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...
23,097
总 Skills
69.8M
总安装量
2,536
贡献者
# Skill 仓库 描述 安装量
9801 threejs-game natea/fitfinder
Three.js Game Development You are an expert Three.js game developer. Follow these opinionated patterns when building 3D browser games. Reference : See reference/llms.txt (quick guide) and reference/llms-full.txt (full API + TSL) for official Three.js LLM documentation. Prefer patterns from those files when they conflict with this skill. Performance Notes Take your time with each step. Quality is more important than speed. Do not skip validation steps — they catch issues early. Read the full cont...
 330
9802 salesforce-dx mindrally/skills
Salesforce DX Development You are an expert in Salesforce DX (SFDX) development, including modern Salesforce development workflows, scratch orgs, and source-driven development. Apex Code Standards Implement proper separation of concerns, suggesting to move reusable functions into a Utility class Leverage efficient SOQL queries and prevent queries within loops Implement error handling and create custom exception classes if necessary Apply Salesforce security best practices with CRUD and FLS val...
 330
9803 cloudflare-hyperdrive jezweb/claude-skills
Cloudflare Hyperdrive Status: Production Ready ✅ Last Updated: 2026-01-09 Dependencies: cloudflare-worker-base (recommended for Worker setup) Latest Versions: wrangler@4.58.0, pg@8.16.3+ (minimum), postgres@3.4.8, mysql2@3.16.0 Recent Updates (2025): July 2025: Configurable connection counts (min 5, max ~20 Free/~100 Paid) May 2025: 5x faster cache hits (regional prepared statement caching), FedRAMP Moderate authorization April 2025: Free plan availability (10 configs), MySQL GA support March...
 330
9804 terraform-specialist sickn33/antigravity-awesome-skills
You are a Terraform/OpenTofu specialist focused on advanced infrastructure automation, state management, and modern IaC practices. Use this skill when Designing Terraform/OpenTofu modules or environments Managing state backends, workspaces, or multi-cloud stacks Implementing policy-as-code and CI/CD automation for IaC Do not use this skill when You only need a one-off manual infrastructure change You are locked to a different IaC tool or platform You cannot store or secure state remotely Instruc...
 330
9805 llm-application-dev-prompt-optimize sickn33/antigravity-awesome-skills
Prompt Optimization You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimization. Use this skill when Working on prompt optimization tasks or workflows Needing guidance, best practices, or checklists for prompt optimization Do not use this skill when The task is unrelated to prompt optimization You need a different domain or tool outside this scope Context...
 330
9806 vulnerability-scanner davila7/claude-code-templates
Vulnerability Scanner Think like an attacker, defend like an expert. 2025 threat landscape awareness. 🔧 Runtime Scripts Execute for automated validation: Script Purpose Usage scripts/security_scan.py Validate security principles applied python scripts/security_scan.py <project_path> 📋 Reference Files File Purpose checklists.md OWASP Top 10, Auth, API, Data protection checklists 1. Security Expert Mindset Core Principles Principle Application Assume Breach Design as if attacker already inside...
 330
9807 langsmith-observability davila7/claude-code-templates
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...
 330
9808 blip-2-vision-language davila7/claude-code-templates
BLIP-2: Vision-Language Pre-training Comprehensive guide to using Salesforce's BLIP-2 for vision-language tasks with frozen image encoders and large language models. When to use BLIP-2 Use BLIP-2 when: Need high-quality image captioning with natural descriptions Building visual question answering (VQA) systems Require zero-shot image-text understanding without task-specific training Want to leverage LLM reasoning for visual tasks Building multimodal conversational AI Need image-text retrieva...
 330
9809 tensorrt-llm davila7/claude-code-templates
TensorRT-LLM NVIDIA's open-source library for optimizing LLM inference with state-of-the-art performance on NVIDIA GPUs. When to use TensorRT-LLM Use TensorRT-LLM when: Deploying on NVIDIA GPUs (A100, H100, GB200) Need maximum throughput (24,000+ tokens/sec on Llama 3) Require low latency for real-time applications Working with quantized models (FP8, INT4, FP4) Scaling across multiple GPUs or nodes Use vLLM instead when: Need simpler setup and Python-first API Want PagedAttention without T...
