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...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
13151 zustand-5 gentleman-programming/gentleman-skills
Basic Store import { create } from "zustand"; interface CounterStore { count: number; increment: () => void; decrement: () => void; reset: () => void; } const useCounterStore = create<CounterStore>((set) => ({ count: 0, increment: () => set((state) => ({ count: state.count + 1 })), decrement: () => set((state) => ({ count: state.count - 1 })), reset: () => set({ count: 0 }), })); // Usage function Counter() { const { count, increment, decrement } = useCounterStore(); retur...
 56
13152 checklist-generator oimiragieo/agent-studio
Quality Checklist Generator Overview Generate comprehensive, context-aware quality checklists combining IEEE 1028 standards (80-90%) with LLM-generated contextual items (10-20%). Ensures systematic quality validation before completion. Core principle: Universal quality standards enhanced with project-specific context. When to Use Always: Before completing implementation tasks During code review QA validation phase Pre-commit verification Before marking tasks complete Exceptions: Throwaway protot...
 56
13153 accessibility-auditor patricio0312rev/skills
Accessibility Auditor Build inclusive web experiences with WCAG 2.1 compliance and comprehensive a11y patterns. Core Workflow Audit existing code: Identify accessibility issues Check WCAG compliance: Verify against success criteria Fix semantic HTML: Use proper elements and landmarks Add ARIA attributes: Enhance assistive technology support Implement keyboard nav: Ensure full keyboard accessibility Test with tools: Automated and manual testing Verify with screen readers: Real-world testing WCA...
 56
13154 repo2skill zhangyanxs/repo2skill
repo2skill - Repository to Skill Converter System Instructions You are repo2skill, a specialized assistant that converts GitHub/GitLab/Gitee repositories into comprehensive OpenCode Skills. When a user asks to convert a repository, follow this exact workflow: Step 1: Parse Repository URL Detect platform and extract repository information: Platform Detection Patterns GitHub: github.com/{owner}/{repo} or www.github.com/{owner}/{repo} GitLab: gitlab.com/{owner}/{repo} or www.gitlab.com/{owner}...
 56
13155 godot-genre-simulation thedivergentai/gd-agentic-skills
Genre: Simulation / Tycoon Optimization, systems mastery, and satisfying feedback loops define management games. Available Scripts sim_tick_manager.gd Expert tick-based simulation with variable speed control and batch processing. Core Loop Invest → Build/Manage → Generate Income → Optimize → Expand NEVER Do in Simulation Games NEVER process every simulated entity individually in _process() — Batch updates in fixed ticks (e.g., once per second). Simulating 1000 businesses individually = 60k calls...
 56
13156 dependency-upgrade secondsky/claude-skills
Dependency Upgrade Master major dependency version upgrades, compatibility analysis, staged upgrade strategies, and comprehensive testing approaches. When to Use This Skill Upgrading major framework versions Updating security-vulnerable dependencies Modernizing legacy dependencies Resolving dependency conflicts Planning incremental upgrade paths Testing compatibility matrices Automating dependency updates Semantic Versioning Review MAJOR.MINOR.PATCH (e.g., 2.3.1) MAJOR: Breaking changes MINOR...
 56
13157 react-performance thebushidocollective/han
React Performance Optimization Master react performance optimization for building high-performance, scalable React applications with industry best practices. React.memo and Component Memoization React.memo prevents unnecessary re-renders by memoizing component output: import { memo } from 'react' ; interface Props { name : string ; onClick : ( ) => void ; } // Basic memoization const ExpensiveComponent = memo ( function ExpensiveComponent ( { name , onClick } : Props ) { console . log ( 'Renderi...
 56
13158 cypress-playwright-setup patricio0312rev/skills
Cypress & Playwright Setup Configure comprehensive end-to-end testing for web applications. Core Workflow Choose tool: Cypress or Playwright Configure project: Browser and test settings Create page objects: Reusable selectors Write tests: User journey coverage Setup fixtures: Test data Integrate CI: Automated testing Playwright Setup Installation npm init playwright@latest Configuration // playwright.config.ts import { defineConfig, devices } from '@playwright/test'; export default defineCon...
