Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
27,427
总 Skills
160.9M
总安装量
2,740
贡献者
# Skill 仓库 描述 安装量
24051 hccl-test ascend-ai-coding/awesome-ascend-skills
HCCL Performance Test HCCL性能测试工具用于测试HCCL（Huawei Collective Communication Library）集合通信的功能正确性以及性能。 Overview 适用场景 ：分布式训练场景下的集合通信性能测试 源码位置 ： ${INSTALL_DIR}/tools/hccl_test 支持版本 ：CANN 8.3.RC1, CANN 8.5, CANN 25.RC 支持的产品型号 产品系列 最大 Rank 数 备注 Atlas 训练系列产品 4096 - Atlas A2 训练系列产品 32K - Atlas A3 训练系列产品/Atlas A3 推理系列产品 32K AlltoAll/AlltoAllV 最大 8K Atlas 300I Duo 推理卡 - - 核心算子（推荐测试） 分布式训练场景最常用： 算子 可执行文件 通信模式 适用场景 推荐度 AllReduce all_reduce_test 多对多 梯度聚合、参数同步 ⭐⭐⭐ 必测 AllGather all_gather_test 多对多 数据聚合、参数收集 ⭐⭐⭐ 必测...
 44
24052 tauri-svelte-typescript-general oimiragieo/agent-studio
Tauri Svelte Typescript General Skill You are an expert in developing desktop applications using Tauri with Svelte and TypeScript for the frontend. Write clear, technical responses with precise examples for Tauri, Svelte, and TypeScript. Prioritize type safety and utilize TypeScript features effectively. Follow best practices for Tauri application development, including security considerations. Implement responsive and efficient UIs using Svelte's reactive paradigm. Ensure smooth communication b...
 44
24053 zoonk-translations zoonk/zoonk
Internationalization (i18n) Workflow Overview This project uses next-intl for internationalization. Translations are stored in JSON message files. Key Functions Server Components : Use getTranslations (no locale needed) Client Components : Use useTranslations Metadata/Server Actions : Use getTranslations with locale parameter Critical Rules 1. No Dynamic Values in Translation Keys IMPORTANT : The t function does NOT support dynamic values as keys. // BAD: Dynamic key - will NOT work const catego...
 44
24054 retainer structurer eddiebe147/claude-settings
Retainer Structurer Structure retainer packages and recurring revenue models for service businesses When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create retainer structurer retainer structure Review and optimize review retainer structurer Get best practices retainer ...
 44
24055 social crisis manager eddiebe147/claude-settings
Social Crisis Manager Handle social media crises with strategic response and reputation management When to Use This Skill Use this skill when you need to: Enhance team collaboration Improve stakeholder engagement Facilitate clear dialogue Not recommended for: Tasks requiring technical development data analysis Quick Reference Action Command/Trigger Create social crisis manager crisis management Review and optimize review social crisis manager Get best practices social crisis manager best practic...
 44
24056 agentdb memory patterns proffesor-for-testing/agentic-qe
AgentDB Memory Patterns What This Skill Does Provides memory management patterns for AI agents using AgentDB's persistent storage and ReasoningBank integration. Enables agents to remember conversations, learn from interactions, and maintain context across sessions. Performance : 150x-12,500x faster than traditional solutions with 100% backward compatibility. Prerequisites Node.js 18+ AgentDB v1.0.7+ (via agentic-flow or standalone) Understanding of agent architectures Quick Start with CLI Initia...
 44
24057 agenix-secrets edmundmiller/dotfiles
Agenix Secrets Create age-encrypted secrets and wire them into NixOS modules. Repo Secret Layout hosts/<host>/secrets/ ├── secrets.nix Public key → .age file mapping (NOT imported into NixOS) ├── my-secret.age Encrypted secret file └── restic/ Subdirectories supported └── repo.age hosts/shared/secrets/ ├── secrets.nix Shared cross-host secrets └── host-keys.nix Maps hostname → public key for filtering Auto-Wiring modules/agenix.nix auto-generates...
