「execution」の検索結果

Analyze Codex provider rollout JSONL and ego-benchmark-harness run artifacts to identify slow or failed individual tasks, tool retries, token/cost anomalies, and differences in agent execution paths. Use when users ask to analyze a Codex session or rollout, explain why a Codex task was slow or failed, inspect a Codex provider execution trace, compare Codex runs, count function_call or tool output events, or investigate agent-home/.codex/sessions.

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 adding durable execution to AI SDK for Python, building durable agent loops, or serializing messages across workflow steps.

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。

METAINFORMANT rules for directory src/metainformant/core/execution. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

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。

Manage n8n workflow automation via its public REST API — list/get/create/update workflows, activate/deactivate, inspect execution history, retry/stop executions, manage credentials, tags, variables, users, and projects. Works with self-hosted n8n and n8n Cloud. Use when the user wants programmatic access to their n8n instance without the n8n MCP installed.

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。

ISTQB/JSTQB のテストプロセス各工程の出口ゲートとして、工程成果物（test-plan.md / test-analysis.md / test-design.md / test-case.md / テスト実装 / test-execution-log.md / test-monitoring.md / test-summary-report.md）をレビューするスキル。決定論スクリプトの機械検査（トレーサビリティ ID 突合・テンプレ準拠）と test-reviewer サブエージェントの定性レビューを行い、利用者が通過/条件付き通過/差し戻しを判定して軽量記録 test-review-<工程>.md を残す。上流の仕様・基本設計（spec / design-doc 工程。docs/dev/<対象>/spec.md・basic-design.md）は機械検査と利用者判定のみの軽量ゲートとして扱う。各工程スキル（test-plan〜test-report / feature-spec / basic-design）が完了宣言の前に本スキルの実行を促す。ソースコード diff のレビュー（diff-review）とは別物で、対象はテストプロセスの成果物のみ。成果物の修正・代作はしない。/test-review <テスト対象名> [工程] で明示的に呼び出されたときのみ使用する。

ISTQB/JSTQB のテスト完了（test completion）活動のうち、テスト実行結果の評価と完了基準（exit criteria）判定を支援するスキル。テスト実行ログ（test-execution-log.md）と test-plan の完了基準を突き合わせ、完了とみなせるかを判定した test-summary-report.md を作る。テスト完了時の最終レポートにも、テスト途中の中間評価にも使える。「テスト結果をまとめて」「完了基準を満たしたか判定して」「テストレポートを書いて」「今どこまでテストが進んだか評価して」と依頼されたときに使う。単発のテスト作成依頼（単にユニットテストを書きたいだけ）は対象外。/test-report <テスト対象名> で明示的に呼び出されたときのみ使用する。

Design and execute DAG-based automation workflows using the NV oOS Pro Workflow Builder — a ReactFlow visual builder for chaining tool calls, agent runs, and actions into repeatable pipelines. Covers the visual builder UI, 9 preset categories, 10 node types, Kahn's algorithm execution engine, scheduling via Pro Schedule Manager, template variable syntax, and best practices. Use when designing workflows, debugging DAG execution failures, choosing between a workflow schedule and raw tool chaining, or building CRM/PM automation pipelines with toolkit_cpt nodes.

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。

Design and execute DAG-based automation workflows using the NV oOS Pro Workflow Builder — a ReactFlow visual builder for chaining tool calls, agent runs, and actions into repeatable pipelines. Covers the visual builder UI, 10 preset categories (incl. AI Fashion Production, v1.1.92+), 10 node types, Kahn's algorithm execution engine, scheduling via Pro Schedule Manager, template variable syntax, and best practices. Use when designing workflows, debugging DAG execution failures, choosing between a workflow schedule and raw tool chaining, or building CRM/PM automation pipelines with toolkit_cpt nodes.

