3,198 件 ・ 関連度順
概要と使いどころ
Comprima modelos de linguagem grandes usando destilação de conhecimento de modelos professor para aluno. Use ao implantar modelos menores com desempenho retido, transferir capacidades do GPT-4 para modelos de código aberto ou reduzir custos de inferência. Aborda escalamento de temperatura, alvos suaves, KLD reversa, destilação de logits e estratégias de treinamento MiniLLM.
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。
Avalia LLMs em mais de 60 benchmarks acadêmicos (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use quando benchmarking de qualidade de modelo, comparação de modelos, relatório de resultados acadêmicos ou rastreamento de progresso de treinamento. Padrão da indústria usado por EleutherAI, HuggingFace e laboratórios principais. Suporta HuggingFace, vLLM, APIs.
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。
Load this skill whenever the project must support speech input or voice control — dictation, "click by voice" grammars, Dragon NaturallySpeaking, Voice Control (iOS/macOS), Voice Access (Android), or any interface where users activate controls by speaking. Under no circumstances let an aria-label override a visible label without keeping the visible text intact and in order. Absolutely always ensure the accessible name contains the visible label, and load alongside keyboard/SKILL.md since speech tools commonly emulate keyboard and pointer input.
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。
[Workflow] Use when activating the Integration Test Green workflow — drive an integration-test suite to fully green with a bounded convergence loop: verify the whole system (or the named target), adjudicate every failure with /debug-investigate + /integration-test-review before any edit, fix at the owning layer, /changes-review each round's fix diff, re-verify from scratch, then sync spec TCs, the integration-test reference doc, and feature docs.
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。
[Code Quality] Use when you need restructure code without changing behavior using extract method, extract class, rename, move, and inline 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。
[Process] Use when the developer wants something explained or taught, or wants to know HOW TO REVIEW a change — by default the current working tasks + changes in context, or whatever the prompt names (a plan, a subsystem, a decision, a concept, a bug). AI derives WHAT to explain from the prompt and ALWAYS delivers a teacher-and-coach review guide, high level first then detail: what was done, a VISUAL MAP (system flowchart, domain ERD, sequence diagrams), the user stories and business rules with their REAL test-case IDs, a REVIEW PATH naming which files to open first and in what order with an exit criterion per stage, the technical concepts needed to follow it, how it works, why THIS solution, every alternative option with pros/cons, the trade-offs accepted, the blast radius, HOW TO TEST AND DEMO the change, the developer's decision levers, and written challenge prompts that provoke the reader to pressure-test the work. Works at ANY scope — from one line of code to the whole project: it SIZES the target into a scope tier, DECOMPOSES a large one into understanding groups, BREAKS the work into tasks before the first deep read, and ACCUMULATES the report group by group on disk so a huge explanation stays complete instead of thinning out. Writes the full report to a single combined markdown file (plans/reports/understand-*.md) that opens with a detailed summary section — or delivers it in full in chat when Step 3 finds no git-ignored directory for it — and always summarizes it in chat. Regardless of coding level. Never interrogates, never quizzes, never blocks.
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。
[Testing] Use when you need to drive an integration-test suite to fully green — each round runs /integration-test-verify (whole system by default, or the target named in the prompt), and on ANY failure combines /debug-investigate + /integration-test-review (report-only) to adjudicate the fault (test wrong · test not optimal · source wrong), then /fix to resolve it at the owning layer, then /changes-review on that round's fix diff, then re-runs a FRESH full verify — looping until the whole suite passes its 2-consecutive-green-runs gate with zero failures.
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。
[Utilities] Use when a project needs to add, change, list, or remove its OWN protocol rules layered on top of a framework skill — a named overlay of extra project rules that applies whenever the targeted skill runs, stored with the project rather than in the portable framework. `/project-skill-protocol list` prints every overlay with its target and description; `add` drafts a new overlay and confirms it before writing; `update` applies a surgical change; `delete` removes it. Overlays are ADDITIVE ONLY — they never replace, override, or waive anything the skill already does. Triggers: skill protocol, project protocol, custom protocol for skill, extend a skill, overlay rules, add rules to a skill, project rules for skills, skill protocol overlay.
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。
[Documentation] Use when you need to generate a step-by-step demo guide (demo script / walkthrough) covering all main user stories and their test cases — scope from a named feature, else the current working context, else confirm with the user — explaining for each case how the domain data is stored/changed and how the domain solves the feature. Triggers: demo guide, generate demo guide, demo script, demo walkthrough, how to demo, prepare demo, sprint demo, user story demo.
