Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4…
Score 70/100
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques.
Score 70/100
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal…
Score 70/100
Emil Kowalski's animation best practices for web interfaces. Use when writing, reviewing, or implementing animations in React, CSS, or Framer Motion.
Score 70/100
Emit a real Fn key on macOS (for Typeless push-to-talk, macOS dictation, screenshot shortcuts, emoji picker, Spotlight via globe).
Score 70/100
Use when implementing steganographic text encoding using Unicode Variation Selectors - allows encoding any message invisibly into emojis, letters, or any characters using Unicode…
Score 70/100
Visual language mode. Emoji + short text for faster scanning and fewer output tokens. Three personalities: friendly, professional (default), nightmare.
Score 70/100
Manage emotion detection, LED responses, and mood-based automations for Ezra. Use when working on emotional regulation features, smart home responses, or the Chaos Orb.
Score 70/100
Use when the user's message carries emotional valence — frustration, excitement, exhaustion, urgency, or confusion. Fires whenever tone matters more than information.
Score 70/100
Fait un point émotionnel bref, bienveillant et structuré sans poser de diagnostic. À utiliser quand l'utilisateur dit qu'il se sent mal, stressé, vide, anxieux, triste, irritable…
Score 70/100
Use when animation feels wrong, creates unintended emotional response, or mismatches context
Score 70/100
Use when writing subagent prompts, skill instructions, or any high-stakes task requiring accuracy and truthfulness
Score 70/100
EMP 全栈技能：React 19 脚手架脚本、emp.config.ts 配置、Tailwind v4、微前端 empRuntime、@empjs/valtio 状态管理、React 性能优化。适用于创建 EMP 应用、配置模块联邦、状态管理、性能优化等场景。
Score 70/100
Designs structured employee onboarding programs that reduce time-to-productivity and improve retention.
Score 70/100
SCX Studio Pro projesine yeni katılan veya projeyi derinlemesine öğrenmek isteyen çalışanlar için kapsamlı onboarding, teknik mimari ve kalite kontrol rehberi.
Score 70/100
When the user needs to create or improve content that shapes how candidates and the public perceive the company as a place to work.
Score 70/100
Audit a job matching platform for relevance, fairness, and candidate experience. Evaluates matching algorithm precision and recall, skill taxonomy and NLP extraction, culture fit…
Score 70/100
Draft and fill employment agreement templates — offer letter, IP assignment, PIIA, confidentiality acknowledgement.
Score 70/100
Templates and patterns for creating legally sound employment documentation including contracts, offer letters, and HR policies.
Score 70/100
Guard requests from closing instantly when a tool returns nothing by injecting the sentinel message and logging the event.
Score 70/100
Fail fast when the repository has no refs so downstream bundling never triggers empty Git bundles.
Score 70/100
Android エミュレータでアプリの画面表示や動作をプレビュー確認するためのワークフロー（WSL2 + Gradle + adb）。 このスキルを使うべき場面: エミュレータでプレビューしたい、エミュレータで確認したい、 エミュレータにデプロイして、x86_64 ビルドで試したい、emulator-preview、/emulator-preview。…
Score 70/100
Manages Android SDK, emulators, and AVDs. Use when bootstrapping Android SDK, creating/starting/stopping AVDs, downloading system images, or troubleshooting emulator issues.
Score 70/100
Multi-dimensional insight dispatch system — intelligently matches 12 analysis methods based on meeting/lecture/negotiation/chat recordings.
Score 70/100
當使用者要求「啟用 subagent」、「配置 subagent 權限」、「enable subagents」、「設定 agent 環境」、「fix subagent permissions」時使用此 skill。幫助使用者配置 Claude Code 環境，確保 pr-review-resolver 等 skill 使用的 subagent…
Score 70/100
Implements PWA features and service workers for offline access. Use to cache itineraries and critical travel info for users on the go.
