9,711 件 ・ 関連度順
概要と使いどころ
Use when EZ_math_model multi or hybrid mode needs several domain-specialist subagents to gather outside knowledge, industry context, model theory, or sensitivity-analysis references in parallel.
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 solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper writing, quality audit, and packaged deliverables.
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 GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when needing direct model control or LoRA hot-loading. Triggers on 'llama.cpp', 'GGUF', 'LoRA adapter', 'benchmark inference', 'llama-server'.
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。
Selects the active profile from triggering context. Evaluates a rule set against inputs (current time, calendar state, geofence, manual command, custom signals) and returns the profile name that consuming Skills (handoff-trigger-check, critic-gate, future Skills) should apply. Configuration-driven; rule set lives in a router config file conforming to the included schema. Deterministic precedence — manual override beats calendar beats time-window beats default. Required default profile guarantees a routing decision always exists. Use when an orchestrator needs to pick a profile automatically rather than having the caller specify one, when wiring calendar/time/Telegram triggers to gate behavior, or when a Skill's behavior should change with availability mode. Trigger on: "what profile should I use," "route to a profile," "which mode am I in," "auto-select profile," "active mode," "current profile." Do NOT use to evaluate work readiness or review proposed changes. Always returns a profile name.
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。
Analyzes Claude Project context budget under the automatic-RAG-by-window model: knowledge files vs. threshold-exempt overhead (Skills, MCPs, CI, Memory). Two modes: Quick Diagnostic and Full Budget Audit. Use when user says "check my context budget," "how much context am I using," "is my project too big," "optimize my token usage," "tier my files," "optimize for RAG," "improve retrieval quality," "should I keep compressing," "am I over-compressing," "should I accept RAG mode." Also trigger on context pressure symptoms: "Claude forgets my instructions," "responses getting generic," "content not found in my knowledge files." Also use when a project audit scores Knowledge Architecture ≤ 3. Do NOT use for content placement decisions (use rootnode-memory-optimization if available), full project audits (use rootnode-project-audit if available), or behavioral tuning (use rootnode-behavioral-tuning if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.
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。
Convert SVG files to high-quality PNG images with precise control over dimensions, background color, and CSS rendering (including mix-blend-mode, filters, gradients). Use this skill when the user wants to: (1) convert SVG to PNG, (2) generate app icons or splash screens from SVG source, (3) batch-generate multiple PNG sizes from a single SVG, (4) render SVG with advanced CSS features like mix-blend-mode or filters to PNG. Triggers: "SVG to PNG", "SVG変換", "PNG変換", "アイコン生成", "スプラッシュ生成", "app icon from SVG", "favicon generation", "splash screen generation".
機能検討・プロダクト機能設計の壁打ちスキル。Mode A「壁打ち開始：〇〇機能」で1機能を深掘り、Mode B「アプリの機能を考えたい」でアプリ全体の機能セットを設計。ペルソナ・競合分析・トンマナを統合して議論。
Design ornamental patterns using modern and speculative aesthetics with colorblind-accessible color scales. Breaks free from historical period constraints to explore cyberpunk, solarpunk, biopunk, brutalist, vaporwave, and other contemporary genres. Includes CVD (Color Vision Deficiency) awareness and perceptually uniform scales (viridis, cividis, inferno). Use when creating ornamental designs in modern or genre-specific aesthetics, designing patterns that must be colorblind-accessible, or exploring hybrid motifs combining historical ornament with contemporary visual language.
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。
Fit hidden Markov models using the Baum-Welch (EM) algorithm with model selection, Viterbi decoding for state sequences, and forward-backward probabilities. Use when observations are generated by unobservable latent states, you need to segment a time series into latent regimes (market regimes, speech phonemes, biological sequences), compute sequence probabilities, decode the most likely hidden state path, or compare models with different numbers of hidden states.
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。
Django ORM patterns: model definitions, field types, model managers, custom QuerySet methods, select_related/prefetch_related for N+1 prevention, transactions, F/Q expressions, Meta indexes and constraints. For django-architect (model definitions) and django-migrations-specialist (field finalization). Activated automatically by django-plugin/stack.md. Use this skill to: - Write clean, efficient Django model definitions with proper field choices and __str__. - Use custom managers and QuerySets to encapsulate query logic. - Prevent N+1 queries with select_related and prefetch_related. - Use transactions for atomic operations. - Define Meta indexes and constraints (for django-migrations-specialist to finalize). Do NOT use this skill for: - Creating actual migrations (makemigrations) — that is django-migrations-specialist. - Web view / API patterns — see django-plugin:django-conventions. - Python idioms — see python-foundation:python-conventions.
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。
FastAPI web framework conventions: APIRouter with prefix/tags/dependencies, Pydantic v2 schemas (BaseModel, model_config, field_validator, model_validator), dependency injection with Depends, async SQLAlchemy session yielding, OAuth2PasswordBearer + JWT auth, lifespan context manager, pydantic-settings configuration, OpenAPI customization, and HTTPException error handling. Activated automatically by fastapi-plugin/stack.md. Use this skill to: - Structure FastAPI apps with per-feature APIRouter modules and a central app factory. - Write Pydantic v2 request and response schemas with proper validators. - Build a reusable Depends-based dependency chain for DB session, auth, and pagination. - Implement JWT-based authentication with get_current_user dependency. - Configure the app from environment variables via pydantic-settings. Do NOT use this skill for: - SQLAlchemy ORM model configuration and Alembic migrations — see fastapi-plugin:sqlalchemy-patterns. - Python language idioms — see python-foundation:python-conventions. - Testing patterns — see python-foundation:pytest-testing.