 56
13159 state-machine-design melodic-software/claude-code-plugins
State Machine Design Skill When to Use This Skill Use this skill when: State Machine Design tasks - Working on statechart and state machine modeling for lifecycle and behavior specification Planning or design - Need guidance on State Machine Design approaches Best practices - Want to follow established patterns and standards Overview Design finite state machines and statecharts for modeling entity lifecycles, workflows, and system behavior. MANDATORY: Documentation-First Approach Before des...
 56
13160 typescript-refactoring-patterns autohandai/community-skills
When you see multiple boolean flags, refactor to discriminated union: ``` // Before interface User { isAdmin: boolean; isGuest: boolean; permissions?: string[]; } // After type User = | { role: 'admin'; permissions: string[] } | { role: 'guest' } | { role: 'member'; permissions: string[] }; ``` Replace Conditional with Polymorphism When you see switch statements on type, use the strategy pattern: ``` // Before function process(item: Item) { switch (item.type) { case 'a':...
 56
13161 speckit-plan dceoy/speckit-agent-skills
Spec Kit Plan Skill When to Use The feature spec is ready and you need a technical implementation plan. Inputs specs/<feature>/spec.md Repo context and .specify/ templates User-provided constraints or tech preferences (if any) If the spec is missing, ask the user to run speckit-specify first. Workflow Setup : Run .specify/scripts/bash/setup-plan.sh --json from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e...
 56
13162 perf-web-optimization tech-leads-club/agent-skills
Web Performance Optimization Systematic approach: Measure → Identify → Prioritize → Implement → Verify. Target Metrics Metric Good Needs Work Poor LCP < 2.5s 2.5-4s > 4s INP < 200ms 200-500ms > 500ms CLS < 0.1 0.1-0.25 > 0.25 TTFB < 800ms 800ms-1.8s > 1.8s Quick Wins 1. Images (usually biggest impact on LCP) <!-- Hero/LCP image: eager + high priority --> < img src = " /hero.webp " alt = " Hero " width = " 1200 " height = " 600 " loading = " eager " fetchpriority = " high " decoding = " async " /...
 56
13163 clinical-trial-schema-designer jorgealves/agent_skills
Clinical Trial Schema Designer Purpose and Intent The clinical-trial-schema-designer bridges the gap between clinical research and data engineering. It helps automate the creation of standardized data structures (CDISC) based on clinical protocols, reducing the manual effort required for data ingestion and submission preparation. When to Use Study Setup : Use during the "Start-up" phase of a clinical trial to design the Electronic Data Capture (EDC) schemas. Data Integration : When merging data ...
 56
13164 godot bfollington/terma
Godot Skill Develop, test, build, and deploy Godot 4.x games. Quick Reference GdUnit4 - Unit testing framework (GDScript, runs inside Godot) godot --headless --path . -s res://addons/gdUnit4/bin/GdUnitCmdTool.gd --run-tests PlayGodot - Game automation framework (Python, like Playwright for games) export GODOT_PATH = /path/to/godot-automation-fork pytest tests/ -v Export web build godot --headless --export-release "Web" ./build/index.html Deploy to Vercel vercel deploy ./build --prod Testing ...
 56
13165 coding-standards expensify/app
Coding Standards & Best Practices Universal coding standards applicable across all projects. When to Activate Starting a new project or module Reviewing code for quality and maintainability Refactoring existing code to follow conventions Enforcing naming, formatting, or structural consistency Setting up linting, formatting, or type-checking rules Onboarding new contributors to coding conventions Code Quality Principles 1. Readability First Code is read more than written Clear variable and functi...
 56
13166 verl-rl-training orchestra-research/ai-research-skills
verl is a flexible, efficient, and production-ready RL training library for large language models from ByteDance's Seed team. It implements the HybridFlow framework (EuroSys 2025) and powers models like Doubao-1.5-pro achieving O1-level performance on math benchmarks. When to Use verl Choose verl when you need: - Production-ready RL training at scale (tested up to 671B parameters) - Flexibility to swap backends (FSDP ↔ Megatron-LM ↔ vLLM ↔ SGLang) - Support for multiple RL algorithms (PPO,...
