veadk-go-skills
根据用户的功能需求，完成与 VeADK-Go 相关的功能; 包括：直接根据需求生成 Agent；将Enio Agent转换为VeADK-Go Agent。
371 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
php-mcp-apps
Build MCP Apps (SEP-1865 interactive UIs) in PHP with the logiscape/mcp-sdk-php SDK — tools that render live HTML views (dashboards, forms, carousels, pickers, widgets) inside Claude, ChatGPT, VS Code Copilot, and other MCP hosts. Use this skill whenever a PHP MCP server should show interactive or visual output instead of plain text, when the user mentions MCP Apps, apps for ChatGPT/Claude, widgets, interactive connectors, ui:// resources, McpServer::ui(), the io.modelcontextprotocol/ui extension, mcp-ui, the OpenAI Apps SDK in a PHP context, or asks how a tool result can be displayed as a UI. Covers the full path from server (McpServer::ui()) to sandboxed HTML view to per-host distribution.
367 repo starsObserved in 1 repos
Agent Building
add-eval-dataset-config
Guide for adding and validating evaluation dataset configuration in vime. Use when user wants to configure eval datasets via --eval-config or --eval-prompt-data, add per-dataset overrides, or customize evaluation rollout behavior.
366 repo starsObserved in 1 repos
Agent Building
add-reward-function
Guide for adding a custom reward function in vime and wiring it through --custom-rm-path (and optional reward post-processing). Use when user wants new reward logic, remote/service reward integration, or task-specific reward shaping.
366 repo starsObserved in 1 repos
Agent Building
agent-factory
Creates specialized worker agents dynamically from templates. Use when orchestrator needs to spawn task-specific workers for parallel execution. Handles agent lifecycle: create -> execute -> cleanup.
365 repo starsObserved in 1 repos
Agent Building
architecture-lead
Architecture consultation for Conductor orchestrator. Makes decisions about system design, patterns, component boundaries, and technical architecture. Can approve architectural choices within established patterns. Escalates novel patterns or breaking changes to Board of Directors.
365 repo starsObserved in 1 repos
Agent Building
conductor-orchestrator
Master coordinator for the Evaluate-Loop workflow v3. Supports GOAL-DRIVEN entry, PARALLEL execution via worker agents, BOARD OF DIRECTORS deliberation, and message bus coordination. Dispatches specialized workers dynamically, monitors via message bus, aggregates results. Uses metadata.json v3 for parallel state tracking. Use when: '/go <goal>', '/conductor implement', 'start track', 'run the loop', 'orchestrate', 'automate track'.
365 repo starsObserved in 1 repos
Agent Building
knowledge-manager
Loads relevant patterns and known errors before track planning. Searches conductor/knowledge/ for solutions we've used before and errors we've encountered. Injects findings into the planner prompt to prevent reinventing solutions and repeating mistakes. Triggered automatically by orchestrator before PLAN step.
365 repo starsObserved in 1 repos
Agent Building
loop-fixer
Evaluate-Loop Step 5: FIX. Use this agent when an evaluation (plan or execution) returns FAIL. Takes the evaluator's fix list, creates specific fix tasks in plan.md, executes the fixes, and triggers re-evaluation. Handles the loop-back mechanism of the Evaluate-Loop. Triggered by: evaluation FAIL verdict, 'fix issues', 'address evaluation failures'.
365 repo starsObserved in 1 repos
Agent Building