「seam」の検索結果

Forge Modular's generator, patch checker, module pack and Forge-worktree seam — the traps that make green results untrue

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。

Building and shipping a Forge app (Modular, Instrument, MIDI, FX, and the sequencer work to come) as a signed installer somebody else can actually use. Covers the seam between the Forge and Pulp repos, what a green signal does and does not prove, shipping the runtime rather than only the binary, and the wiring gaps that make a finished feature behave like a missing one.

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。

Compact current session context into a handoff document for seamless continuation in a new session. Use when context window is exhausted, switching machines, handing work to another agent, or ending a long session mid-task.

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。

Unity level design-to-code translation. Trigger & event architecture, encounter design contracts, checkpoint & respawn, cinematic & scripted sequences, environmental storytelling hooks, level streaming & loading seams. DESIGN INTENT format: INTENT/WRONG/RIGHT/SCAFFOLD/ DESIGN HOOK. Based on Unity 6.3 LTS.

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 task needs the judgment of a carpet installer — testing a slab for moisture before glue-down, laying out seam and pattern-match placement for a room wider than the goods roll, deciding stretch-in vs direct-glue method, diagnosing a wrinkled or peaking installation, or pricing a moisture-mitigation or re-stretch change 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。

A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.

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。

Explicit-only last resort. Draws game art from code, with no image model - pixel sprites from a PixelSpec, flat vector props, UI and icons from portable SVG, rigged characters with planted feet, FX with a JS runtime, seam-proven autotiles, playable top-down layouts with collision, stylized parallax and ambient plate motion - palette-exact, with QA and review sheets. Use only when the user explicitly asks for code-drawn art, or when generate2dmedia route_media.py finds no image or video route (no-route, exit 3). Never the default - image generation (generate2dsprite, generate2dmap, video2dsprite) comes first for characters, props, maps and FX. Not for painterly, detailed or likeness art, HD-2D plates or realistic fire, smoke or water. Always disclose the result as code-drawn.

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。

Presentation/Core/Engine split control plane — the canonical entry point for any work decomposing the Yuzu server into three binaries (presentation · core · engine) per ADR-0031-presentation-core-engine-decomposition / ADR-0032 (the admission interlock) / ADR-0033 (access-control spine). Use when the user says "/split", "/pce-split", "/decomposition", asks to plan or implement a split workstream (WS-A*, WS-B*, WS-X*), asks "what's our gap to the presentation/core split" or "is it safe to extract presentation/the engine yet", asks to audit split readiness, or starts work touching the seam (handlers calling stores directly, the INV-31-4 contract test, the Drogon port, `server/presentation` or `server/engine`, the `uce` DB grants, component service identity, or the ADR-0032 admission/grant/audit substrate — `use_case_run_id`, the release log, the capability-declaration registry).

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 reviewing a codebase for architectural friction, shallow modules, poor test seams, scattered behavior, duplicated orchestration, or opportunities to deepen modules before implementing a ticket or workflow.

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 designing or improving a module interface, choosing a seam, reducing shallow modules, making code easier to test, or reviewing architecture for locality, leverage, adapters, and deep-module design.

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。

Produce a UGC-style talking-head video ad end to end on the MaxFusion MCP — research the product with user-supplied competitor leads, tear down 5 competitor Meta ads and 5 organic TikToks, write a pain-driven script that sounds like a person talking (never like an ad), reverse-prompt a rights-clean photoreal actor from a user-supplied reference photo, generate two chained 10-second Gemini Omni clips that play as one continuous take, and ship a single seamless 9:16 MP4. Use whenever the user wants a UGC ad, a talking-head ad, an ad for an app or product, mentions Omni or Gemini Omni Flash, drops an actor photo and asks for a video ad, or says anything like "make me some UGC", "let's make ads for X", or "another variation". Built for Claude Code (local ffmpeg); degrades to Claude app with documented fallbacks.

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。

A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.

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。

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

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。

Session handoff — compress current context into a structured prompt for seamless continuation in a new session. Use when: switching sessions, running low on context, or needing to hand off work.

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。

Audit agent runtimes and their tests for lifecycle inference, capability overload, context pollution, correlated verification, prompt-only control, false success, dead compatibility paths, test-only seams, and complexity without contribution. Use for whole-repository agent audits, slop or dead-code triage, test contribution reviews, large refactors, tool/context simplification, and cleanup requests that need proof before deleting code or tests.