 56
13167 refine-prompt paulrberg/agent-skills
Context Working directory: ! pwd Request: $ARGUMENTS Task You are an expert prompt engineer. Create an optimized prompt based on $ARGUMENTS . 1. Craft the Prompt Apply relevant techniques: Few-shot examples (when helpful) Chain-of-thought reasoning Role/perspective setting Output format specification Constraints and boundaries Self-consistency checks Structure with: Clear role definition (if applicable) Explicit task description Expected output format Constraints and guidelines 2. Display the Re...
 56
13168 performance sgcarstrends/sgcarstrends
Performance optimization Deep performance optimization based on Lighthouse performance audits. Focuses on loading speed, runtime efficiency, and resource optimization. How it works Identify performance bottlenecks in code and assets Prioritize by impact on Core Web Vitals Provide specific optimizations with code examples Measure improvement with before/after metrics Performance budget Resource Budget Rationale Total page weight < 1.5 MB 3G loads in ~4s JavaScript (compressed) < 300 KB Parsing ...
 56
13169 app-review pollinations/pollinations
App Review Process app submissions from GitHub issues. Validation (registration, duplicates, stars) is pre-done by workflow. Categories Pick the best fit: image , video_audio , writing , chat , games , learn , bots , build , business APPS.md Row Format | EMOJI | Name | Web_URL | Description (~200 chars) | LANG | category | @author | github_id | repo_url | ⭐stars | discord | other | Submitted_Date | Issue_URL | Approved_Date | Submitted_Date : Issue creation date (when user submitted) Issue_URL :...
 56
13170 erpnext-syntax-jinja openaec-foundation/erpnext_anthropic_claude_development_skill_package
ERPNext Jinja Templates Syntax Skill Correct Jinja syntax for Print Formats, Email Templates, and Portal Pages in ERPNext/Frappe v14/v15/v16. When to Use This Skill USE this skill when: Creating or modifying Print Formats Developing Email Templates Building Portal Pages (www/*.html) Adding custom Jinja filters/methods via hooks DO NOT USE for: Report Print Formats (they use JavaScript templating, not Jinja) Client Scripts (use erpnext-syntax-clientscripts) Server Scripts (use erpnext-syntax-serv...
 56
13171 dev-api-design vasilyu1983/ai-agents-public
API Development & Design — Quick Reference Use this skill to design, implement, and document production-grade APIs (REST, GraphQL, gRPC, and tRPC). Apply it for contract design (OpenAPI), versioning/deprecation, authentication/authorization, rate limiting, pagination, error models, and developer documentation. Modern best practices (Jan 2026): HTTP semantics and cacheability (RFC 9110), Problem Details error model (RFC 9457), OpenAPI 3.1+, contract-first + breaking-change detection, strong Aut...
 56
13172 nemo-curator orchestra-research/ai-research-skills
NeMo Curator - GPU-Accelerated Data Curation NVIDIA's toolkit for preparing high-quality training data for LLMs. When to use NeMo Curator Use NeMo Curator when: Preparing LLM training data from web scrapes (Common Crawl) Need fast deduplication (16× faster than CPU) Curating multi-modal datasets (text, images, video, audio) Filtering low-quality or toxic content Scaling data processing across GPU cluster Performance: 16× faster fuzzy deduplication (8TB RedPajama v2) 40% lower TCO vs CPU al...
 56
13173 langsmith-observability orchestra-research/ai-research-skills
LangSmith - LLM Observability Platform Development platform for debugging, evaluating, and monitoring language models and AI applications. When to use LangSmith Use LangSmith when: Debugging LLM application issues (prompts, chains, agents) Evaluating model outputs systematically against datasets Monitoring production LLM systems Building regression testing for AI features Analyzing latency, token usage, and costs Collaborating on prompt engineering Key features: Tracing : Capture inputs, outputs...
 56
13174 architecture-documentation melodic-software/claude-code-plugins
Architecture Documentation When to Use This Skill Use this skill when you need to: Generate architecture documentation for a system Create C4 diagrams (Context, Container, Component) Document architecture for different stakeholder viewpoints Produce technical overviews or executive summaries Keywords: document, c4, container, context, component, viewpoint, architecture description, technical overview, executive summary Document Types Type Audience Content Context All stakeholders System boun...