 44
24058 backup-retention-policy dengineproblem/agents-monorepo
Backup Retention Policy Expert Эксперт по управлению жизненным циклом данных и восстановления после сбоев. Правило 3-2-1-1-0 3 копии важных данных (1 основная + 2 резервные) 2 различных типа носителей 1 внешняя/облачная резервная копия 1 автономная/неизменяемая резервная копия 0 ошибок после тестирования Уровни хранения Уровень Доступ Период Стоимость Горячий Частый 0-30 дней $$$ Теплый Периодический 30-90 дней $$ Холодный Редкий 90 дней-7 лет $ Архив Долгосрочный 7+ лет ¢ AWS S3 Lifecycle Polic...
 44
24059 loaders-spinners dylantarre/animation-principles
Loader & Spinner Animation Principles Apply Disney's 12 principles to loading indicators for engaging, informative wait experiences. Principles Applied to Loaders 1. Squash & Stretch Bouncing dot loaders should squash on landing, stretch while rising. Creates life-like, playful motion. 2. Anticipation Before progress completes, bar can briefly pause or slow. Spinners can decelerate before stopping. Signals completion coming. 3. Staging Loader should be clearly visible but not block conten...
 44
24060 openfootball outsharp/shipp-skills
openfootball / football.json API openfootball is a free, open, public domain collection of football (soccer) data. The football.json repository provides pre-built JSON files for major leagues and tournaments worldwide. No API key or authentication is required. Data Sources There are two ways to access the data: 1. Raw GitHub URLs (Primary) https://raw.githubusercontent.com/openfootball/football.json/master/{season}/{league}.json 2. GitHub Pages Mirror https://openfootball.github.io/{country}/{se...
 44
24061 commit-push-pr-workflow yiyousiow000814/xauusd-calendar-agent
Commit, Push & PR Workflow Applies to this repo's conventions: Do not commit directly to main; use a feature branch and a PR. PR/issue titles: English. PR bodies/comments: Simplified Chinese by default (unless the request starts with [EN]). Avoid GitHub CLI --body with escaped newlines; prefer --body-file or stdin to prevent literal \\n. This skill is written to work well on Windows (PowerShell 5.1+). Bash examples are optional. Branch Create a feature branch from main before making changes:...
 44
24062 busirocket-refactor-workflow busirocket/agents-skills
Strict, step-by-step refactoring guidance for maintaining code quality. When to Use Use this skill when: - Refactoring files with multiple exports (use `@file` workflow) - Splitting components/hooks/utils into smaller files - Moving inline types to `types/` - Enforcing post-refactor quality checks Non-Negotiables (MUST) - After any refactor: run the project's standard checks (e.g. `yarn check:all`) as a mandatory quality gate. - If a file has multiple responsibilities, split immediate...
 44
24063 sequential-thinking duc01226/easyplatform
Sequential Thinking Enables structured problem-solving through iterative reasoning with revision and branching capabilities. Core Capabilities Iterative reasoning: Break complex problems into sequential thought steps Dynamic scope: Adjust total thought count as understanding evolves Revision tracking: Reconsider and modify previous conclusions Branch exploration: Explore alternative reasoning paths from any point Maintained context: Keep track of reasoning chain throughout analysis When to Use...
 44
24064 shabbat-times hoodini/ai-agents-skills
Jewish Calendar & Shabbat Times Access Shabbat times and Jewish calendar data via the Hebcal API. Quick Start // Get Shabbat times for a location const response = await fetch( 'https://www.hebcal.com/shabbat?cfg=json&geonameid=5128581&M=on' ); const data = await response.json(); Shabbat Times API By GeoNames ID (Recommended) const url = new URL('https://www.hebcal.com/shabbat'); url.searchParams.set('cfg', 'json'); url.searchParams.set('geonameid', '5128581'); // New York url.searchParams.s...
 44
24065 behavior-driven-testing robotlearning123/behavior-driven-testing
Behavior-Driven Testing Start from user behavior, not code structure. Every user-reachable path must be tested—no branch left uncovered, no edge case assumed. Core Principles Behavior over Implementation - Test what users see, not how code works Exhaustive Coverage - Every branch, every condition, every edge case Context Awareness - Every test must define its preconditions explicitly Real Environment Validation - Mocks are tools, not destinations Workflow Overview Testing follows three phases. F...
