「hf」の検索結果

Run a GGUF model locally with llama.cpp, and find one on the HF Hub.

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。

Install and verify the msmodeling development environment. Use when the user explicitly asks to install msmodeling dependencies, set up this repository, create `myenv` with `uv`, install this repository's `requirements.txt`, set project `PYTHONPATH`, or configure `HF_ENDPOINT`; if the user only says to install an environment, ask whether they mean msmodeling dependencies before proceeding.

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 code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.

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。

Audits whether a machine-readable regelrecht law model is faithful to the LETTER of the wettekst — and strictly separates the wettekst (leading) from the toelichting (Nota/Memorie van Toelichting; explanatory, not a norm). Runs in critical passes per article/lid and detects four deviation classes: toelichting-bleed (a modeled criterion that the letter only states as an open norm, or not at all), missing verbatim elements (a word/condition such as a "tenzij" or a qualifier dropped from the model), wrong legal_basis anchoring (an endpoint hung on a "kapstok"-article while the operative norm lives elsewhere), and verbatim-drift in text: (an ingetrokken/older redaction). Also detects positief-lid vs uitsluitings-lid conflicts and checks the chapeau for an explicit derogation rule ("zo nodig in afwijking van het eerste lid") before judging precedence. Classifies every finding as modelfout (fix), wettekst-gevolg (report, do not fix), or letter-vs-toelichting-question (jurist decides what is leading + revision signal). Use when the user wants to know if a model is "dicht bij de letter", mentions letter vs toelichting/bedoeling, fidelity, "natuurgetrouw", or before trusting feature outcomes.

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。

Performs critical code reviews using REVIEW.md guidelines. Evaluates code quality, architecture, testing, and domain-specific concerns (legal faithfulness, cross-law references, engine safety). Use after completing significant code changes or before merging.

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 hunting GitHub Actions cache poisoning vulnerabilities where an attacker can inject malicious content into the CI/CD cache and have it restored by a privileged downstream workflow. Trigger on: "cache poisoning", "actions/cache", "actions/setup-node", "node_modules cache", "GitHub Actions cache", "pnpm cache", "LRU eviction", "10GB limit", "Cacheract", "poisoned cache", "workflow cache attack", supply chain via CI cache, "ng-renovate", "cache stuffing", scheduled workflow cache restore, shared cache key, "hashFiles package.json", cross-workflow cache, PR workflow release workflow same key, "npm install prefer-offline", Cacheract, Gato-X, supply chain npm token.

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。

Capture faithful PNGs of Pulp view trees / imported UIs headlessly. Covers render_to_png backends (Skia vs CoreGraphics), the image-compositing gotcha, capture_png from a live GPU host, and the --screenshot-backend validate flag. Use whenever you render a UI to a PNG to eyeball or montage it.

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 AI and navigation guide. Use when working with NavMesh, pathfinding, NavMeshAgent, NavMeshSurface, NavMeshObstacle, off-mesh links, or Unity Sentis (ML model inference). Covers AI navigation package, runtime NavMesh baking, and common AI patterns like state machines and behavior trees. 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 NavMesh pathfinding patterns, safety checks, and performance optimization.

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 code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.

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, import, analyze, resume, or revise an end-to-end Circuit Weaver electronic design from requirements through validated functional KiCad schematics, placement review, and a truthful manufacturing handoff. Use for new designs and for existing KiCad/PCB/Gerber projects that need durable state. Use kicad for one-off file inspection, bom for standalone sourcing, and design-wizard only when the user explicitly requests the slower questionnaire.

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 Bridge and Lock Tender — deciding whether to open a movable span for a vessel signal during a restricted-hours window, sequencing a lock chamber's fill/empty and valve staging, verifying an interlock/gate cycle before commanding span movement, resolving a marine-traffic-vs-vehicle-traffic conflict, or coordinating a vessel passage over VHF.

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。

Treino Ultralytics YOLO pose para keypoints do campo de futebol (32 kp), export ONNX, e inferência em vídeo com vaila.soccerfield_keypoints_ai (CSV getpixelvideo + overlay). Use quando o usuário fala em football pitch keypoints, YOLO26 pose, treino Roboflow/HF dataset martinjolif, field_keypoints_getpixelvideo, calibração FIFA, ou soccerfield_keypoints_ai.