 56
13175 accessible-motion dylantarre/animation-principles
Accessible Motion Design Apply Disney's 12 animation principles while ensuring accessibility for users with vestibular disorders, motion sensitivity, and cognitive disabilities. Quick Reference Principle Accessible Implementation Squash & Stretch Opacity/color change instead Anticipation State change indication without motion Staging Focus management, not motion-based Straight Ahead / Pose to Pose Instant state changes Follow Through / Overlapping Eliminated or minimal fade Slow In / Slow Out ...
 56
13176 project-onboarding mgd34msu/goodvibes-plugin
When to Use Invoke this skill when: Starting work on an unfamiliar codebase After context is lost (new session) When check_onboarding_performed indicates no memories exist When user asks to "learn about this project" or "understand this codebase" Onboarding Workflow Step 1: Check Existing Knowledge First, check if onboarding was already performed: List files in: .claude/context/memory/ Look for: project-structure.md, build-commands.md, test-commands.md If memories exist, read them and skip to St...
 56
13177 package-script-writer umbraco/umbraco-cms-backoffice-skills
Package Script Writer (psw) Generate and run Umbraco CMS installation scripts using the psw CLI tool. Workflow Check if PSW CLI is installed: psw --version If command not found, the .NET tools path may not be in PATH. Try: Linux/Mac: export PATH="$PATH:$HOME/.dotnet/tools" && psw --version Windows: %USERPROFILE%\.dotnet\tools\psw --version If not installed, install it: dotnet tool install --global PackageScriptWriter.Cli Then run the psw command (see below) Non-Interactive Usage (Claude Code) Th...
 56
13178 reactive-dashboard-performance erichowens/some_claude_skills
Reactive Dashboard Performance Expert in building production-grade reactive dashboards that load in <100ms and have comprehensive test coverage. Core Expertise Performance Patterns (Linear, Vercel, Notion-grade) Skeleton-First Loading Render skeleton immediately (0ms perceived load) Stream in data progressively Never show spinners for <200ms loads Aggressive Caching React Query with staleTime: 5min, cacheTime: 30min Optimistic updates for mutations Prefetch on hover/mount Code Splitting ...
 56
13179 swot-pestle-analysis melodic-software/claude-code-plugins
Strategic Environmental Analysis Perform strategic environmental analysis using SWOT, PESTLE, and Porter's Five Forces frameworks. Creates structured assessments for competitive positioning and strategic planning. What is Strategic Environmental Analysis? Strategic environmental analysis examines internal and external factors that impact an organization's ability to achieve its objectives. Three complementary frameworks provide different perspectives: Framework Focus Perspective Best For SWO...
 56
13180 react-native gentleman-programming/gentleman-skills
React Native Skill Load with: base.md + typescript.md Project Structure project/ ├── src/ │ ├── core/ Pure business logic (no React) │ │ ├── types.ts │ │ └── services/ │ ├── components/ Reusable UI components │ │ ├── Button/ │ │ │ ├── Button.tsx │ │ │ ├── Button.test.tsx │ │ │ └── index.ts │ │ └── index.ts Barrel export │ ├── screens/ Screen components │ │ ├── Home/ │ │ │ ├── HomeScree...
 56
13181 responsive-design owl-listener/designer-skills
Responsive Design When to use this skill New website/app : Layout design for combined mobile-desktop use Legacy improvement : Converting fixed layouts to responsive Performance optimization : Image optimization per device Multiple screens : Tablet, desktop, and large screen support Instructions Step 1: Mobile-First Approach Design from small screens and progressively expand. Example : /* Default: Mobile (320px~) */ .container { padding : 1 rem ; font-size : 14 px ; } .grid { display : grid ; gri...
 56
13182 import-export groeimetai/snow-flow
Import/Export handles data migration, bulk operations, and data transfer. Import/Export Architecture ``` Data Sources ├── Files (CSV, Excel, XML) ├── JDBC Connections └── REST/SOAP Import Process ├── Import Set Tables ├── Transform Maps └── Target Tables Export Process ├── Scheduled Exports ├── Report Exports └── XML Export ``` Key Tables | `sys_import_set` | Import set records | `sys_data_source` | Data sources | `sys_transform_map` | Transfor...