 330
9810 javascript-typescript-typescript-scaffold sickn33/antigravity-awesome-skills
TypeScript Project Scaffolding You are a TypeScript project architecture expert specializing in scaffolding production-ready Node.js and frontend applications. Generate complete project structures with modern tooling (pnpm, Vite, Next.js), type safety, testing setup, and configuration following current best practices. Use this skill when Working on typescript project scaffolding tasks or workflows Needing guidance, best practices, or checklists for typescript project scaffolding Do not use this ...
 330
9811 hyva-cms-components-dump hyva-themes/hyva-ai-tools
Hyvä CMS Component Dump Locates all components.json files from Hyvä CMS modules and outputs a merged JSON object containing all component definitions from active modules. Usage Important: Execute this script from the Magento project root directory. Run the dump script: php <skill_path>/scripts/dump_cms_components.php Where <skill_path> is the directory containing this SKILL.md file (e.g., .claude/skills/hyva-cms-components-dump). Output format: A single JSON object containing all merged ...
 330
9812 ln-401-task-executor levnikolaevich/claude-code-skills
Executes a single implementation (or refactor) task from Todo to To Review using the task description and linked guides. Purpose & Scope - Handle one selected task only; never touch other tasks. - Follow task Technical Approach/plan/AC; apply KISS/YAGNI and guide patterns. - Update Linear/kanban for this task: Todo -> In Progress -> To Review. - Run typecheck/lint; update docs/tests/config per task instructions. - Not for test tasks (label "tests" goes to ln-404-test-executor). Task Sto...
 330
9813 container-debugging aj-geddes/useful-ai-prompts
Container Debugging Overview Container debugging focuses on issues within Docker/Kubernetes environments including resource constraints, networking, and application runtime problems. When to Use Container won't start Application crashes in container Resource limits exceeded Network connectivity issues Performance problems in containers Instructions 1. Docker Debugging Basics Check container status docker ps -a docker inspect <container-id> docker stats <container-id> View container logs doc...
 330
9814 neural network design aj-geddes/useful-ai-prompts
Neural Network Design Overview This skill covers designing and implementing neural network architectures including CNNs, RNNs, Transformers, and ResNets using PyTorch and TensorFlow, with focus on architecture selection, layer composition, and optimization techniques. When to Use Designing custom neural network architectures for computer vision tasks like image classification or object detection Building sequence models for time series forecasting, natural language processing, or video analysis ...
 330
9815 code-metrics-analysis aj-geddes/useful-ai-prompts
Code Metrics Analysis Overview Measure and analyze code quality metrics to identify complexity, maintainability issues, and areas for improvement. When to Use Code quality assessment Identifying refactoring candidates Technical debt monitoring Code review automation CI/CD quality gates Team performance tracking Legacy code analysis Key Metrics Metric Description Good Range Cyclomatic Complexity Number of linearly independent paths 1-10 Cognitive Complexity Measure of code understandability <15...
 330
9816 statistics-math pluginagentmarketplace/custom-plugin-data-engineer
Statistics & Mathematics Mathematical foundations for data science, machine learning, and statistical analysis. Quick Start import numpy as np import scipy.stats as stats from sklearn.linear_model import LinearRegression Descriptive Statistics data = np.array([23, 45, 67, 32, 45, 67, 89, 12, 34, 56]) print(f"Mean: {np.mean(data):.2f}") print(f"Median: {np.median(data):.2f}") print(f"Std Dev: {np.std(data, ddof=1):.2f}") print(f"IQR: {np.percentile(data, 75) - np.percentile(data, 25):.2f}") ...
 330
9817 email-gateway jezweb/claude-skills
Email Gateway (Multi-Provider) Status: Production Ready ✅ Last Updated: 2026-01-10 Providers: Resend, SendGrid, Mailgun, SMTP2Go Quick Start Choose your provider based on needs: Provider Best For Key Feature Free Tier Resend Modern apps, React Email JSX templates 100/day, 3k/month SendGrid Enterprise scale Dynamic templates 100/day forever Mailgun Developer webhooks Event tracking 100/day SMTP2Go Reliable relay, AU Simple API 1k/month trial Resend (Recommended for New Projects) const respons...
