Results for “dispatch”

Use when acting as the orchestrator agent that drives Syntropic137 - running the dogfood loop, deciding what to dispatch next, landing agent PRs, deploying a beta, triaging failed executions, or keeping the scratchpad, paper cuts and retrospectives current. Trigger phrases include "orchestrator tick", "keep the loop running", "what should we dispatch next", "land these PRs", "why are PRs stacking up", "deploy the next beta", "pit stop", "the run failed, what now", "write the retro", "is the system helping", "scale quality", "learning loop for the orchestrator". Do NOT use for deciding whether one task belongs in a workspace or locally (see `dogfooding`), for turning one incident into an eval case (see `learning-loop`), for designing a workflow A/B experiment (see `workflow-experimentation`), or for release-branch and version-bump mechanics (see `devops`).

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

Use when: 'do work', 'dispatch builder', or team lead triggers automated task implementation. Governs end-to-end flow from dispatch through verification, fail handling, batch mode, and escalation.

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

大学業務文書 (広報原稿 / 研修教材 / 申請書 / 学生向け案内等) のドラフトを 読み取り、subagent dispatch で「AI 臭度」「業務文書適切性」「読者負荷」の 3 軸評価を返す。「この広報原稿、AI っぽくない？」「研修資料が硬すぎないか 気になる」「職員が書いたふうに仕上げたい」と問われた時に起動する。 mizchi-blog-style の評価ワークフローを大学業務文書向けに翻訳、職員 / 学生 / 学外読者の 3 ロールのいずれかで subagent がドラフトを読み、 冗長敬語 / 空虚強調 / 両論併記等を行番号付きで指摘する。反復改善は 呼び出し側判断、本 skill 自体はシングル実行。

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

attention notification watcher（承認待ち / 判断待ち / CI 失敗等を OS 通知 + 音で能動通知）を dispatcher ペインの右側に split で常駐起動する。`.state/attention.json` が未配置なら ja 既定テンプレートを `tools/templates/attention.example.json` から自動コピーする。 起動後のペイン id は `.state/attention_pane.json` に記録し、`/org-attention-stop` から参照する。 「attention 起動」「通知監視を始めて」「watcher を立てて」等で発動。 `/org-start` からの auto-start はしない（明示起動推奨ポリシー）。

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

open Issue を triage して「次の仕事候補（N 件 + 推奨 1 件）」を窓口が人間へ提示する。 候補はオペレーターが書いたゴール台帳（registry/goals/）の条項に当たるものだけで、条項順に並ぶ。 tools/work_discovery_scan.py を 1 回実行し、その候補 JSON を 設計書 §5.2 / §12 の人間可読フォーマットでレンダリングするところで停止する（propose-only）。 起動主体は窓口に限定。手動 / イベント起動のみ（常駐 /loop なし）。 「次の仕事候補出して」「triage して」「次なにやる？」や PR マージ後の proactive next-dispatch で窓口が手動起動する。

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

調査（Explore）・設計（Plan）・実装（general-purpose）・レビュー（review-* スキル群）のサブエージェントをオーケストレーションして開発タスクを遂行するスキル。依頼文からゴール（調査のみ / 設計まで / 実装まで / レビュー）を判定し、必要なフェーズだけ実行する。親は自分でコードを読み書きせず、分解・dispatch・検収・機械検証に徹する。Use when starting any non-trivial development task（複数ファイル・複数層にまたがる調査/設計/実装/レビュー）, when user says 'オーケストレート', 'orchestrate', '調べて', '設計して', '実装して', '調べて直して', or 'レビューして'.

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

ATM Captain 派工治理。觸發詞 派工 / 派工單 / dispatch / 開卡 / 派任務 / 派代理 / Phase 0 / Phase 1 / AAO / task card / condition review / 收口。負責 AI-Atomic-Framework (AAF) + 3KLife 雙 repo 治理：強制 Context Map 4 層、雙代理拆分（防外卡 mirror commit）、AAF 嚴格 2 commit、3KLife target_repo 嚴格 1 commit、7-8 段回報、禁止清單前置強化、Captain condition review。承載 0064 → 0093+ 累積的紀律教訓。

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

Delegating work down to subagents: briefs, report statuses, independent review. Use when writing an implementer or verifier brief, dispatching a subagent to build, fix, or verify work you own, or a subagent reports DONE, blocked, or concerns. NOT for campaign-scale doctrine (use campaign-pattern).

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

Assign independent bugs or test failures to separate agents that work at the same time. Define each agent’s scope and expected report, then check for conflicting changes and run the full test suite before integrating fixes.

