908 个 · 按相关度排序
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
中文简介正在准备中。当前显示原文说明。
Interactively gather parameters for `python -m cli.inference.text_generate`, generate a concrete text generation simulation command, explain assumptions, ask for execution confirmation, then run the command and summarize performance metrics. Use when the user wants to validate a specific model, hardware profile, batch/query size, prefill or decode scenario, TP/DP/EP/MOE parallel strategy, profiling database, chrome trace, empirical metrics export, or a best row produced by throughput_optimizer.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Search for papers and similar competition solutions related to the competition, and summarize in survey/papers/. Use during the research phase or when exploring new approaches.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Condense long reports, documents, or data exports into structured summaries with key findings, implications, and recommended actions. Use when the work is distilling dense content for busy readers. Do not use for original analysis, strategy formulation, or when the source material needs expert interpretation beyond summarization.
中文简介正在准备中。当前显示原文说明。
Summarize meeting notes or transcripts into decisions, action items, owners, risks, and follow-up messages. Use after meetings when raw notes need a clean recap.
中文简介正在准备中。当前显示原文说明。
Build and validate Azure infrastructure in a lab or sandbox using Azure CLI and official Microsoft docs. Use when creating verification environments, provisioning hub-and-spoke VNets, VPN Gateway or ExpressRoute-adjacent validation labs, checking subscription/tenant access, debugging Azure deployment constraints, comparing before/after route behavior, or cleaning up lab resources. Triggers on 'Azure 検証', '検証環境', 'PoC', 'sandbox', 'lab', 'Azure CLI で構築', 'VPN Gateway', 'VNet peering', 'BGP', 'route validation', 'summarizedGatewayPrefixes', 'デプロイして検証', 'インフラ検証'.
中文简介正在准备中。当前显示原文说明。
Prepare video URLs or local video files for GitHub Copilot analysis by extracting captions, sampled frames, contact sheets, and a prompt packet. Use when the user asks Copilot to watch, inspect, summarize, or diagnose a video, screen recording, demo, webinar, YouTube/Loom/TikTok/X/Vimeo URL, or .mp4/.mov/.mkv/.webm file.
中文简介正在准备中。当前显示原文说明。
Company expense receipt workflow. OCR, rename, sort, summarize, and prepare receipt images/PDFs/videos for D365 expense mapping and attachment. Use when sorting company expense receipts, organizing travel expense files, OCR renaming, receipt sorting, expense sorting, レシート仕分け, 出張経費バッチ, D365経費仕分け, D365経費カテゴリマッピング, or D365経費精算. Not for personal or sole-proprietor tax receipts (確定申告).
中文简介正在准备中。当前显示原文说明。
Transcribe local MP4/M4A/MP3/WAV/WEBM audio or video with ffmpeg and Whisper, then optionally produce diarized transcripts, customer-facing meeting minutes, action items, and PPT-ready summaries. Use when: 文字起こし, transcription, transcribe mp4, meeting transcript, mp4から文字起こし, 録画から議事録, 顧客向け議事録, 話者分離, diarization, whisper CLI, ffmpeg.
中文简介正在准备中。当前显示原文说明。
Writes expert academic paper summaries for social science research, particularly political science and applied statistics. Use when asked to summarize, review, or create a reading summary of an academic paper, PDF, or research article. Accepts a file (PDF or text format) or a directory of papers. Produces a structured markdown summary — approximately 400–600 words — covering primary contributions, major questions and answers with point estimates, methods and data, and limitations and robustness. Includes BibTeX citation retrieved from Google Scholar and keyword metadata.
中文简介正在准备中。当前显示原文说明。
"Apply Social Identity Theory to analyze how group categorization, identification, and intergroup comparison drive behavior, bias, and conflict. Use this skill when the user needs to explain in-group favoritism or out-group hostility, diagnose organizational silo dynamics, design inclusive team structures, or when they ask 'why do groups polarize', 'how does team identity affect collaboration', or 'what drives us-vs-them thinking'.".
中文简介正在准备中。当前显示原文说明。
"Implement text summarization using extractive and abstractive approaches. Use this skill when the user needs to condense long documents, build an automatic summarization pipeline, or compare summarization strategies — even if they say 'summarize this document', 'TLDR', or 'key points extraction'.".
中文简介正在准备中。当前显示原文说明。
Updates this skill pack from upstream, and owns the consent that decides whether it ever updates on its own. Checks whether the clone is behind, asks the user — update now, always keep me up to date, not now, or never ask again — and carries out the answer: applies the update through ./scripts/update.sh, records the consent flag the SessionStart hook already reads, snoozes on an escalating ladder, or turns the check off for good. Summarizes what changed between the two commits from the CHANGELOG. Use when the user asks to update or upgrade the pack, get the latest skills or the newest version, when the session banner reports that updates are available, when they ask whether their clone is current, when they want unattended updates switched on or off, or when they want to stop being asked. It never applies an update without an answer, and notify-only is the default.
中文简介正在准备中。当前显示原文说明。
Use when analyzing how Plugin Inspector rule, warning, deprecation, or compatibility changes affect the ClawHub plugin corpus. Guides agents to export plugins from ClawHub, run `plugin-inspector batch`, and summarize affected plugins and finding frequency.
中文简介正在准备中。当前显示原文说明。
Use this agent when you need to create a pathway summary for a gene after completing the main gene review. This agent should be invoked specifically to generate GENE-pathway.md files that summarize the gene's role in biological pathways with proper citations and mermaid diagrams.
中文简介正在准备中。当前显示原文说明。
Use when about to commit, finish a task, open a PR, summarize work for the user, or when the user asks for a review or summary — NOT just on autonomous commits, which are rare in OpenCode usage
中文简介正在准备中。当前显示原文说明。
Runs a sample in an instrumented sandbox to observe behavior: process tree, file and registry changes, network activity, and persistence, then summarizes the behavioral report into capabilities and IOCs. Activates for requests to detonate a sample, do dynamic or behavioral analysis, or interpret sandbox output.
中文简介正在准备中。当前显示原文说明。
Sign, notarize, package, and distribute Pulp plugins and apps across macOS, Windows, and Android
中文简介正在准备中。当前显示原文说明。
Generates a contextual onboarding document for a new contributor or agent joining the project. Summarizes project state, architecture, conventions, and current priorities relevant to the specified role or area.
中文简介正在准备中。当前显示原文说明。
Teach a topic, video, article, codebase change, spec, or transcript until the user demonstrably understands it, using staged instruction, a running checklist doc, and quizzes. Use whenever the user says "teach me", "explain this in detail", "help me understand X", "/teach-me", "walk me through this", "I want to learn X", "understand this deeply", or pastes a YouTube URL, article, paper, PR, or spec and asks to understand it rather than summarize it. Also use when the user wants study notes or raw material from a source they are learning. Do NOT use for a quick factual lookup, a summary request, or when the user just wants the answer.
中文简介正在准备中。当前显示原文说明。
Summarizes Google Cloud Data Lineage graphs to help users debug data quality issues and understand data provenance for BQ/GCS. Use when summarizing upstream and downstream data flows, and presenting complex lineage data as an intuitive Markdown report. Don't use for generic BigQuery queries, editing lineage relationships, or downstream deprecation. Don't use for downstream blast-radius impact analysis (use datalineage-bigquery-asset-impact-analysis skill instead).
中文简介正在准备中。当前显示原文说明。
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, measure the causal effect of an intervention, compute correlations between columns, detect change points or structural breaks, extract trend or seasonality components, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.
中文简介正在准备中。当前显示原文说明。