 44
24066 interview-scorecard-builder dengineproblem/agents-monorepo
Interview Scorecard Builder Expert in creating structured interview scorecards for consistent, fair candidate evaluation. Core Design Principles Competency-Based Structure Define 4-6 core competencies aligned with role requirements Include both technical and behavioral competencies Map competencies to specific job responsibilities Weight competencies based on role criticality STAR Method Integration Structure questions to elicit Situation, Task, Action, Result responses Provide behavioral indica...
 44
24067 azure-cosmos-java sickn33/antigravity-awesome-skills
Azure Cosmos DB SDK for Java Client library for Azure Cosmos DB NoSQL API with global distribution and reactive patterns. Installation < dependency > < groupId > com.azure </ groupId > < artifactId > azure-cosmos </ artifactId > < version > LATEST </ version > </ dependency > Or use Azure SDK BOM: < dependencyManagement > < dependencies > < dependency > < groupId > com.azure </ groupId > < artifactId > azure-sdk-bom </ artifactId > < version > {bom_version} </ version > < type > pom </ type > < ...
 44
24068 altinity-expert-clickhouse-metrics altinity/skills
Real-Time Metrics Monitoring Real-time monitoring of ClickHouse metrics, events, and asynchronous metrics. Quick Diagnostics 1. Key Health Metrics select 'Running Queries' as metric, (select value from system.metrics where metric = 'Query') as value, '' as unit, if(value > 100, 'High', 'OK') as status union all select 'Memory Usage', (select value from system.asynchronous_metrics where metric = 'MemoryResident'), formatReadableSize(value), if(value > (select va...
 44
24069 retention marketer eddiebe147/claude-settings
Retention Marketer Develop retention strategies to reduce churn and increase customer lifetime value When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create retention marketer retention marketing Review and optimize review retention marketer Get best practices retention...
 44
24070 alpinejs brettatoms/agent-skills
AlpineJS Best Practices Golden Rule: Keep Attributes Short Never put complex logic in HTML attributes. If your x-data , x-init , or any directive exceeds ~50 characters, extract it. Directive Cheatsheet Directive Purpose Example x-data Declare reactive component state x-data="{ open: false }" x-init Run code on component init x-init="fetchData()" x-show Toggle visibility (CSS display) x-show="open" x-if Conditional rendering (must wrap <template> ) <template x-if="show"> x-for Loop (must wrap <t...
 44
24071 responsive-adaptive dylantarre/animation-principles
Responsive & Adaptive Timing Responsive timing adapts duration to context: device capability, travel distance, user preferences, and interaction type. One duration doesn't fit all situations. Disney Principles for Adaptive Motion Context-Aware Application Squash & Stretch: Scale with device - more subtle on mobile (less screen real estate for deformation). Anticipation: Shorter on touch devices - touch users expect faster response than mouse users. Staging: Adapt to viewport - smaller scree...
 44
24072 open-targets-search yorkeccak/scientific-skills
Open Targets Search Search the complete Open Targets database of drug-disease associations and target validation data using natural language queries powered by Valyu's semantic search API. Why This Skill is Powerful No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters Semantic Search: Understands the meaning of your query, not just keyword matching Full-Text Access: Returns complete target-disease association data with evidence ...
 44
24073 model evaluator eddiebe147/claude-settings
Model Evaluator The Model Evaluator skill helps you rigorously assess and compare machine learning model performance across multiple dimensions. It guides you through selecting appropriate metrics, designing evaluation protocols, avoiding common statistical pitfalls, and making data-driven decisions about model selection. Proper model evaluation goes beyond accuracy scores. This skill covers evaluation across the full spectrum: predictive performance, computational efficiency, robustness, fairne...
 44
24074 workflow-project-intake heyvhuang/ship-faster
Project Intake (Brainstorm + Clarify + Route) Treat Skills as "stateless execution units", externalize all state to the file system. This skill is positioned as "project entry / requirements clarification" : When user only has a vague idea: help them clarify requirements (minimum information set) before entering execution chain When user provides repo / clear objectives: quickly confirm understanding, then enter the correct workflow/step This skill is not responsible for actual large-scale imple...
 44
24075 dotnet-api novotnyllc/dotnet-artisan
dotnet-api Overview ASP.NET Core APIs, data access, backend services, security, and cloud-native patterns. This consolidated skill spans 32 topic areas. Load the appropriate companion file from references/ based on the routing table below. Baseline dependency: references/minimal-apis.md defines the core ASP.NET Core Minimal API patterns (route groups, endpoint filters, TypedResults, parameter binding) that apply to most API development tasks. Load it by default when building HTTP endpoints. Most...
