菜单
SkillsMP 已收集 Impertio-Studio/Open-Agents 中的 23 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 23 / 23 个已收集 Skill。
Bidirectioneel communicatiesysteem tussen meta-orchestrator en agents. Auto-loads bij agent spawning, inbox monitoring, statusupdates ontvangen, of feedback van agents. Triggert op: oa send, oa inbox, oa watch-inbox, agent done, blocked agent, feedback loop,…
原文语言：荷兰语
Applies OpenAEC Foundation brand to artifacts. WORKSPACE OVERRIDE — overrides global Impertio brand. Triggers on: branding, huisstijl, corporate identity, visual design, OpenAEC style.
原文语言：英语
Detects newly created or recently modified skills in ~/.claude/skills/ and auto-generates matching agent templates in the Open-Agents library. Use when a new skill has been created, when skills have been updated, or when the user says 'generate template for…
原文语言：英语
Deterministic reference for collecting agent output in Open-Agents. Use when Claude needs to retrieve completed agent results, understand output file locations, or choose between collect/watch/attach commands. Activates for: oa collect, output/result.md,…
原文语言：英语
CLI reference for managing running agents: stopping, cleaning, attaching, watching, listing. Use when checking agent state, stopping agents, or cleaning workspaces. Activates for: oa kill, oa clean, oa attach, oa watch, oa status, agent lifecycle.
原文语言：英语
Grows the agent library from successful oa runs. Use when reviewing completed agent output that follows a clear, repeatable pattern, or when the user mentions saving an agent as a template. Activates for: oa collect shows success, save as template, make…
原文语言：英语
Automated planner→workers→combiner pipeline for complex multi-step tasks. Use when a task requires planning then parallel execution then synthesis. Activates for: oa pipeline, pipeline, planner, combiner, multi-step task.
原文语言：英语
Exact CLI reference for spawning oa agents. Use when: spawning an agent via oa run, configuring agent flags, selecting --model, using --direct, managing agent names. Activates for: oa run, spawn agent, start agent, agent flags, --direct, --model.
原文语言：英语
Deterministic reference for the Open-Agents state file (agents.json). Use when Claude needs to inspect agent state, read AgentRecord fields, understand status values, or trace state transitions. Activates for: agents.json, agent state, status…
原文语言：英语
Inter-agent messaging and output collection in Open-Agents. Use when: sending messages between agents, checking inboxes, broadcasting announcements, or collecting completed agent output. Activates for: oa send, oa inbox, oa broadcast, oa collect, agent…
原文语言：英语
CLI reference for oa delegate — automatic orchestrator+workers spawning. Use when a task needs hierarchical decomposition with an orchestrator managing parallel workers. Activates for: oa delegate, delegate task, orchestrator, max-workers,…
原文语言：英语
4 reusable agent orchestration patterns: Research Swarm, Build Pipeline, Review Chain, Batch Processor. Use when choosing how to structure multi-agent work. Activates for: orchestration pattern, research swarm, build pipeline, review chain, batch processor.
原文语言：英语
5-element prompt structure for oa agent tasks (L-010). Use when writing or reviewing an oa run prompt. Activates for: agent prompt, prompt template, 5-element, oa run prompt, prompt structure.
原文语言：英语
Decide when and how to delegate tasks to oa agents. Use when evaluating task scope, choosing between inline work and agent spawning, or structuring a delegation plan. Activates for: delegate, spawn, auto-delegate, parallel agents, oa pipeline, delegation plan.
原文语言：英语
Model selection guide for oa agents: haiku/sonnet/opus by task type. Use when choosing --model for oa run or oa pipeline. Activates for: which model, claude/haiku, claude/sonnet, claude/opus, model selection, --model.
原文语言：英语
How to write explicit scope and quality rules for oa agent prompts. Use when formulating scope bullets, role statements, or inline rules for an agent. Activates for: agent scope, quality rules, role statement, explicit scope, bullet points.
原文语言：英语
Pattern for spawning a dedicated fix-agent when output quality checks fail. Use when an agent's output has errors, missing content, or format violations. Activates for: fix agent, quality failure, output error, spawn fixer, L-016, L-017.
原文语言：英语
Mandatory 5-check quality gate after every agent batch. Use when Claude needs to validate batch output before proceeding to the next phase. Activates for: batch complete, agent done, oa collect, validate output, quality check, all agents finished.
原文语言：英语
Automatically update core documentation after agent work completes. Use when Claude needs to spawn guardian agents to update LESSONS.md, ROADMAP.md, or DECISIONS.md after a batch or session. Activates for: batch done, session end, guardian, update docs,…
原文语言：英语
CLI reference for checkpoint and resume — crash recovery for long-running agents. Use when an agent crashes mid-task or you need to save progress for later resumption. Activates for: oa checkpoint, oa resume, crash recovery, checkpoint agent.
原文语言：英语
Explains oa agent workspace layout, --direct flag, and how agents write output. Use when understanding where agent files go or how to access agent output. Activates for: workspace, agent output, --direct, /tmp/oa-agent, result.md, project_root.
原文语言：英语
Coordinate multi-agent teams using staging patterns and shared result directories. Use when managing a group of workers writing to shared output, sequencing phases, or using oa team commands. Activates for: oa team, staging area, shared results, phase…
原文语言：英语
Access and interpret the oa web UI and Textual TUI. Use when opening the dashboard, checking agent status visually, reading logs, or using the bridge API. Activates for: oa dashboard, oa web, web UI, localhost:5174, bridge API.
原文语言：英语