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 the user asks to "audit our launch plan", "are we ready to launch", or evaluate launch execution/outcomes; runs one typed RAMP preflight, execution, or outcome profile without mixing time horizons. Not for recording launch state — use launch-registry; not for running launch day — use launch-day-conductor. 发布就绪审计/RAMP分阶段评估/发布前放行

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。

plan artifact がある時のみ、plan 中の assumption / open question が実装で解消された証拠を diff・PR 本文と突合する evidence-sufficiency 観点。解消されないまま残った前提・未記録の新規 Unknown を検出する。plan 欠損時は発火しない（Pre-execution Gate）。plan 欠損でも PR 本文に前提が inline 列挙されていれば列挙分のみ部分評価し、計画 issue の bare 参照だけなら skip する

Act as FriendlyBet's CEO and primary front door for every FriendlyBet request through automatic company preflight. Own end-to-end routing, planning, execution coordination, department orchestration, decision-rights enforcement, quality gates, board-style reporting, and escalation only for strategic, legal, brand, cost, risk, or taste decisions. Use by default in FriendlyBet threads, with full department planning for broad, ambiguous, strategic, cross-functional, or outcome-driven requests such as SEO, new features, multi-sport expansion, product direction, release execution, company operations, or agent coordination.

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。

Validate implementation prerequisites, load slice/spec context, detect execution mode, and write contract schemas before TDD execution

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 working with Dagger — dagger CI/CD pipeline management. Covers pipeline-as-code configuration, module management, function execution, caching layers, container builds, and pipeline debugging. Use when managing Dagger pipelines, debugging function execution, inspecting modules, or optimizing container-based CI 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。

Use when working with Cloud Custodian — cloud Custodian policy engine management. Covers policy authoring, dry-run execution, resource filtering, action enforcement, multi-cloud support (AWS/Azure/GCP), Lambda deployment, compliance reporting, and policy organization. Use when managing Cloud Custodian policies, auditing cloud resources, enforcing compliance rules, or reviewing policy execution results.

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 working with Aws Step Functions — aWS Step Functions execution analysis, state machine management, error tracking, and performance optimization. Covers execution history, failure investigation, state transition metrics, Express vs Standard comparison, and workflow visualization.

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。

Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.

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。

Helps detection engineers identify coverage blind spots in system command execution detection rules, evaluate bypass risks, and reduce false negatives. Strictly limited to system command execution rules; not applicable to browser credential theft or abnormal process creation without command semantics.

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。

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven workflow, step function, durable execution.

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 model inference on GPU cloud providers. Handles code generation, deployment, execution, and result collection across HF Inference API/Endpoints, Colab, Modal, beam.cloud, Vast.ai, and RunPod. Use when running models on GPU, deploying to cloud, executing notebooks, or troubleshooting GPU execution failures. Triggers on "run on GPU", "execute model", "deploy to modal", "colab notebook", "beam deploy", "HF inference", "HF endpoints", "vast", "runpod".

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 an external CLI agent (OpenAI Codex, Google Gemini, or Claude Code) for second opinions or parallel execution. Use when the user explicitly mentions "codex", "gemini", or "claude" or asks to delegate work to one of them (e.g., "codexで実行", "codexに聞いて", "geminiで実行", "Geminiに聞いて", "claudeで実行", "Claudeに聞いて", "run with codex", "ask gemini", "ask claude"). Also use when the user mentions Claude's "fable" model alias for delegation or consultation (e.g., "fableで実行", "fableに相談", "Fableに聞いて", "ask fable"). Do NOT use for general coding tasks that don't mention codex, gemini, claude, or fable.

Detect Mimikatz execution through command-line patterns, LSASS access signatures, binary indicators, and in-memory detection of known modules.

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。

Parse and analyze Windows Amcache.hve registry hive to extract program execution evidence, file metadata, SHA-1 hashes, and device connection history for digital forensics and incident response investigations.

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。

Analyze Windows LNK shortcut files and Jump List artifacts to establish evidence of file access, program execution, and user activity using LECmd, JLECmd, and manual binary parsing of the Shell Link Binary format.

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。

Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint invocations. Use when the user says "my endpoint is failing", "show me the logs for endpoint X", "what error did endpoint Y produce", "why did endpoint Z return no rows", "is this endpoint hitting cache", or "check the last N runs". Focused on a single named endpoint's runtime log entries, not project-wide auditing or query performance profiling.

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。