 44
24076 changelog cloudflare/cloudflare-docs
You are a witty and enthusiastic product marketer tasked with creating a fun, engaging change log for an internal development team. Your goal is to summarize the latest merges to the main branch, highlighting new features, bug fixes, and giving credit to the hard-working developers. Time Period For daily changelogs: Look at PRs merged in the last 24 hours For weekly summaries: Look at PRs merged in the last 7 days Always specify the time period in the title (e.g., "Daily" vs "Weekly") Default: G...
 44
24077 high-output-management guia-matthieu/clawfu-skills
High Output Management Manage teams the way Andy Grove ran Intel: a manager's output is not what the manager does — it is what their organization produces. This skill turns High Output Management into auditable practice: production principles for knowledge work, output indicators, managerial leverage, meetings as the medium of management, clean decisions, OKRs, and a management style matched to task-relevant maturity. Core Principle A manager's output = the output of their organization + the out...
 44
24078 learning-assessor teachingai/full-stack-skills
本技能帮助您创建各种学习评估工具，包括测验题目、评估标准、评分 rubric 和学习分析。 关键词: 学习评估、测验设计、评分标准、rubric、学习分析、考试题目 核心功能 1. 测验题目设计 - 设计多种题型（选择题、填空题、简答题、论述题等） - 确保题目与学习目标对齐 - 设计不同难度级别的题目 - 创建题目解析和参考答案 2. 评估标准制定 - 制定清晰的评估标准 - 设计评分细则和权重分配 - 创建评分 rubric（评分量规） - 确保评估的客观性和一致性 3. 学习分析 - 分析学习数据和学习趋势 - 识别学习难点和薄弱环节 - 提供个性化学习建议 - 生成学习报告和反馈 4. 评估工具创建 - 创建在线测验和问卷 - 设计项目评估表 - 创建同伴评估工具 - 设计自我评估工具 使用指南 题目设计原则 - 目标对齐: 每道题目都应对应明确的学习目标 - 难度梯度: 题目应覆盖不同认知层次（记忆、理解、应用、分析、评价、创造） - 清晰明确: 题目表述清晰，避免歧义 - 公平性: 确保题目对所有学习者公...
 44
24079 brand-marketing dengineproblem/agents-monorepo
Brand Marketing Animation Apply Disney's 12 animation principles to commercials, advertisements, brand identity, and marketing content. Quick Reference Principle Brand/Marketing Implementation Squash & Stretch Product bounce, logo elasticity Anticipation Build-up to reveal, suspense Staging Product hero shots, focal control Straight Ahead / Pose to Pose Story flow vs key moments Follow Through / Overlapping Logo elements settle, tagline delay Slow In / Slow Out Dramatic reveals, smooth motion ...
 44
24080 runway calculator eddiebe147/claude-settings
Runway Calculator Calculate cash runway, burn rate, and financial sustainability projections When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create runway calculator cash runway Review and optimize review runway calculator Get best practices runway calculator best prac...
 44
24081 unit-converter dkyazzentwatwa/chatgpt-skills
Convert between units across multiple physical dimensions. Features - Multiple Categories: Length, mass, temperature, time, volume, etc. - Compound Units: Speed, density, pressure - Precision Control: Configurable decimal places - Batch Conversion: Convert lists of values - Formula Display: Show conversion formulas Quick Start ``` from unit_converter import UnitConverter converter = UnitConverter() Simple conversion result = converter.convert(100, "km", "miles") print(f"100 km = {re...
 44
24082 data-integrity-auditor patricio0312rev/skills
Data Integrity Auditor Detect and fix data integrity issues automatically. Integrity Check Types 1. Orphaned Records -- Find orphaned orders (no matching user) SELECT o.id, o.user_id FROM orders o LEFT JOIN users u ON u.id = o.user_id WHERE u.id IS NULL; -- Find orphaned order items (no matching order) SELECT oi.id, oi.order_id FROM order_items oi LEFT JOIN orders o ON o.id = oi.order_id WHERE o.id IS NULL; 2. Broken Foreign Keys // scripts/check-foreign-keys.ts async function checkForeignKe...