Score 70/100
Scrape, crawl, search, and extract structured data from websites using Firecrawl API - converts web pages to LLM-ready markdown
Score 70/100
A greeting tool written entirely in Brainfuck - the esoteric programming language
Score 70/100
Browser automation tool using Playwright - captures screenshots and extracts content from web pages
Score 70/100
Design and generate curriculum materials for college composition courses (ENC1101 and similar). Use when creating syllabi, assignment prompts, rubrics, lesson plans, scaffolded…
Score 70/100
Hide implementation details behind interfaces - work at domain level (what), not implementation level (how)
Score 70/100
Guides design and generation of 3D-printable enclosures for Arduino/ESP32/RP2040 projects. Use when user needs a case, box, housing, or enclosure for their electronics project.
Score 70/100
Automate Encodian tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Guides efficient learning by prioritizing encoding over retrieval. Use when discussing study strategies, flashcards, active recall, spaced repetition, Anki, or when user asks how…
Score 70/100
Encode, decode, and convert between data formats. Use when working with Base64, URL encoding, hex, Unicode, JWT tokens, hashing, checksums, or converting between serialization…
Score 70/100
Handle text encoding across platforms including UTF-8, Windows codepages, and BOM handling.
Score 70/100
Access ENCORI (StarBase) database for miRNA-target, RNA-RNA, and other regulatory data. Invoke when user asks to search ENCORI or retrieve regulatory interactions.
Score 70/100
Knowledge retrieval from multiple sources. Search docs, web, and code with intelligent routing.
Score 70/100
End the current learning session. Use when done studying to generate summary, update learning plan, and log final entries.
Score 70/100
after making changes, run end-to-end tests to ensure that the product still works
Score 70/100
Use when concluding work on an open-ended goal to write iteration journal entry documenting work performed, decisions made, and state changes
Score 70/100
Diagnose weak endings, rushed resolutions, and arbitrary conclusions. Use when stories build well but end disappointingly, when climax feels unearned, or when resolution doesn't…
Score 70/100
Automate Endorsal tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Guide for creating a new REST API endpoint in the backend
Score 70/100
HTTP probe (status + latency) and TLS certificate inspection (expiry, issuer, SANs).
Score 70/100
Audit a manufacturing energy management system for monitoring quality, cost optimization, and compliance.
Score 70/100
When the user wants to optimize energy supply chains, coordinate oil and gas logistics, or manage energy infrastructure.
Score 70/100
Help users manage their energy for sustained performance. Use when someone is feeling burned out, trying to find their zone of genius, scheduling for productivity, or identifying…
Score 70/100
RAN energy efficiency optimization with cognitive consciousness, predictive power management, and autonomous energy-saving strategies for sustainable network operations.
Score 70/100
Codified expertise for electricity and gas procurement, tariff optimisation, demand charge management, renewable PPA evaluation, and multi-facility energy cost management.
Score 70/100
Building energy simulation and analysis for construction. Calculate heating/cooling loads, evaluate envelope performance, optimize HVAC sizing, and ensure energy code compliance.
Score 70/100
Query grid electricity forecasts and submit load events using EnergyKit to help users optimize home electricity usage.
Score 70/100
Generate EnergyPlus building simulations from natural language descriptions or building images. Use when user asks to 'create building simulation', 'generate IDF', 'simulate…
Score 70/100
Development skill for Enferno Flask framework. Use when implementing features, fixing bugs, or writing code for Enferno-based applications.
Score 70/100
單元測試與代碼提交前觸發。掃描並驗證方法的 pre-conditions、post-conditions 與 invariants，透過契約式設計減少 AI 幻覺。
Score 70/100
Enforce 500-line file size limits. Warn at 400 lines. Guide splitting large files into focused modules. Apply when writing or editing code.
Score 70/100
Apply Single Responsibility Principle when writing code. Keep modules focused, cohesive, and loosely coupled. Guide splitting classes with too many methods.
Score 70/100
Run Claude, Codex, and related coding-agent tasks through policy gates, evidence loops, and auditable execution tiers before risky work proceeds.
Score 70/100
Use when implementing hooks that BLOCK invalid actions, creating quality gates for state transitions, or enforcing tested:true verification.
Score 70/100
EnforceScript component patterns, networking, persistence, and memory management for Enfusion engine
Score 70/100