 329
9818 create-client-tool cognitedata/dune-skills
Create a Client Tool Scaffold a new AtlasTool named $ARGUMENTS and wire it into the app. Background Client tools let the Atlas Agent invoke logic that runs in the browser — rendering charts, querying local state, showing UI panels, triggering navigation, etc. The agent decides when to call the tool; the app executes it and returns a result. The flow is: Agent responds with a clientTool action The library validates the arguments against the TypeBox schema execute() runs in the browser and returns...
 329
9819 voice-agents davila7/claude-code-templates
Voice Agents You are a voice AI architect who has shipped production voice agents handling millions of calls. You understand the physics of latency - every component adds milliseconds, and the sum determines whether conversations feel natural or awkward. Your core insight: Two architectures exist. Speech-to-speech (S2S) models like OpenAI Realtime API preserve emotion and achieve lowest latency but are less controllable. Pipeline architectures (STT→LLM→TTS) give you control at each step but ad...
 329
9820 browser-extension-builder davila7/claude-code-templates
Browser Extension Builder Role: Browser Extension Architect You extend the browser to give users superpowers. You understand the unique constraints of extension development - permissions, security, store policies. You build extensions that people install and actually use daily. You know the difference between a toy and a tool. Capabilities Extension architecture Manifest v3 (MV3) Content scripts Background workers Popup interfaces Extension monetization Chrome Web Store publishing Cross-brows...
 329
9821 debugging mrgoonie/claudekit-skills
Debugging When to use this skill Encountering runtime errors or exceptions Code produces unexpected output or behavior Performance degradation or memory issues Intermittent or hard-to-reproduce bugs Understanding unfamiliar error messages Post-incident analysis and prevention Instructions Step 1: Gather Information Collect all relevant context about the issue: Error details : Full error message and stack trace Error type (syntax, runtime, logic, etc.) When did it start occurring? Is it reproduci...
 329
9822 cloudflare dmmulroy/cloudflare-skill
Cloudflare Platform Skill Consolidated skill for building on the Cloudflare platform. Use decision trees below to find the right product, then load detailed references. Your knowledge of Cloudflare APIs, types, limits, and pricing may be outdated. Prefer retrieval over pre-training — the references in this skill are starting points, not source of truth. Retrieval Sources Fetch the latest information before citing specific numbers, API signatures, or configuration options. Do not rely on baked-in...
 329
9823 solidity mindrally/skills
Solidity You are an expert in Solidity smart contract development with deep knowledge of security patterns and gas optimization. Core Principles Cut the fluff. Code or detailed explanations only Maintain brevity while prioritizing accuracy and depth Answer first, explain later when needed Code Structure & Security Use explicit visibility modifiers and NatSpec documentation Apply function modifiers to reduce redundancy Follow naming conventions: CamelCase for contracts PascalCase for interfaces...
 329
9824 kysely mindrally/skills
Kysely Development Guidelines You are an expert in Kysely, TypeScript, and SQL database design with a focus on type safety and query optimization. Core Principles Kysely is a thin abstraction layer over SQL, designed by SQL lovers for SQL lovers Full type safety with autocompletion for tables, columns, and query results Predictable 1:1 compilation to SQL - what you write is what you get No magic or hidden behavior - explicit and transparent query building Works with Node.js, Deno, Bun, Cloudflar...
 329
9825 spring-framework mindrally/skills
Spring Framework You are an expert in Java programming, Spring Boot, Spring Framework, Maven, JUnit, and related Java technologies. Code Style and Structure Write clean, efficient, and well-documented Java code with accurate Spring Boot examples Follow camelCase for methods and variables, PascalCase for classes Structure applications with clear separation: controllers, services, repositories, models, and configurations Spring Boot Specifics Utilize Spring Boot starters for quick project setup ...
 329
9826 remix mindrally/skills
Remix Development You are an expert in Remix, React, TypeScript, and full-stack web development. Key Principles Write concise, technical Remix code with accurate TypeScript examples Embrace progressive enhancement and web standards Use loaders for data fetching and actions for mutations Leverage nested routes for code organization Prioritize server-side rendering and web fundamentals Project Structure app/ ├── components/ Reusable React components ├── models/ Database mod...
 329
9827 go mindrally/skills
Go (Golang) You are an expert in Go development with deep knowledge of APIs, microservices, and backend systems. Core Principles Write idiomatic Go code following Go conventions Utilize Go 1.22+ features including new routing capabilities Follow RESTful API design principles Implement proper error handling with custom error types when beneficial Code Organization Clean Architecture principles with handlers, services, repositories, and domain models Interface-driven development with explicit de...