 56
13183 r3f-fundamentals bbeierle12/skill-mcp-claude
React Three Fiber Fundamentals Quick Start import { Canvas } from '@react-three/fiber' import { useRef } from 'react' import { useFrame } from '@react-three/fiber' function RotatingBox() { const meshRef = useRef() useFrame((state, delta) => { meshRef.current.rotation.x += delta meshRef.current.rotation.y += delta * 0.5 }) return ( <mesh ref={meshRef}> <boxGeometry args={[1, 1, 1]} /> <meshStandardMaterial color="hotpink" /> </mesh> ) } export default fun...
 56
13184 chrome-debug zenobi-us/dotfiles
Chrome Debugging and Browser Manipulation via Remote Debugging Protocol Overview Chrome DevTools Protocol (CDP) enables remote browser automation and debugging through mcporter. Key capabilities: Live browser debugging alongside Agent conversations Automated form filling and interaction testing Visual feedback via screenshots Console log and network request inspection JavaScript execution in page context Prerequisites [CRITICAL] Before using Chrome DevTools, ensure: Chrome/Chromium is runni...
 56
13185 b2c-scaffold salesforcecommercecloud/b2c-developer-tooling
B2C Scaffold Skill Use the b2c scaffold commands to generate B2C Commerce components from templates. Tip: If b2c is not installed globally, use npx @salesforce/b2c-cli instead. Examples List Available Scaffolds list all scaffolds b2c scaffold list list only cartridge scaffolds b2c scaffold list --category cartridge show extended info (description, tags) b2c scaffold list -x Generate a Cartridge generate interactively b2c scaffold cartridge generate with name b2c scaffold cartridge --name ap...
 56
13186 docs-writer tech-leads-club/agent-skills
docs-writer skill instructions As an expert technical writer for the Gemini CLI project, your goal is to produce documentation that is accurate, clear, and consistent with the project's standards. You must adhere to the documentation contribution process outlined in CONTRIBUTING.md and the style guidelines from the Google Developer Documentation Style Guide. Step 1: Understand the goal and create a plan Clarify the request: Fully understand the user's documentation request. Identify the core f...
 56
13187 hig-components-content raintree-technology/apple-hig-skills
Apple HIG: Content Components Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Adapt to different sizes and contexts. Content components must work across screen sizes, orientations, and multitasking configurations. Use Auto Layout and size classes. Make content accessible. Charts need audio graph support. Images need alt text. Collections need proper VoiceOver navigation order. All content com...
 56
13188 psi siviter-xyz/dot-agent
PSI - Plan Spec Implement Structured workflow for planning, specifying, and implementing changes with documentation-first approach. When to Use Only use when: Explicitly directed by the user Mentioned in project AGENTS.md file Do not use automatically - this is an opt-in workflow, not a default. Core Workflow Plan → Spec → Implement Phases are independent - you can start with any phase, but all must ensure documentation stays up-to-date. Key Principles Ephemeral planning - Plans stored ...
 56
13189 cron-scheduler aidotnet/moyucode
Cron Scheduler Tool Description Parse, validate, and explain cron expressions. Calculate next run times and generate cron syntax. Trigger /cron command User needs cron expression help User wants to schedule tasks Usage Explain cron expression python scripts/cron_scheduler.py "0 9 * * 1-5" Get next N run times python scripts/cron_scheduler.py "*/15 * * * *" --next 5 Generate cron from description python scripts/cron_scheduler.py --generate "every day at 9am" Validate expression python scripts...
 56
13190 frontend-dev-guidelines bbeierle12/skill-mcp-claude
Frontend Development Guidelines (React · TypeScript · Suspense-First · Production-Grade) You are a senior frontend engineer operating under strict architectural and performance standards. Your goal is to build scalable, predictable, and maintainable React applications using: Suspense-first data fetching Feature-based code organization Strict TypeScript discipline Performance-safe defaults This skill defines how frontend code must be written , not merely how it can be written. 1. Frontend Feasibi...
 56
13191 debug-with-file catlog22/claude-code-workflow
Codex Debug-With-File Prompt Overview Enhanced evidence-based debugging with documented exploration process . Records understanding evolution, consolidates insights, and uses analysis to correct misunderstandings. Core workflow : Explore → Document → Log → Analyze → Correct Understanding → Fix → Verify Key enhancements over /prompts:debug : understanding.md : Timeline of exploration and learning Analysis-assisted correction : Validates and corrects hypotheses Consolidation : Simplifies proven-wr...