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 wants to create, generate, build, update, refresh, or improve their personal writing style guide from their own sent writing (Generate mode), OR when they ask the agent to write, draft, reply, rewrite, edit, polish, or humanize something in their voice (Use mode). Teach your agent how to write like you.

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 game AI systems including behavior trees, finite state machines, GOAP planning, utility AI scoring, A-star and NavMesh pathfinding, steering and flocking behaviors, perception and awareness models, dynamic difficulty adjustment, NPC dialogue trees and scheduling, boss AI patterns.

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。

Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.

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。

Research current job markets and hiring requirements, analyze recent job descriptions (JDs), compare them with a user's resume, projects, skills, and constraints, and turn evidence gaps into prioritized career actions. Use when students, job seekers, or career changers ask about current role or industry outlook (including “现在行情怎么样”), whether a role or JD fits them (including “这个JD适合我吗”), cross-platform JD sampling, resume evidence gaps or truthful tailoring, what career skill to learn next, target-role course or certificate decisions, application readiness, or a capacity-bounded 30/60/90-day job-search plan. Do not use for unrelated personal or education advice, simple factual lookups, automatic job applications, or unsupported resume rewriting.

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 3D printing with Flashforge Adventurer 5M printers ("Ralph Wiggum").

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。

法律事项的运营性计费执行。月度账单准备和计费指示、LC 发票审查和代垫款处理、客户账单质询回应、现金流建模（LC 付款义务与客户收款对比）、杠杆和消耗分析（人员配置组合、预测总成本、利润轨迹）。触发词：‘prepare the bill’（准备账单）、‘billing instruction’（计费指示）、‘end of month billing’（月末计费）、‘LC invoice’（LC 发票）、‘local counsel invoice’（本地顾问发票）、‘pass through as disbursement’（作为代垫款转付）、‘client querying the invoice’（客户质疑发票）、‘billing dispute’（计费争议）、‘cashflow gap’（现金流缺口）、‘when will we get paid’（我们何时能收到付款）、‘LC payment due’（LC 付款到期）、‘leverage analysis’（杠杆分析）、‘staffing mix’（人员配置组合）、‘predicted total cost’（预测总成本）、‘burn rate by grade’（按职级消耗率）、‘are we on track’（我们在轨道上吗）、‘what will this matter cost’（此事项将花费多少）。

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。

Maps between gene identifier systems (Ensembl, Entrez, HGNC symbol, UniProt, RefSeq, MANE) using AnnotationDbi, biomaRt, mygene, pyensembl, and Ensembl REST. Encodes Ensembl version stripping with GENCODE _PAR_Y preservation, the Ziemann 2016 Excel autocorrect debacle and Bruford 2020 HGNC renames (SEPT*->SEPTIN*, MARCH*->MARCHF*, MARC*->MTARC*, DEC1->DELEC1), OCT4/POU5F1 alias resolution, biomaRt archive endpoints for release pinning, the `filters` (plural) gotcha, MANE Select for clinical reporting, cross-species orthology via Ensembl Compara / OMA / OrthoDB, and tx2gene construction for tximport. Use when converting gene IDs across systems, handling renamed symbols, building tx2gene, pinning to a specific Ensembl release for reproducibility, or mapping cross-species orthologs.

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。

Capture what someone actually said without contaminating it with your own inference. Invoke when eliciting intent in conversation (design discussion, requirement interview, decision surfacing) and when turning a conversation into a durable record (ADR, decision node, memory entry, spec `## Decisions` row). Enforces quote-before-critique, keeps illustration separate from commitment, and holds interpretation subordinate to verbatim. Prevents the failure where unspecified space is filled by the recorder and then evaluated as if the speaker had specified it.

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。

llama.cpp local GGUF inference + HF Hub model 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。

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

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 AI agents with Hugging Face's SmolAgents framework. Use when creating code-executing agents, tool-calling agents, multi-agent systems, agentic RAG, text-to-SQL pipelines, web browsing agents, or any multi-step AI workflows. Covers CodeAgent, ToolCallingAgent, custom tools, MCP integration, memory management, secure code execution (E2B, Docker, Blaxel), and model configuration (HF Inference, LiteLLM, Transformers, Ollama).

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。