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。

分布式并行策略选型与实测（USP / CP 通信掩盖 / CFG / TP/RSP/PP 概览；含拓扑相关选型 （按实测拓扑分域条件化：域内 bulk vs 跨域 head-parallel 翻转）与 AlltoAllV 缺陷绕过）。在 model-auto-optimization 中承担 S3：优先 USP、结合拓扑带宽差异选 CP，少量 step + 多 rank 验证特性开启与掩盖（产物：并行方案 + 多 rank 证据）。当用户需要多卡并行 策略选择、**序列并行形态抉择**（纯 Ulysses vs 复合 AllGather-KV×Ulysses：按 GQA / 跨域带宽 / 形态 plumbing 条件化定胜负）、**并行 × 稀疏叠加**（seam 契约：先汇聚后稀疏、 窗口偏移、块对齐、per-head 掩码；含「稀疏看似生效实则未生效」判定）、通信掩盖调优 （含**掩盖率上限**：1-1/n 何时成立、c/f 决定的真实上限、没生效的排查）、**并行方案 差异归因**（阶段 Δ 分解 / 集合通信按 communicator 归属 / 4→8 卡线性度），或排查多卡 跑不动 / 通信暴露大 / 换卡组 / 端口 bind / HCCL 带宽验证问题时使用；**并收编原并行作用域诊断**： 改了 SP/CP/Ulysses/AllGather-KV 后**不报错但结果没变/性能没变**、或小规模能跑大规模崩 （如 Ascend EE1003 coreDim 超限）时，用本技能证明"改动到底有没有生效"（判别量逐层收窄 + 两侧对照 + 日志≠生效，见 `references/scope-effectiveness-check.md`）； 即使用户只说 "多卡跑不动""通信暴露大""为什么没达到 6/7 的掩盖率""CP 和 USP 该选哪个""CP 叠稀疏 怎么不生效"而未说并行，也应触发。特性档位/接口事实见 `docs/zh/features/parallelism.md` /`usp.md`（仓内真源），框架侧开启见 framework-integration； 本技能承载选型决策、monkey-patch 掩盖与多卡诊断实测。 由 dev-workflow 多卡场景触发，亦由 model-auto-optimization 的 S3 阶段触发。

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 surfacing architectural friction and proposing deepening refactors (shallow modules → deep modules) for testability and AI-navigability. Triggers on "improve architecture", "find deepening opportunities", "where is this codebase shallow", "architecture review". Emits structured candidates + precise patches; delegates ALL rendering to mk:preview. NOT for diagram/HTML rendering (see mk:preview); NOT for trade-off deliberation (see mk:party); NOT for plan critique (see mk:plan-ceo-review).

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。

Designs adaptive clinical trials including group-sequential (O'Brien-Fleming, Pocock, Lan-DeMets spending), sample-size re-estimation (blinded Friede-Kieser, unblinded Cui-Hung-Wang, Mehta-Pocock promising zone), seamless Phase 2/3 with treatment-arm selection, population enrichment, and response-adaptive randomisation. Covers FDA 2019 Final Adaptive Designs Guidance, FDA 2022 Master Protocols, and ICH E20 Step 2b/3 draft (June 2025, NOT final). Use when planning interim analyses, sample-size re-estimation, or master/platform-trial designs.

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。

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

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 and govern an MCP server as a bounded tool seam. Defines which tools the agent may call, enforces the principle that agents call tools and tools call infrastructure. Trigger when adding or reviewing an MCP server in an agent system.

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。

Google ADK (Agent Development Kit) orchestration patterns — boundaries, agent composition, and tool seams. Trigger when designing or reviewing multi-agent systems built on ADK. Authoritative source: adk.dev.

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。

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

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。

Establish SAML 2.0 identity federation between on-premises Active Directory and Azure AD (Microsoft Entra ID) for seamless cross-domain authentication and SSO to cloud applications.

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。

Shared vocabulary for designing deep modules, interfaces, seams, adapters, leverage, and locality. Use when designing or reshaping module boundaries, making code more testable, or evaluating interface depth.

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。