6,405 件 ・ 関連度順
概要と使いどころ
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
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。
Generate the success criteria for a task or question, then review work against them. Given a task, goal, or open-ended question, decompose it into scenarios, evaluation perspectives, and fine-grained weighted YES/NO criteria using the Recursive Expansion Tree (RET) method; if work is supplied, score it criterion-by-criterion and surface what is missing or could be better. Use when asked to self-review or check your own work, judge whether a task is done well or completely, build a definition-of-done or completeness checklist, create an evaluation rubric or grading criteria, score or grade answers to a question, set up an LLM-as-judge rubric, or when the user mentions self-review, completeness check, success criteria, evaluation criteria, scoring rubric, Qworld, or the RET algorithm.
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。
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible 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。
High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.
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。
Drug and chemical toxicity assessment via adverse outcome pathways (AOPs), real-world FAERS adverse event signals, FDA labels, and toxicogenomic associations. Triangulates molecular initiating event to cellular outcome to organ-level toxicity to clinical adverse event. Use for hepatotoxicity/cardiotoxicity/nephrotoxicity prediction and toxicology reports.
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。
TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) live code execution, (A) automated validation, (B) ToolUniverse audit, (E) less-is-more simplification. Core philosophy: each concept appears exactly once; remove don't add; no emojis; single setup entry point. Use when reviewing docs, before releases, after API changes, or when asked to audit, fix, or simplify 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。
Validates docked / generated protein-ligand poses using PoseBusters physical-validity tests, strain energy quantification, geometric checks (planarity, vdW overlap, bond/angle distortion), and pose-energy reasonableness. Filters AI-docking outputs (DiffDock, EquiBind, NeuralPLexer) where ~50% of poses fail physical-validity tests. Use when QC-ing docking results, comparing classical vs ML docking outputs, or filtering pose lists before SAR analysis.
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。
Stellar Assets (classic) + trustlines + Stellar Asset Contract (SAC) bridge to smart contracts. Covers asset issuance, distribution, authorization flags, clawback, regulated assets, trustline management, and the SAC interop layer that exposes classic assets as SEP-41 contract tokens. Use when tokenizing real-world assets, issuing stablecoins, managing trustlines, or bridging classic assets to smart contracts.
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 the competitive landscape for an SCF submission. Identifies similar projects on Stellar and other chains, assesses overlap and differentiation. Use when reviewing or drafting an SCF submission and you need to map similar projects on Stellar and other chains and articulate the differentiation.
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。
Fetch external documents linked in SCF submissions — Google Docs, Google Drive PDFs, GitHub, Notion, IPFS. Use when a submission links to an architecture doc, whitepaper, or technical spec hosted externally. Handles URL transformation for Google services.
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。
Implement replicated appearance data, GenericVisualizer mappings, sprite layers, overlays, and client visual systems.
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。
Generate an XLSX timesheet with logged hours, hourly rates, per-entry amount formulas, and totals for client billing or payroll.
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。
Generate a product listing image with photo, price badge, and promotional text 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。
Generate a multi-sheet XLSX workbook with quarterly revenue, expenses, and summary formulas.
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。
Smoke tests contra URL Vercel deployada (preview ou production). Verifica saude minima do deploy — homepage, assets, auth, console errors, performance. Usa Playwright CLI ou suite de smoke tests. Use apos cada deploy para garantir que nada quebrou.
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。
Android Accessibility Service security analysis and pentesting. Use this skill whenever the user mentions Android security testing, accessibility service abuse, RAT detection, malware analysis, ClayRat, PlayPraetor, overlay phishing, credential harvesting, or any Android app security assessment involving AccessibilityService APIs. This skill helps detect malicious accessibility services, analyze abuse patterns, and harden apps against accessibility-based attacks.
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。
Apply the aoa-safe-infra-change workflow inside an abyss-* repository using repo-relative operational surfaces, explicit local authority notes, rollback posture, and local validation commands. Use when the base infra-change workflow is correct but a thin project overlay is needed for one abyss repo. Do not use when the base skill is sufficient without local adaptation or when the task is really about producing a shareable artifact.
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。
This skill enables Claude to audit access control implementations in various systems. It uses the access-control-auditor plugin to identify potential vulnerabilities and misconfigurations related to access control. Use this skill when the user asks to "audit access control", "check permissions", "assess access rights", or requests a "security review" focused on access management. It's particularly useful for analyzing IAM policies, ACLs, and other access control mechanisms in cloud environments, applications, or infrastructure. The skill helps ensure compliance with security best practices and identify potential privilege escalation paths.
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 you need to design, review, or improve security in Micronaut applications — including micronaut-security authentication, @Secured and intercept-url-map rules, JWT/session strategies, SecurityService checks, CORS, CSRF awareness for browser apps, rejection handlers, and sensitive-data-safe logging. This should trigger for requests such as Add Micronaut security support; Review Micronaut security configuration; Improve API authorization in Micronaut; Add JWT security in Micronaut; Harden Micronaut route authorization rules. Part of cursor-rules-java project
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。
Technical SEO audit across 8 categories: crawlability, indexability, security, URL structure, mobile, Core Web Vitals, structured data, JS rendering. Schema deep validation → seo-schema. AI crawlers → seo-geo-technical. Use when user says "technical SEO", "crawl issues", "robots.txt", "Core Web Vitals".
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。
This skill should be used when agents need to log into websites, retrieve passwords, or access credentials. CRITICAL - always use find_credential with the website URL, never guess item 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。
Check the working conditions of a Japanese job offer item by item against the conditions an employer states in writing, compare the offer letter or 労働条件通知書 with the job posting and what was said in interviews, and separate what is confirmed in writing from what is still only verbal. Use when a user has received an offer, a working-conditions notice, or an employment contract and wants to know what is missing, what conflicts with earlier statements, and what to confirm before the acceptance deadline; do not use to rule on whether the terms are lawful, to decide whether to accept or decline, or to contact the employer on the user's behalf.
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。
Read a Japanese job posting closely and report what it actually states: base pay separated from fixed overtime allowance, the range converted to an hourly basis, required versus preferred requirements, and the terms left ambiguous. Use when a user wants a 求人票 or job description examined before applying, wants two postings compared on the same basis, or wants questions prepared about pay and working conditions; do not use to judge whether the user will be hired, to infer duties the posting does not state, or to evaluate the employer's reputation.
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 a specific company before applying or interviewing by gathering facts from primary and official sources, recording the source and date behind every claim, and keeping anonymous or unverifiable material clearly separated from confirmed fact. Use when a user asks what a company actually does, how it makes money, what its published conditions are, whether a posting matches the company's own disclosures, or what to verify before an interview; do not use to predict hiring outcomes, to repeat review-site content as fact, or to bulk-crawl sites that prohibit automated access.
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。