「core」の検索結果

Diagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow despite demeaner_backend="cupy64" and an idle GPU. Use when: (1) a script looping dozens of pf.feols models on a 100k+ row panel takes ~1 min/model, (2) process inspection shows ~1-1.5 cores busy and nvidia-smi shows ~0% GPU utilization with a resident cupy context, (3) planning any worker prompt that will run a model grid (robustness variants x FE structures x domains). Root cause: per-model CPU-side single-threaded fixed costs (formulaic model-matrix build, interaction construction, singleton detection, cluster vcov) dominate wall time; GPU demeaning is a small slice. Fix: shard the model grid across OS processes and/or use pyfixest multiple-estimation syntax; mandate this IN THE WORKER PROMPT.

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。

Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.

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。

Gate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat, gpt-*-latest, gemini-*-preview, any provider alias without a pinned version). Use when: (1) resuming a paused or credit-exhausted scoring run days after its last chunk, (2) topping up credits to finish a campaign, (3) extending a cached scoring pipeline with new items. Prevents silently splicing two model versions or serving revisions into one measure. Verified 2026-07-16: for $0.30 caught a serving-revision drift WITHIN DeepSeek v4-flash (same alias, same family, litigation scores systematically shifted across a 2-day gap) before an $83 resume spend.

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。

Automate App Store & Google Play screenshot generation for Flutter apps. Scans routing and screens, scores high-value marketing screens, generates self-contained mock harness, runs native simulator captures (iPhone 6.9", iPad 13", Android Phone/Tablet), strips alpha channels, and validates exact store resolutions.

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。

Improve a skill using a test-fix-retest loop. Runs static checks, proposes targeted fixes, rewrites the skill, re-tests, and keeps or reverts based on score change.

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。

Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.

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。

Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before /code-review and /story-done.

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 6 C# scripting guide. Use when writing MonoBehaviour scripts, handling lifecycle events (Awake, Start, Update, FixedUpdate), using coroutines or async/await (Awaitable), working with ScriptableObjects, events, delegates, or core APIs like Vector3, Quaternion, Time, Debug. Based on Unity 6.3 LTS documentation.

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 game loop and progression design-to-code translation. Core loop scaffolding, session lifecycle, win/lose condition architecture, meta loop hooks, tunable difficulty, pacing & encounter timing. 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。

Unity 6 core concepts and architecture guide. Use when working with GameObjects, Components, Transforms, Scenes, Prefabs, ScriptableObjects, or Unity project structure. Covers the entity-component architecture, object hierarchy, tags, layers, and project conventions. Based on Unity 6.3 LTS documentation.

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。

用于诊断或改进前端性能、Core Web Vitals、包体积、运行时渲染成本、网络瀑布、内存泄漏、长任务、Lighthouse 问题或性能预算；中文触发词包括 性能优化、页面卡顿、首屏慢、包体积、Web Vitals。

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 or improving frontend performance, Core Web Vitals, bundle size, runtime rendering cost, network waterfalls, memory leaks, long tasks, Lighthouse findings, or performance budgets; Chinese triggers include performance optimization, page freeze, slow first screen, bundle volume, Web Vitals.

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。

OpenUI generative UI with C# ASP.NET Core Minimal API backend. Direct OpenAI API SSE streaming via HttpClient on .NET 10.

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 whether all score-deciding logic in sgl-eval is vendored from NeMo-Skills, or whether some has crept into SE code. Use when the user asks "are we vendoring enough", "review vendor coverage", "audit vendoring", "is our vendoring complete", or before a release.

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。

Build full-stack Nuxt applications, with zero configuration.

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 tenure-track/tenured Education Professor in a teacher-preparation program — designing a licensure course unit against InTASC/CAEP standards, deciding whether a candidate's borderline edTPA score needs a targeted or full retake, triaging a failing student-teaching placement, or assembling CAEP self-study evidence for reaccreditation.

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 an Engineering Teacher, Postsecondary — diagnosing a spike in a gatekeeper course's D/F/W rate, running a capstone design course with an industry sponsor, closing the loop on an ABET student-outcome assessment, or building a tenure/promotion teaching-effectiveness case beyond raw student evaluation scores.

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 dermatologist — triaging a pigmented lesion for melanoma risk, choosing a biopsy technique and reading the pathology in clinical context, staging a skin cancer to decide margins or Mohs referral, escalating psoriasis/eczema treatment by severity score, or managing isotretinoin risk under REMS/iPLEDGE rules.

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 Computer Hardware Engineer — designing a power delivery network and selecting decoupling capacitors for a digital IC's core rail, budgeting a high-speed signal's rise time against trace impedance and via stub length, closing static timing on a board-level DDR or SerDes interface, sizing thermal resistance for a package's TDP, or reviewing a PCB layout for signal- or power-integrity risk before fab release.

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 Compensation, Benefits, and Job Analysis Specialist — market-pricing a job against salary survey data, scoring a job through a point-factor or IPE job evaluation, running a pay-equity regression or cohort analysis, building or refreshing a salary structure and compa-ratio bands, classifying a job family's FLSA exemption status through the duties test, or modeling benefits plan cost (loss ratio, PEPM, self-funded vs. fully insured). Distinct from hr-people-manager (owns the comp/leveling judgment calls — whether to approve an exception, promote someone into a level), hr-specialist (owns individual-case leave/I-9/ADA/FLSA reclassification for one employee's drifted duties), and compensation-benefits-manager (owns pay philosophy, negotiation-range policy, and the department that runs this work). This role owns the mechanics: the survey match, the point score, the regression, the band math — the analysis those upstream policy and downstream judgment calls are made against.

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 Cooling/Freezing Equipment Operator — calculating freezing time for a new product thickness via the thickness-squared relationship rather than assuming linear scaling, verifying freezing completion by actual core/thermal-center temperature rather than surface temperature or elapsed time, recognizing a temperature plateau as expected latent-heat removal rather than a malfunction, or matching belt speed/residence time to the calculated freezing time requirement.

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 Chief Technology Officer — deciding build vs buy for a core system, choosing whether an architecture bet is worth a full rewrite, sizing an SLA/uptime commitment against engineering cost, structuring engineering teams around a product roadmap, or writing the technical risk section of a board update.

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 board-certified Clinical Neuropsychologist — building a neuropsychological battery to localize a brain-behavior deficit, adjudicating performance validity before interpreting any cognitive score, distinguishing a dementia subtype or mTBI sequela from a psychiatric or malingering cause, or writing a forensic, pre-surgical (epilepsy/tumor), or serial-retest report.

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 board-certified cardiologist — triaging chest pain with a risk score, titrating heart-failure guideline-directed medical therapy, deciding revascularization strategy for stable or acute coronary disease, or working through anticoagulation decisions in atrial fibrillation. US practice default (ACC/AHA guideline framework). A reasoning aid, not medical advice.

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。