 44
24083 internal-comms guanyang/antigravity-skills
When to use this skill To write internal communications, use this skill for: 3P updates (Progress, Plans, Problems) Company newsletters FAQ responses Status reports Leadership updates Project updates Incident reports How to use this skill To write any internal communication: Identify the communication type from the request Load the appropriate guideline file from the examples/ directory: examples/3p-updates.md - For Progress/Plans/Problems team updates examples/company-newsletter.md - For compan...
 44
24084 altinity-expert-clickhouse-mutations altinity/skills
Mutation Tracking and Analysis Track and diagnose ALTER UPDATE, ALTER DELETE, and other mutation operations. Quick Diagnostics 1. Current Mutations Status select database, table, mutation_id, command, create_time, is_done, parts_to_do, latest_failed_part, latest_fail_time, latest_fail_reason from system.mutations where not is_done order by create_time 2. Mutation Summary by Table select database, table, countIf(not is_done) as pending, c...
 44
24085 testing-expert personamanagmentlayer/pcl
Testing Expert Skill Expert in testing strategies for React, Next.js, and NestJS applications. When to Use This Skill Writing unit tests Creating integration tests Setting up E2E tests Testing React components Testing API endpoints Testing database operations Setting up test infrastructure Reviewing test coverage Project Context Discovery Scan Documentation: Check .agent/SYSTEM/ARCHITECTURE.md for testing architecture Identify Tools: Jest/Vitest, React Testing Library, Supertest, Playwright/Cy...
 44
24086 sentry tech-leads-club/agent-skills
Sentry (Read-only Observability) Quick start If not already authenticated, ask the user to provide a valid SENTRY_AUTH_TOKEN (read-only scopes such as project:read , event:read ) or to log in and create one before running commands. Set SENTRY_AUTH_TOKEN as an env var. Optional defaults: SENTRY_ORG , SENTRY_PROJECT , SENTRY_BASE_URL . Defaults: org/project {your-org} / {your-project} , time range 24h , environment prod , limit 20 (max 50). Always call the Sentry API (no heuristics, no caching). I...
 44
24087 golang-performance 89jobrien/steve
Persona: You are a Go performance engineer. You never optimize without profiling first — measure, hypothesize, change one thing, re-measure. Thinking mode: Use ultrathink for performance optimization. Shallow analysis misidentifies bottlenecks — deep reasoning ensures the right optimization is applied to the right problem. Modes: Review mode (architecture) — broad scan of a package or service for structural anti-patterns (missing connection pools, unbounded goroutines, wrong data structures). Us...
 44
24088 ml-paper-writing galaxy-dawn/claude-scholar
ML Paper Writing for Top AI Conferences Expert-level guidance for writing publication-ready papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, COLM . This skill combines writing philosophy from top researchers (Nanda, Farquhar, Karpathy, Lipton, Steinhardt) with practical tools: LaTeX templates, citation verification APIs, and conference checklists. For systems venues (OSDI, NSDI, ASPLOS, SOSP) , use the systems-paper-writing skill, which provides paragraph-level structural blueprints, writing pat...
 44
24089 secrets-detection-rules dengineproblem/agents-monorepo
Secrets Detection Rules Expert Expert in pattern matching, regex optimization, false positive reduction, and comprehensive coverage for detecting sensitive credentials in source code. Core Principles detection_philosophy : precision_over_recall : principle : "Minimize false positives" reason : "Too many alerts = alert fatigue = ignored alerts" layered_detection : levels : - "High confidence: Known patterns" - "Medium confidence: Entropy + context" - "Low confidence: Heuristics" entropy_analysis ...
 44
24090 review-vue nesnilnehc/ai-cortex
Skill: Review Vue Purpose Review Vue 3 code for framework conventions only. Do not define scope (diff vs codebase) or perform security/architecture analysis; those are handled by scope and cognitive skills. Emit a findings list in the standard format for aggregation. Focus on Composition API and <script setup> , reactivity (ref/reactive, computed/watch), component boundaries and props/emits, state (Pinia/store), routing and guards, performance (e.g. v-memo), and accessibility where relevant. Cor...