 56
13192 docker-git-bash-guide josiahsiegel/claude-plugin-marketplace
Docker on Windows Git Bash / MINGW - Path Conversion Guide This skill provides comprehensive guidance on handling Docker commands in Git Bash (MINGW) on Windows, with specific focus on volume mount path conversion issues and solutions. The Path Conversion Problem When running Docker commands in Git Bash (MINGW) or MSYS2 on Windows, automatic path conversion can cause serious issues with volume mounts and other Docker commands. What Triggers Automatic Conversion MSYS/MINGW shells automatical...
 56
13193 codeup abcfed/claude-marketplace
No SKILL.md available for this skill. View on GitHub
 56
13194 umbraco-skill-validator umbraco/umbraco-cms-backoffice-skills
Skill Content Validator Validates all SKILL.md files in the repository for broken links, missing references, and invalid paths. What This Skill Does Runs deterministic validation script - Fast, consistent checking of all links Generates structured report - JSON output with all issues found Spawns fixer subagent - AI-powered fix suggestions for issues Presents fix plan - Diff-style changes for approval Executes approved fixes - Only applies changes user approves Validation Checks Check Type Descr...
 56
13195 schema-creator oimiragieo/agent-studio
Schema Creator Skill WARNING: DO NOT WRITE DIRECTLY TO .claude/schemas/ Schema files are protected by unified-creator-guard.cjs (Gate 4 in CLAUDE.md). Direct writes bypass post-creation steps (catalog updates, consumer assignment, integration verification). Always use the schema-creator skill workflow for creating schemas. Direct writes create "invisible artifacts" that no validator or agent can discover. Creates JSON Schema validation files for the Claude Code Enterprise Framework. Schemas enfo...
 56
13196 brightdata danielmiessler/personal_ai_infrastructure
Customization Before executing, check for user customizations at: ~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/BrightData/ If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults. Voice Notification When executing a workflow, do BOTH: Send voice notification : curl -s -X POST http://localhost:8888/notify \ -H "Content-Type: application/json" \ -d '{"messa...
 56
13197 python-logging-strategist jorgealves/agent_skills
Python Logging Strategist Purpose and Intent Design structured logging systems with context propagation. Use to ensure Python applications are observable and logs are machine-readable. When to Use Project Setup : When initializing a new Python project. Continuous Integration : As part of automated build and test pipelines. Legacy Refactoring : When updating older Python codebases to modern standards. When NOT to Use Non-Python Projects : This tool is specialized for the Python ecosystem. Error C...
 56
13198 vega markdown-viewer/skills
Vega / Vega-Lite Visualizer Quick Start: Structure data as array of objects → Choose mark type (bar/line/point/area/arc/rect) → Map encodings (x, y, color, size) to fields → Set data types (quantitative/nominal/ordinal/temporal) → Wrap in ```vega-lite or ```vega fence. Always include $schema , use valid JSON with double quotes, field names are case-sensitive. Use Vega-Lite for 90% of charts; Vega only for radar, word cloud, force-directed. Critical Syntax Rules Rule 1: Always Include Schema "$sc...
 56
13199 ccxt-php ccxt/ccxt
CCXT for PHP A comprehensive guide to using CCXT in PHP projects for cryptocurrency exchange integration. Installation Via Composer (REST and WebSocket) composer require ccxt/ccxt Required PHP Extensions cURL mbstring (UTF-8) PCRE iconv gmp (for some exchanges) Optional for Async/WebSocket ReactPHP (installed automatically with ccxt) Quick Start REST API - Synchronous <?php date_default_timezone_set ( 'UTC' ) ; // Required! require_once 'vendor/autoload.php' ; $exchange = new \ ccxt \ binance ( ...
 56
13200 specalign 0xbigboss/claude-code
Spec Alignment Principles (Always Active) These apply whenever a spec file and its corresponding implementation are both in context: Spec and Code Must Agree A spec describes intended behavior; code implements it. When they disagree, one is wrong. Never silently tolerate drift - surface it immediately when noticed. The user decides which is the source of truth for each discrepancy. Do not assume. Drift Categories Type drift : spec defines fields/types that don't match the implementation Behavior...
 56