• Investigating test failures with unrelated causes
• Fixing independent problems in separate subsystems
• Defining focused tasks for multiple agents

Check the full connection between a local agent API and a remote sandbox through a temporary tunnel. Run a task that needs no connected tools, verify its response, and restore the web app’s original API connection.

• Checking a local agent API from end to end
• Investigating tasks stuck after dispatch
• Verifying gateway callbacks reach the local API

Browse available specialist agents by domain, select up to five, and run them independently on the same task in parallel. Receive a combined report showing each agent’s findings, shared conclusions, conflicting recommendations, and suggested next steps.

• Browsing available specialist agents
• Selecting agents from different domains
• Reviewing a site for security and SEO before launch

Design local data storage in Swift using actors, which control concurrent access to shared data. Combine an in-memory cache with JSON file storage, implement save and lookup operations, and connect the repository to an observable ViewModel.

• Building local storage for an iOS or macOS app
• Designing local storage for an offline-first app
• Replacing lock-based synchronization with Swift actors

Set up recurring work in Claude Code by combining persistent memory, scheduled prompts, task queues, and optional computer control. The skill explains how to connect these components, including external scheduling for work that continues after a session closes.

• Reviewing pull requests at regular intervals
• Collecting and summarizing research findings daily
• Preparing meeting notes from saved context

Coordinate multiple Orca workers by assigning tasks, exchanging threaded messages, and waiting for results or escalations. Use task dependency graphs and decision gates to supervise work that needs ongoing coordination across agents.

• Splitting work across multiple Orca workers
• Coordinating tasks with dependencies
• Waiting for worker results or escalations

Scan declared MCP servers and tools for permission, policy, and dependency issues without executing them. Produce JSON or a Markdown table, and set a severity threshold that determines whether a CI check fails.

• Review declared MCP server and tool permissions
• Check policy and dependency issues in MCP configuration
• Fail CI when findings reach a chosen severity

Coordinate background tasks with specialized agents for research, optimization, audits, and more. Use execution history, quality scores, success rates, and latency to guide agent selection, track performance, and check benchmark compliance.

• Choose specialized agents for different task types
• Review agent quality, success rates, and latency
• Record execution feedback to inform future assignments

Refactor TypeScript code that handles several variants in multiple places using frozen classes and a Visitor interface, which defines a handler for each variant. This helps type checking expose missing handlers when new variants are added.

• Refactor a union type with repeated switch statements
• Design commands or nodes that need several kinds of processing
• Catch missing handlers when adding a new variant

Analyze custom virtual machines written in JavaScript by extracting instruction tables, examining constants, and capturing runtime state. Use the findings to reconstruct how obfuscated code executes, including custom runtimes used in risk-control engines.

• Identify a custom virtual machine in obfuscated JavaScript
• Extract and classify virtual machine instructions
• Trace exported functions and their execution flow

Find explanations, tutorials, configuration guidance, and code examples in official documentation for Microsoft technologies. Choose documentation sources for Azure, .NET, VS Code, GitHub, Aspire, and Agent Framework based on where the relevant material is published.

• Find official explanations and setup instructions
• Look up code examples for a specific language
• Research VS Code settings or extension APIs

Work through GitHub pull request feedback by classifying findings, fixing code, running repository checks, and posting replies. With suitable permissions, the skill repeats Copilot reviews until the latest code is reviewed and every thread has an agent response.

• Address outstanding Copilot review comments
• Run repeated reviews on a completed pull request
• Explain declined suggestions and hand off design decisions

Understand and modify SGLang's CI pipelines, including test stage order, start conditions, early stopping after failures, and workload splitting. Use the guide to add jobs and investigate failed, skipped, or cancelled checks.

• Add a test job to an SGLang CI stage
• Investigate failed or skipped CI checks
• Update test partitions and waiting job counts

Configure tools and skills for sub-agents before dispatching development tasks. Role presets cover implementation, planning, reviews, testing, and verification, with defined boundaries for what each agent should do and whether it may modify files.

• Setting tool permissions before spawning a sub-agent
• Separating implementation, planning, and review roles
• Configuring agents for review without file changes

Find the migration path for the removed OMX parallel execution command. This retirement notice directs users to replace `$ultrawork` with `$team`, which manages worker panes, shared task state, messaging, dispatch, and coordinated worker lifecycles.

• Check the replacement for a removed command
• Update old instructions to use `$team`
• Identify which feature manages parallel workers

Coordinates specialist agents in Claude Code to work from product requirements through design, implementation, testing, deployment, and operations. Includes task queues, saved progress, parallel reviews, and recovery workflows for managing extended development work.

• Turning product requirements into development tasks
• Coordinating implementation, testing, and reviews
• Resuming extended work from saved progress