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。
Turns company records into structured company research summaries. Use when the user provides company names or records and wants a consistent overview, market position, and relevance assessment.
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。
Normalizes company names, industries, domains, locations, and descriptions. Use when the user provides company records and wants consistent canonical fields with confidence and unresolved items flagged.
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 inspect the harness memory namespace (HNSW + emergent-time decay).
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。
Replace with what this skill does and when to use it. Include trigger phrases users say, e.g. "audit my API", "scaffold a skill"; activation-critical routing belongs here.
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。
Improves Agent Skills via validate → rule-based eval cases → plugin-eval → prompt evals → bounded edits with held-out gates. Use when tuning skill quality, routing, or adopting Chrome/Microsoft T-named quality gates—not for bulk validate-only or SkillOpt automation.
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。
Telegram CLI for AI agents. Use when the user needs to read or search Telegram, send or edit a message, download media, organise Saved Messages, monitor conversations, or automate a Telegram task. Triggers on “check my messages”, “send a message”, “search Telegram”, “read unread”, “listen to chat”, “download from Telegram”, тэг сохранёнок, чаты, каналы, and @peer names.
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。
Before improving anything, show the spread of what can concretely be done on this specific input — a short menu of 3-5 interventions from lightest to heaviest touch, then wait for the user to pick. Domain-agnostic; works on any material the user hands over. Trigger when the user says "spread", "show me my options", "what can you do with this", or asks to improve or fix something without specifying how. Do NOT trigger when the user has already named a specific fix — then just do the fix.
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。
Route ordinary public-web information tasks to the correct Tavily CLI operation. Use when the task concerns publicly accessible webpages and needs web discovery, clean extraction, URL mapping, same-site crawling, or public-web-only research, but the exact Tavily operation is not yet clear or several operations must be sequenced. Prefer the specific leaf skill when intent is clear: tavily-search for discovery without a URL, tavily-extract for known URLs, tavily-map for URL/site-structure discovery, tavily-crawl for content from many pages on one site, tavily-research for cited multi-source synthesis, and tavily-dynamic-search for programmatic filtering with context isolation. Do not use for named social/community/media/career/code platforms, login or cookie-dependent content, platform-native discussions, or cross-platform collection; use Agent Reach there. Do not use for local files, Git operations, deployments, or ordinary code editing.
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。
Discover ordinary public webpages with LLM-optimized Tavily search results. Use when no specific URL is known and the user needs a quick public-web lookup, articles, recent news, sources, or domain-filtered results. This is the default Tavily leaf for simple public-web discovery. Do not use when the user already supplied the target URL (use tavily-extract), wants URLs under one known site (tavily-map), wants many pages' content (tavily-crawl), needs a full cited synthesis (tavily-research), or needs named platforms, login state, platform-native content, or cross-platform collection (Agent Reach).
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 clean markdown, text, or targeted chunks from one or more known, publicly accessible webpage URLs via the Tavily CLI. Use when the URLs are already supplied or discovered and the user wants page content rather than more URLs. Do not use to find an unknown page (tavily-search), list a site's URL structure (tavily-map), bulk-extract a site section (tavily-crawl), or retrieve named platform, authenticated, cookie-dependent, or platform-native content (Agent Reach). Can process up to 20 public URLs per request.
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。
Produce comprehensive synthesis with explicit citations from multiple ordinary public-web sources via the Tavily CLI. Use for detailed reports, comparisons, market or literature research, and questions whose answer requires multi-source web evidence rather than a quick lookup. Do not use for simple discovery (tavily-search), one known URL (tavily-extract), one-site URL discovery or bulk extraction (tavily-map/crawl), or research centered on named social, community, career, code, media, authenticated, or cross-platform sources (Agent Reach). Takes 30-120 seconds.
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。
Phase 4 Turn 1 of disease-market-sizing-orchestration. Generates report HTML with mandatory citation anchors per fact claim. Reads contract + staging + sources/. Every drug/treatment/stat/recommendation MUST carry [pmid:.../guideline:.../nct:...] anchor that resolves to an actual file in sources/. NEVER hardcode drug names or numerical claims. Use AFTER evidence recall (phase 3), BEFORE content-verification-layer (Turn 2).
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。
Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.
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。
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.
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 this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.
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。