2797 个 · 按相关度排序
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
中文简介正在准备中。当前显示原文说明。
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
中文简介正在准备中。当前显示原文说明。
Build auditable Excel workbooks headless with openpyxl — blue/black/green cell conventions, formulas over hardcodes, named ranges, balance checks, sensitivity tables. Use for financial models, audit outputs, reconciliations.
中文简介正在准备中。当前显示原文说明。
Build fully-integrated 3-statement models (IS, BS, CF) in Excel with working capital schedules, D&A roll-forwards, debt schedule, and the plugs that make cash and retained earnings tie. Pairs with excel-author.
中文简介正在准备中。当前显示原文说明。
Build institutional-quality DCF valuation models in Excel — revenue projections, FCF build, WACC, terminal value, Bear/Base/Bull scenarios, 5x5 sensitivity tables. Pairs with excel-author. Use for intrinsic-value equity analysis.
中文简介正在准备中。当前显示原文说明。
Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
中文简介正在准备中。当前显示原文说明。
Operating discipline distilled from Claude Fable 5 for sessions and subagents on weaker models (Opus 4.x, Sonnet 5/4.x, Haiku 4.5) doing agentic coding. Load it at the START of any non-trivial task when not running on Fable 5: debugging, refactoring, changes across 2+ files, or unfamiliar code; and instruct a subagent on Opus/Sonnet/Haiku to read this skill with a non-trivial assignment. Triggers include "think like Fable", "fable-mode", "turn on discipline", "work carefully", dispatching a subagent on a weaker model, and repeated mistakes or rework in the session. NOT needed for trivial edits (rename, typo, one-liner) or purely conversational answers.
中文简介正在准备中。当前显示原文说明。
Operating discipline distilled from Claude Fable 5 for sessions and subagents on weaker models (Opus 4.x, Sonnet 5/4.x, Haiku 4.5) doing agentic coding. Load it at the START of any non-trivial task when not running on Fable 5. Операционная дисциплина мышления Fable 5 для менее сильных моделей. Загружай в начале любой нетривиальной задачи (дебаг, рефакторинг, ≥2 файлов, незнакомый код), когда работаешь НЕ на Fable 5 — и указывай сабагенту на Opus/Sonnet/Haiku прочитать этот скилл вместе с нетривиальным заданием. Триггеры — «думай как Fable», «fable-mode», «включи дисциплину», «работай аккуратно», запуск сабагента на слабой модели, повторяющиеся ошибки/переделки в сессии. НЕ нужен для тривиальных правок (rename, опечатка, one-liner) и чисто разговорных ответов.
中文简介正在准备中。当前显示原文说明。
Provides ASR (Automatic Speech Recognition) services via uwebasr.zcu.cz. Use this skill to transcribe audio files in multiple languages (CS, SK, EN, DE, PL, HU, HR, SR, NL) using state-of-the-art models like Zipformer.
中文简介正在准备中。当前显示原文说明。
Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.
中文简介正在准备中。当前显示原文说明。
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations. Use PROACTIVELY for business intelligence or strategic analysis.
中文简介正在准备中。当前显示原文说明。
Validates models and IOptions. DataAnnotations, IValidatableObject, IValidateOptions<T>.
中文简介正在准备中。当前显示原文说明。
Architects Blazor apps. Hosting models, render modes, routing, streaming, prerender.
中文简介正在准备中。当前显示原文说明。
Detects AI-generated deepfake audio used in voice phishing (vishing) attacks by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models. Supports batch analysis of audio files, generates confidence scores, and produces forensic reports. Activates for requests involving deepfake voice detection, vishing investigation, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.
中文简介正在准备中。当前显示原文说明。
This skill covers detecting anomalies in Modbus/TCP and Modbus RTU communications in industrial control systems. It addresses function code monitoring, register range validation, timing analysis, unauthorized client detection, and deep packet inspection for malformed Modbus frames. The skill leverages Zeek with Modbus protocol analyzers, Suricata IDS with OT rules, and custom Python-based detection using Markov chain models for normal Modbus transaction sequences.
中文简介正在准备中。当前显示原文说明。
Detects anomalous authentication patterns using UEBA analytics, statistical baselines, and machine learning models to identify impossible travel, credential stuffing, brute force, password spraying, and compromised account behaviors across authentication logs. Activates for requests involving authentication anomaly detection, login behavior analysis, UEBA implementation, or suspicious sign-in investigation.
中文简介正在准备中。当前显示原文说明。
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
中文简介正在准备中。当前显示原文说明。
[BETA] AEM Cloud Service expert skill — migrate javax.inject.@Inject fields in Sling Model (@Model) classes to injector-specific annotations (@ValueMapValue / @OSGiService / @SlingObject). Self-discoverable (scan for @Model classes with field-level @Inject); the replacement is chosen deterministically from each field's declared type. Use for "fix @Inject in HeroModel.java", "modernize my Sling Models", or when scanning an AEM project for @Inject misuse. Detailed decision table, companion-annotation handling, import management, and file-level skip policy are in recipe.md. This skill is in beta. Verify all outputs before applying them to production projects.
中文简介正在准备中。当前显示原文说明。
Create effective content models for your blocks that are easy for authors to work with. Use this skill anytime you are building new blocks, making changes to existing blocks that modify the initial structure authors work with.
中文简介正在准备中。当前显示原文说明。
Create, edit, fix, or explain Mermaid diagrams for relationships, decision branches, interactions, lifecycles, and data models; also use when the parent selects a diagram to materially clarify an explanation. Do not trigger for simple status, one fact, short lists, quantitative charts, or marketing slides.
中文简介正在准备中。当前显示原文说明。
Creates comprehensive threat models using STRIDE methodology with asset identification, threat enumeration, mitigation strategies, and residual risk assessment. Use for "threat modeling", "security analysis", "STRIDE", or "risk assessment".
中文简介正在准备中。当前显示原文说明。
Creates comprehensive load test plans with realistic scenarios, traffic models, k6 scripts, and success criteria. Use for "load testing", "performance testing", "capacity validation", or "stress testing".
中文简介正在准备中。当前显示原文说明。
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.
中文简介正在准备中。当前显示原文说明。
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
中文简介正在准备中。当前显示原文说明。