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。
Measure the active Agent model with pinned offline ModelTrace sampling and return an unsigned closed-set attribution record. Use before Agent-originated commits, Issue/PR creation or material updates, comments, reviews, and current collaboration writes in either execution mode. Do not treat a fingerprint, declared model label, or record reference as authenticated identity, permission, independent review, or acceptance.
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。
对 DiT（扩散/多模态生成）模型执行 W8A8 动态（data-free）或 W8A8 MXFP8（data-free）量化。覆盖 HunyuanVideo、Wan2.2-T2V/I2V/TI2V、FLUX.1-dev（已迁移）、SD3、Sana、HunyuanDiT、CogViewX 等。YAML apiversion 固定 multimodal_sd_modelslim_v1，统一 MultimodalPipelineInterface 重构路径（不再保留 LegacyMultimodalPipelineInterface）。模板与字段以 msmodelslim/model/hunyuan_video/model_adapter.py（唯一已迁移到重构路径且 lab_practice YAML 已 validated 的 DiT）为参考；其它 DiT 需按各自推理仓的 `parse_args` 调整字段集合。data-free 指不引入外部激活校准数据，spec.dataset（校准集短名，短名如 wan2_2_t2v；enable_dump: false 时不参与 dump）仍必填；精度调优通过下游经验库 L2 §7 + 直接调 `quantization-expert-experience-tuning-rules/scripts/apply_rollback.py`（整层回退）扩展 exclude 列表，闭环由 `quantization-accuracy-tuning-orchestrator` 调度。
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。
为 msModelSlim 创建基础 Transformers 模型适配器（Model Adapter）。 包含创建适配器、实现必需接口与注册安装流程。 适用：Decoder-only LLM、理解类 VLM（仅 LLM/text 部分）。 多模态生成（DiT/扩散，含双/多专家）见下方「多模态生成扩展」节，按需加载。 不适用：Encoder-only、非 Transformers 架构。
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。
为 msModelSlim 适配流程注入反量化能力。先识别模型权重是否可反量化，再实现反量化脚本并接入 model_adapter。当前仅覆盖 FP8 的 per-block 与 per-channel 两类；若格式不确定或无公开反量化规则，要求用户提供反量化脚本或浮点权重。
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 professional brand-quality product images via Higgsfield's mode-specific prompt enhancement pipeline. Entry point for any product visual with a specific format or platform target. Use whenever: "product photoshoot", "lifestyle product shots", "Pinterest pin", "hero banner", "ad pack", "virtual try-on", "studio shot", "carousel images", "Meta ads creative", "model wearing product", "levitating product", "splash shot", "CGI style product", "restyle product image", Shopify image, brand campaign visual. 10 modes: product_shot, lifestyle_scene, closeup_product_with_person, moodboard_pin, hero_banner, social_carousel, ad_creative_pack, virtual_model_tryout, conceptual_product, restyle. Backend assembles the prompt — never call gpt_image_2 directly for product shots. NOT for: one-off images without a product (use image-gen), branded video with avatars (use higgsfield-generate), Soul training (use higgsfield-soul-id). Requires Higgsfield CLI and authed account.
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。
Codex CLIと相談するスキル。 ユーザーが「codexと相談して」「codexに聞いて」「codexにレビューしてもらって」と言った時に使用する。 現在の会話コンテキストに基づいてCodex CLIにプロンプトを送り、結果を要約して報告する。 「codexはAstraで」「effortはhighで」のようにCodexのmodelやreasoning effortを指定された時は、そのmodelとeffortで実行する。
Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.
"Model viral spread dynamics using SIR/SIS/SEIR compartmental models. Use this skill when the user needs to predict content spread patterns, estimate viral thresholds, or model information cascades in social networks — even if they say 'will this go viral', 'epidemic model for content', or 'spread prediction'.".
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。
Extract sensitive training data and internal capabilities from AI models through repeated programmatic querying. Use this skill when testing LLMs and ML models for data privacy leaks, intellectual property exposure, or unintended memorization. Covers membership inference, prompt extraction, training data reconstruction, and API boundary testing.
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。
Identify and exploit vulnerabilities in the AI Supply Chain by injecting malicious models, datasets, or dependencies. Use this skill to simulate advanced persistent threats (APTs) compromising Hugging Face repositories, manipulating pre-trained weights (Model Poisoning), and exploiting insecure deserialization during model loading (e.g., Pickle files).
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。
AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.
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 any installed skill on several models at once — you, OpenAI Codex, OpenCode and whoever else the profile names — and show what each one made of it side by side. Every model gets the same prepared copy of the skill and works read-only. Use for "/multi:skill <name>", "run this skill on every model", "run <skill> through multi", or any skill whose answer you want from more than one model.
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。