for new modules and refactoring, plus roles and file ownership rules for parallel work.
中文简介正在准备中。当前显示英语简介。
Organize development work across multiple AI agents by defining roles, splitting tasks, sharing status, and resolving conflicts. Use file ownership rules and Codex agent tools to coordinate parallel changes without assigning simultaneous writers to one file.
中文简介正在准备中。当前显示英语简介。
Set up a consistent local environment for developing ClawTeam, then validate changes with focused tests and real agent workflows. Includes scripts for connecting other projects to local skills and guidance for investigating coordination bugs.
中文简介正在准备中。当前显示英语简介。
Check a Kiln branch or pull request through real browser interactions. Multiple agents test separate feature areas in isolated environments, then combine findings into a severity-ranked Markdown report with reproduction steps and expected versus actual behavior.
中文简介正在准备中。当前显示英语简介。
Set up Diverga through an interactive researcher profile wizard. It records your discipline, experience, statistical tools, database access, and collaboration preferences, then saves configuration that guides explanations, code suggestions, and database recommendations.
中文简介正在准备中。当前显示英语简介。
Review econometric code, proofs, data workflows, and outputs with multiple specialist agents. Assess identification—the assumptions that let data establish an effect—alongside estimation, numerical stability, and reproducibility, then consolidate findings into prioritized tasks.
中文简介正在准备中。当前显示英语简介。
Coordinate complex tasks across multiple agents through planning, execution, review, and revision. Agents save their work to local files and return status summaries, helping the main agent manage limited context while delivering the final result.
中文简介正在准备中。当前显示英语简介。
Manage code changes across multiple AI agents while recording operations and their outcomes. Use previous task histories to find similar attempts, inspect successful patterns, and obtain suggested steps for implementation, code review, deployment, or merging changes.
中文简介正在准备中。当前显示英语简介。
Build advanced AgentDB workflows with database synchronization, multiple databases, and search that combines meaning with attribute filters. Covers similarity measures, diverse search results, and operational patterns for distributed AI applications.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Create and run BB workflows that coordinate multiple worker agents. Organize independent tasks into parallel stages, verify outputs, pass structured results between steps, and inspect execution progress using validated JavaScript workflow scripts.
中文简介正在准备中。当前显示英语简介。
Review a git diff or selected files with parallel agents to find behavior regressions, security risks, reliability problems, and compatibility or test gaps. Receive filtered, evidence-backed findings and prioritized recommendations without changing files.
中文简介正在准备中。当前显示英语简介。
Investigate bugs, crashes, and intermittent failures without changing code. Multiple agents examine evidence from different angles, then produce ranked possible causes, confidence levels, and the smallest steps needed to confirm the diagnosis.
中文简介正在准备中。当前显示英语简介。