「tpo」の検索結果

从固定点（commit、branch、tag 或 merge-base）开始，沿两条轴线审查变更——规范（代码是否遵循仓库文档化的编码规范？）和规格（代码是否与原始 issue/PRD 的要求一致？）。两条审查线在并行子 agent 中运行，并以并排方式报告结果。当用户想审查一个分支、PR、进行中的变更，或要求"从 X 开始审查"时使用。

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。

询问哪个技能或流程适合你的情况。本仓库内技能的路由器。

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 running throughput/latency (serving speed) benchmarks against an already-running model server. Uses sgl_jax.bench_serving to sweep batch-size/concurrency and measure throughput and latency, producing summary.csv and per-point bs_<N>/result.jsonl. Speed only — accuracy/eval belongs to model-accuracy-benchmark. Triggers on throughput, latency, bench_serving, batch-size sweep, tok/s, TTFT, TPOT — not accuracy/eval.

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 seeing errors about better-sqlite3 native module, NODE_MODULE_VERSION mismatch, "was compiled against a different Node.js version", or similar native binding errors.

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。

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

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。

Break a PRD into independently-workable issues and write each as a local markdown file in issues/. Use when the user wants to turn a PRD into a list of concrete tasks.

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。

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

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 a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.

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。

Generate a PRD from the client brief and write it as a local markdown file in issues/. Use when the user wants to turn a client request into a structured PRD.

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。

Authentication coercion (PetitPotam MS-EFSR, PrinterBug MS-RPRN, DFSCoerce MS-DFSNM) chained into NTLM relay (impacket ntlmrelayx) toward LDAP, AD CS web enrollment (ESC8), or SMB. Use when SMB signing is not enforced or LDAP channel binding is missing, and you want to force a privileged machine account to authenticate to your relay and turn that into RBCD, a DCSync-capable ACL grant, or a certificate. Includes the exact Coercer/ntlmrelayx commands, requirements, detection, and remediation.

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。

Think and work like an expert Horticulturist. Use when a task calls for Horticulturist judgment. Reasons from plant-environment-cultural coupling, source-sink carbon partitioning, and chilling/photoperiod thresholds through rootstock-scion matching, DLI/VPD and substrate EC/pH targets, Dynamic/Utah chill models, and CA/MA postharvest setpoints while treating blossom-end rot, bitter pit, tipburn, storage scald, and MRL/PHI breaches as first-class failure modes.

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。

Think and work like an expert Catalysis Engineer. Use when a task calls for Catalysis Engineer judgment. Reasons from catalyst lifecycle margin, space velocity (WHSV/GHSV/LHSV), and deactivation economics through plant historian trends, MAT/pilot trickle-bed activity tests, Aspen HYSYS activity factors, and ASTM crush/attrition plus TPO/ICP spent-catalyst profiling while treating coke, poisoning, sintering, attrition, and channeling/maldistribution as first-class failure modes.

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 devopsdays event that is already listed on the site has to be cancelled or postponed, and its pages need to stop advertising dates, registration, and sponsorship.

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 this skill when authoring reusable, idempotent MATLAB scripts that build System Composer architecture models via the architecture-modeling API — `systemcomposer.createModel`, `addComponent`, `addPort`, `setInterface`, `connect(srcPort, dstPort)`, interface dictionaries (.sldd) with `addInterface`/`addElement`, profiles/stereotypes with `Profile.createProfile` and `addStereotype`, or `systemcomposer.allocation.createAllocationSet`. Also trigger when debugging these APIs (connections that don't appear, interfaces that don't resolve, profile save errors, `createAllocationSet` signature-mismatch errors). Do NOT trigger for ad-hoc structural edits to an already-built model (adding one SubSystem, rewiring a port) — use `building-simulink-models` with `model_edit` for that.

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。

Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.

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。

Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.

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。

arkcli 模型查询与基础模型服务激活能力：列出、搜索、获取火山公共基础模型详情，以及用户明确要求的开通/激活模型服务（`arkcli models activate`）；Volc 还支持 TTFT/TPOT 性能排名、延迟趋势和输入长度对比。激活已有基础模型服务不等于部署/创建 Endpoint，不得转成 `+deploy`。优先使用产品命令 `arkcli models ...`，而不是直接调用 Raw API。反触发：用户的最终目标是创建 / 部署 Endpoint 时，本 skill 承担有界的只读候选查询，owning skill 由创建路径确定：普通产品创建走 arkcli-deploy；用户显式要求 raw CRUD / CI / 无守卫的 `infer endpoint create` 走 arkcli-infer-endpoint。候选首先执行 `models search ... --size 10 --format json`；成功完整结果直接复用，空结果与捕获缺损按 reference 有界恢复，并把实时返回的 `name` 与非空 `primary_version` 组合成可直接传给 `--model` 的完整 ID，不能拉全量清单、把裸家族名当可部署 ID，或逐候选追加 `models get`。注意：查询/管理账号下自传或精调的自定义模型（`cm-xxx`）走 arkcli-custommodel。

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 writing tests, improving coverage, or deciding what to test in this CLI

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。

Generator economic dispatch and cost optimization for power systems. Use when minimizing generation costs, computing optimal generator setpoints, calculating operating margins, or working with generator cost functions.

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 touching Unity per-frame code, spawning, physics queries, UI updates or rendering setup - profiling with numbers, zero-GC hot paths (caching, NonAlloc queries, no LINQ/closures/boxing, TMP SetText), ObjectPool, allocation tests, Burst/Jobs for bulk math, and rendering/physics settings that cost frames.

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。

Reviews Remix v2 code for v1-shape meta exports (BREAKING in v2), cookie security gaps (httpOnly, secure, secrets rotation), auth gates in wrong layer, and missing CSRF. Use when reviewing meta/SEO, session, auth, or form-mutation code in a Remix v2 codebase.

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。

Spark Studio's team-culture Relic — a 5-person AI product startup that existed 2022–2025: roast first then work, hotpot on Fridays, used Feishu while cursing Feishu daily, requirements always changing but versions always shipping. 星火工作室（Spark Studio）的团队文化 Relic。一个 2022-2025 年间存在过的 5 人 AI 产品创业团队： 先吐槽再开工，周五点海底捞，用飞书但天天骂飞书，需求总在变但总能把版本扛上线。

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 diagnosing NPU + PyTorch or LLM Serving Host CPU affinity, NUMA locality, cgroup/cpuset constraints, CPU range conflicts, PyTorch/runtime threading, DataLoader, tokenizer, scheduler, vLLM-Ascend, SGLang, TTFT, TPOT, tokens/s, QPS, or multi-rank/multi-worker CPU binding issues.

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。