115 件 ・ 関連度順
概要と使いどころ
Classifies raw pilot request → structured JSON {task_type, class, artifact, budget_estimate, confidence, routing_tag, resolution_path, schema_version, result_type, expected_result_kind, result_kind_resolution, hypothesis_relation}. Keyword-fast (<200ms) or Haiku fallback (<60s). Does NOT create WP or call executor.
日本語の概要は準備中です。原文の説明を表示しています。
Executes Ansible playbooks for server diagnostics and remediation using ansible-runner Python SDK. Supports inventory parsing, vault-encrypted credentials, and real-time task output streaming.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a LibAFL fuzzer needs an executor, observer, feedback, mutator, scheduler, or objective composed around a target. Not for remote, credential, publish, deploy, or irreversible changes.
日本語の概要は準備中です。原文の説明を表示しています。
Interactively gather parameters for `python -m cli.inference.text_generate`, generate a concrete text generation simulation command, explain assumptions, ask for execution confirmation, then run the command and summarize performance metrics. Use when the user wants to validate a specific model, hardware profile, batch/query size, prefill or decode scenario, TP/DP/EP/MOE parallel strategy, profiling database, chrome trace, empirical metrics export, or a best row produced by throughput_optimizer.
日本語の概要は準備中です。原文の説明を表示しています。
Interactively gather parameters for `python -m cli.inference.throughput_optimizer`, generate a deployment simulation command, explain assumptions, ask for execution confirmation, then run the simulation and summarize the best parallel strategy. Use when the user wants to evaluate a model on one or more hardware profiles, compare hardware targets, compare aggregation versus disaggregation versus PD ratio optimization, choose TP/EP/MOE-DP search ranges, or obtain recommended concurrency, throughput, TTFT, and TPOT results from throughput modeling.
日本語の概要は準備中です。原文の説明を表示しています。
The Arbor research-coordinator protocol: the OBSERVE -> IDEATE -> SELECT -> DISPATCH -> DECIDE cycle over a durable Idea Tree. Preloaded automatically on /auto-research sessions. The coordinator never edits code or runs commands — executors do that in isolated worktrees; the coordinator steers the tree with idea_tree / dispatch_experiments / merge_experiment.
日本語の概要は準備中です。原文の説明を表示しています。
Execute test suites with proper configuration, parallel execution, and detailed reporting. Use when running unit tests, integration tests, or full test suites.
日本語の概要は準備中です。原文の説明を表示しています。
Scaffold a new Forge subagent (planner/architect/executor/reviewer/debugger/memory-style). Use when adding anything to src/agents/.
日本語の概要は準備中です。原文の説明を表示しています。
Scaffold a new Forge subagent (planner/architect/executor/reviewer/debugger/memory-style).
日本語の概要は準備中です。原文の説明を表示しています。
Systematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts). Use when a task is stuck, looping, or emitting wrong tool calls.
日本語の概要は準備中です。原文の説明を表示しています。
Systematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts). Use when a task is stuck, looping, or producing wrong tool calls.
日本語の概要は準備中です。原文の説明を表示しています。
Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work should run in an observable background terminal instead of the Agent tool.
日本語の概要は準備中です。原文の説明を表示しています。
Multi-file hypothesis testing with keep/discard loop, compound baselines, and experiment logging
日本語の概要は準備中です。原文の説明を表示しています。
Policy-aware Safe portfolio rebalancing assistant for 31Third ExecutorModule.
日本語の概要は準備中です。原文の説明を表示しています。
Drafts a Chapter 11 Plan of Reorganization under 11 U.S.C. §§ 1121–1129 with claim classification, treatment provisions, distribution mechanics, executory contract determinations, and confirmation compliance. Use when preparing reorganization plans, restructuring debts, classifying claims, drafting Chapter 11 plans, or helping debtors emerge from bankruptcy. Trigger keywords: reorganization plan, Chapter 11, plan of reorganization, debt restructuring, cramdown, claim classification, confirmation order.
日本語の概要は準備中です。原文の説明を表示しています。
Routes Confluence Cloud tasks to the right mk:confluence-* leaf skill. Use for 'confluence', 'wiki page', 'spec page', or ambiguous intent. NOT an executor -- forks to a leaf skill.
日本語の概要は準備中です。原文の説明を表示しています。
Routing skill — recommends the correct mk:jira-* leaf for any Jira task. Triggers: 'jira', 'jira ticket', ambiguous Jira intent. NOT an executor — every actual operation forks via a leaf skill.
日本語の概要は準備中です。原文の説明を表示しています。
Routing skill — recommends the correct mk:jira-* leaf for any Jira task. Triggers: 'jira', 'jira ticket', ambiguous Jira intent. NOT an executor — every actual operation forks via a leaf skill.
日本語の概要は準備中です。原文の説明を表示しています。
Routing skill — recommends the correct mk:confluence-* leaf for any Confluence Cloud task. Triggers: 'confluence', 'wiki page', 'spec page', ambiguous Confluence intent. NOT an executor — every actual operation forks via a leaf skill.
日本語の概要は準備中です。原文の説明を表示しています。
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
日本語の概要は準備中です。原文の説明を表示しています。
Wave-based parallel scheduling for DAG execution. Manages execution order, resource allocation, and parallelism constraints. Activate on 'schedule dag', 'execution waves', 'parallel scheduling', 'task queue', 'resource allocation'. NOT for building DAGs (use dag-graph-builder) or actual execution (use dag-parallel-executor).
日本語の概要は準備中です。原文の説明を表示しています。
Combines and synthesizes outputs from parallel DAG branches. Handles merge strategies, conflict resolution, and result formatting. Activate on 'aggregate results', 'combine outputs', 'merge branches', 'synthesize results', 'fan-in'. NOT for execution (use dag-parallel-executor) or scheduling (use dag-task-scheduler).
日本語の概要は準備中です。原文の説明を表示しています。
Executes DAG waves with controlled parallelism using the Task tool. Manages concurrent agent spawning, resource limits, and execution coordination. Activate on 'execute dag', 'parallel execution', 'concurrent tasks', 'run workflow', 'spawn agents'. NOT for scheduling (use dag-task-scheduler) or building DAGs (use dag-graph-builder).
日本語の概要は準備中です。原文の説明を表示しています。
The intelligence layer of WinDAGs. Decomposes natural language tasks into Hierarchical Task DAGs (HTDAGs), matches subtasks to skills, executes waves in parallel, and dynamically expands nodes when complexity exceeds executor capability. Use for 'orchestrate', 'execute DAG', 'parallel agents', 'decompose task', 'coordinate skills'. NOT for single-skill tasks or simple linear workflows.
日本語の概要は準備中です。原文の説明を表示しています。