4,148 件 ・ 関連度順
概要と使いどころ
在 W8A8 动态量化后，用 MindIE-SD 冒烟测试 DiT 量化权重是否可加载（可选 skill）。与 `quant-tuning-evaluate`（DiT 扩展节）的区别：本 skill 仅做"能跑通 + 权重可用"的轻量验证（4~16 条 prompt，几分钟出结果），不算分；后者产出视频集交 `quant-tuning-score-dit`（AISBench-VBench 16 维度）评分，是调优回路一环。不引入 vLLM-Ascend、不做精度指标评估（FID/CLIP-score 等）。
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。
当用户直接要求进行数据集压缩测评，或在量化调优过程中需要使用 AISBench 评测工具输出数据集精度等场景时使用。 本 Skill 负责：使用 AISBench 数据集压缩代码、用 RBF Kernel Herding 算法生成压缩后的数据子集（coreset），并按用户目标交付两种产物之一： ① 接入量化调优主流程：产出独立的 coreset 数据集配置（不覆盖原始数据），回传「全集 config_name + coreset config_name」给编排层，供 evaluation.yaml 切换； ② 仅数据集压缩测评（不做量化调优）：基于 example 模板生成「全集测试脚本」和「子集测试脚本」两份 shell 脚本。 暂时支持 AIME 2025 和 GPQA，其他数据集需要再结合 aisbench tools目录下 herding_coreset_selector 源码进行分析。
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。
解析中文自然语言中的 AISBench 测评需求，检查 Python 与 AISBench 运行环境，通过分轮追问确认关键配置，将基准名称映射为仓库内的数据集任务，在用户最终确认后生成并执行 AISBench CLI，并返回精度指标和产物路径。适用于用户要求使用 AISBench 评测模型或运行数据集；不适用于实现新数据集或仅解释基准概念。
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。
Call Exa Search (POST /search) for semantic web retrieval with ranked results, filters, freshness, highlights/text, structured output, or streaming. Use when the agent needs open-ended web search, competitor discovery, news, people, or research papers and does not already have URLs. Prefer Exa MCP web_search_exa / web_search_advanced_exa when available; otherwise raw HTTP with EXA_API_KEY. NOT for known-URL extraction (use exa-contents or firecrawl) or multi-step list-building (use company-research / lead-generation / Agent API).
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。
Employer Brand Audit — Glassdoor/Indeed review analysis, LinkedIn company page assessment, career site evaluation, employee testimonials, competitiveness vs other employers
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。
30/60/90 Day Onboarding Plan — Day 1 setup, week 1 ramp, month 1 milestones, month 2 contributions, month 3 evaluation criteria
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。
Content angle generator for turning dry expert topics into high-engagement infotainment. Applies 7 journalistic angle types (Myth vs Reality, Paradox, Level Error, Price of Solution, Conditions, Hidden Driver, Contrary Thesis) + historical/future lens + news-hook framing. Use when experts need their content to become interesting rather than just informative - blog posts, video scripts, social content, newsletters, landing pages, ad hooks. For any niche: B2B, B2C, services, products, personal brand.
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 scoring finished content against quality dimensions, evaluating whether a piece meets publishable standards, or determining which workflow phase needs rework based on quality gaps.
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。
Provides a complete workflow for implementing verified email retrieval on Android Credential Manager API. Use this skill to integrate a secure, OTP-less email verification flow into an Android app. This skill solves the problem of high-friction sign-up processes by leveraging cryptographically verified credentials from trusted providers like Google.
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。
Work with the @upstash/vector TypeScript/JavaScript SDK, a serverless vector database for embeddings, similarity search, semantic search, and RAG (retrieval-augmented generation). Use when upserting, querying, fetching, ranging, or deleting vectors, upserting raw text against an index with a built-in embedding model, choosing dense, sparse, or hybrid indexes, filtering by metadata, organizing data with namespaces, running resumable queries, or connecting Upstash Vector to an AI or LLM application. Also use when the user asks for a vector store, vector search, nearest-neighbor or kNN search, embeddings storage, semantic cache, recommendations or similarity features, or a hosted vector index that needs no infrastructure.
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。
Calculates CRAP (Change Risk Anti-Patterns) score for .NET methods, classes, or files. Use when the user asks to assess test quality, identify risky untested code, compute CRAP scores, or evaluate whether complex methods have sufficient test coverage. Requires code coverage data (Cobertura XML) and cyclomatic complexity analysis. DO NOT USE FOR: writing tests, general test execution unrelated to coverage/CRAP analysis, or general code coverage reporting without CRAP context.
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。
Optimize embedding strategies for AI retrieval. TRIGGERS - Use when user needs help with ai-embedding-optimizer related 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。
Plan AI fine-tuning projects with data preparation, training, and evaluation. TRIGGERS - Use when user needs help with ai-fine-tuning-plan related 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。
Build text and data classification systems with training and evaluation. TRIGGERS - Use when user needs help with ai-classification-system related 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。
Evaluate and implement agricultural technology solutions. TRIGGERS - Use when user needs help with agricultural-technology related 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。
Jaeger provider for obz. Covers trace search, trace retrieval by ID, and extension commands for service and operation discovery. This skill should be used when the user mentions "Jaeger", "obz trace -p jg", or needs to search distributed traces from a Jaeger backend.
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。
Grafana Tempo provider for obz. Covers trace search, trace retrieval by ID, and extension commands for tag discovery. This skill should be used when the user mentions "Tempo", "Grafana Tempo", "TraceQL", "obz trace -p tempo", or needs to search traces from a Tempo backend.
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。
VictoriaTraces provider for obz. Covers trace search, trace retrieval by ID, and extension commands for service and operation discovery via the Jaeger-compatible HTTP API. This skill should be used when the user mentions "VictoriaTraces", "obz trace -p vt", or needs to search distributed traces from a VT backend.
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。
Show one skill in full — its team record or Library folder, versions, installs, health, and its eval report when it is a team skill — as Markdown boards from the terum-skills CLI. Use when the user names a skill and asks what it is, who installed it, how it scored, or what its receipt says.
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。
List the skills on this machine (your Library) and the skills your team shares (the Marketplace) as Markdown boards from the terum-skills CLI. Use when the user asks what skills they have, what the team shares, what is installed, edited, untracked or missing an eval, or wants an overview of their terum-skills state.
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。
Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use this skill whenever reviewing a PR, diff, or code snippet for accidental complexity — particularly when the code was generated by an AI coding assistant and line-by-line review isn't feasible. Also use when the user asks about complecting, simplicity vs. easiness, structural coupling, or concept deduplication. Trigger on phrases like "is this simple", "does this complect", "review for complexity", "structural analysis", or any reference to Hickey, Simple Made Easy, or grey-box 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。
Evaluate architecture and module boundaries for volatility-based decomposition using Juval Lowy's framework (from "Righting Software", building on Parnas 1972). Use when reviewing module splits, service boundaries, new abstractions, or any decomposition decision. Trigger on phrases like "where should this boundary be", "how to split this", "module boundaries", "encapsulate change", "volatility", or references to Lowy, Parnas, or "Righting Software". Complements /hickey (interleaved concerns) with a different lens (change encapsulation).
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。
Search and explore an Obsidian vault through the NoteBrain CLI (semantic search, tags, backlinks, connections, hidden links, boosted retrieval). Use it whenever the user mentions their notes, knowledge base, Obsidian vault, semantic search, finding connections or unlinked notes, or asks exploratory questions like "what do I know about X", "find notes related to Y", "what connects to Z", or "summarize my notes on W" — even when they never say NoteBrain, vector search, or ChromaDB.
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。