 44
24091 progress-summary epicenterhq/epicenter
Progress Summary Generate conversational summaries of work in progress, using the same style as well-crafted PR descriptions. Core Principles Motivation First Every summary starts with WHY. Not what files changed, not how it works—WHY this work matters. Good opening : We've been tackling the session timeout issue that was logging users out mid-upload. The root cause was the session refresh only triggering on navigation, not during background activity. Bad opening : We added a keepalive call to t...
 44
24092 executing-plans zenobi-us/dotfiles
Executing Plans Overview Load plan, review critically, execute all tasks, report when complete. Announce at start: "I'm using the executing-plans skill to implement this plan." Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill. The Proce...
 44
24093 test-driven-development zenobi-us/dotfiles
Test-Driven Development (TDD) Overview Write the test first. Watch it fail. Write minimal code to pass. Core principle: If you didn't watch the test fail, you don't know if it tests the right thing. Violating the letter of the rules is violating the spirit of the rules. When to Use Always: New features Bug fixes Refactoring Behavior changes Exceptions (ask your human partner): Throwaway prototypes Generated code Configuration files Thinking "skip TDD just this once"? Stop. That's rationalization...
 44
24094 survey analyzer eddiebe147/claude-settings
Survey Analyzer Expert survey research agent that processes survey data, analyzes responses, identifies patterns, and generates actionable insights. Specializes in quantitative analysis, qualitative coding, sentiment analysis, cross-tabulation, and recommendation generation from survey feedback. This skill applies rigorous survey methodology, statistical analysis, and data visualization to transform raw survey responses into clear insights. Perfect for customer feedback, employee engagement, mar...
 44
24095 section-logic-polisher willoscar/research-units-pipeline-skills
Purpose: close the main “paper feel” gap that remains even when a subsection is long and citation-dense: - missing/weak thesis (paragraph 1 never commits to a claim) - weak inter-paragraph flow (paragraph islands; no content-bearing bridges) This is a local, per-H3 polish step that happens after drafting and before merging. What this skill blocks on (and what it does not) Blocking (must fix): - paragraph 1 lacks an explicit thesis / takeaway (a content claim) Non-blocking (diagnostic onl...
 44
24096 ai-code-cleanup 89jobrien/steve
AI Code Cleanup This skill identifies and removes AI-generated artifacts that degrade code quality, including defensive bloat, unnecessary comments, type casts, and style inconsistencies. When to Use This Skill After AI-assisted coding sessions Before code reviews or merging branches When cleaning up code that feels "over-engineered" When removing unnecessary defensive code When standardizing code style after AI generation When preparing code for production What This Skill Does Identifies AI A...
 44
24097 trading-psychology omer-metin/skills-for-antigravity
No SKILL.md available for this skill. View on GitHub
 44
24098 jurisdiction-advisor skala-io/legal-skills
First published on Skala Legal Skills Legal Disclaimer This skill is provided for informational and educational purposes only and does not constitute legal advice. The analysis and information provided should not be relied upon as a substitute for consultation with a qualified attorney. No attorney-client relationship is created by using this skill. Laws and regulations vary by jurisdiction and change over time. Always consult with a licensed attorney in your jurisdiction for advice on specific ...
 44
24099 godot-genre-idle-clicker thedivergentai/gd-agentic-skills
Genre: Idle / Clicker Expert blueprint for idle/clicker games with exponential progression and prestige mechanics. NEVER Do NEVER use standard float for currency — Floats overflow at ~1.8e308. Implement BigNumber (mantissa + exponent) from day 1. NEVER use Timer nodes for revenue — Timers drift and pause when game pauses. Use _process(delta) accumulator for precise timing. NEVER make prestige feel like punishment — Post-prestige runs should be 2-5x faster. Otherwise players feel like they lost p...
 44
24100 brand-agency glebis/claude-skills
Agency Brand Styling Overview To access Agency's official brand identity and style resources, use this skill. The style is based on neobrutalism aesthetic with bold colors, hard shadows, and strong typography. Brand Guidelines Colors Main Colors: Background Light: ffffff - Light backgrounds Foreground Dark: 000000 - Primary text and dark elements Muted: e5e5e5 - Subtle backgrounds, secondary elements Primary Palette: Primary (Orange): e85d04 - Main accent, CTAs, highlights Secondary (Yello...
 44