 329
9828 pay-with-any-token uniswap/uniswap-ai
Pay With Tokens Use the Tempo CLI to call paid APIs and handle 402 challenges automatically. When the Tempo wallet has insufficient balance, fund it by swapping and bridging tokens from any EVM chain using the Uniswap Trading API . Tempo CLI Setup Run these commands in order. Do not skip steps. Step 1 — Install: mkdir -p " $HOME /.local/bin" \ && curl -fsSL https://tempo.xyz/install -o /tmp/tempo_install.sh \ && TEMPO_BIN_DIR = " $HOME /.local/bin" bash /tmp/tempo_install.sh Step 2 — Login (requ...
 329
9829 agent-skills-creator mblode/agent-skills
Agent Skills Creator Create skills that follow the Agent Skills open format. Covers the full lifecycle from pattern selection through validation and README update. Reference Files File Read When references/format-specification.md Default: frontmatter constraints, directory structure, naming rules references/skill-patterns.md Choosing a pattern or need a structural template for a specific skill type references/quality-checklist.md Final validation before shipping Choose a Skill Pattern Pattern Wh...
 329
9830 usage-based-billing dodopayments/skills
Reference: [docs.dodopayments.com/features/usage-based-billing](https://docs.dodopayments.com/features/usage-based-billing/introduction) Charge customers for what they actually use—API calls, storage, AI tokens, or any metric you define. Overview Usage-based billing is perfect for: - APIs: Charge per request or operation - AI Services: Bill per token, generation, or inference - Infrastructure: Charge for compute, storage, bandwidth - SaaS: Metered features alongside subscriptions Core ...
 329
9831 home-assistant-awtrix bradsjm/hassio-addons
AWTRIX Workflow Use the bundled awtrix_fs.py script for deterministic filesystem operations and LaMetric icon imports. Use absolute device paths (leading / ) to avoid firmware path errors. Use references for endpoint behavior and MQTT/HA integration patterns. Quick start All script and reference files are relative to the location of this SKILL.md file. python3 scripts/awtrix_fs.py --host < ip > status python3 scripts/awtrix_fs.py --host < ip > icons list python3 scripts/awtrix_fs.py --host < ip ...
 329
9832 notion-spec-to-implementation davila7/claude-code-templates
Spec to Implementation Convert a Notion spec into linked implementation plans, tasks, and ongoing status updates. Quick start Locate the spec with Notion:notion-search , then fetch it with Notion:notion-fetch . Parse requirements and ambiguities using reference/spec-parsing.md . Create a plan page with Notion:notion-create-pages (pick a template: quick vs. full). Find the task database, confirm schema, then create tasks with Notion:notion-create-pages . Link spec ↔ plan ↔ tasks; keep status curr...
 329
9833 quantizing-models-bitsandbytes davila7/claude-code-templates
bitsandbytes - LLM Quantization Quick start bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss. Installation: pip install bitsandbytes transformers accelerate 8-bit quantization (50% memory reduction): from transformers import AutoModelForCausalLM, BitsAndBytesConfig config = BitsAndBytesConfig(load_in_8bit=True) model = AutoModelForCausalLM.from_pretrained( "meta-llama/Llama-2-7b-hf", quantization_config=config, device_map="auto" ) Memory: ...
 329
9834 algorithmic-art davila7/claude-code-templates
Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms). This happens in two steps: Algorithmic Philosophy Creation (.md file) Express by creating p5.js generative art (.html + .js files) First, undertake this task: ALGORITHMIC PHILOSOPHY CREATION To begin, create an ALGORITHMIC PHILOSOPHY (not static images or templates) that will be interpreted thr...
 329
9835 conductor-new-track sickn33/antigravity-awesome-skills
New Track Create a new track (feature, bug fix, chore, or refactor) with a detailed specification and phased implementation plan. Use this skill when Working on new track tasks or workflows Needing guidance, best practices, or checklists for new track Do not use this skill when The task is unrelated to new track You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionab...
 329
9836 postgres-best-practices sickn33/antigravity-awesome-skills
Supabase Postgres Best Practices Comprehensive performance optimization guide for Postgres, maintained by Supabase. Contains rules across 8 categories, prioritized by impact to guide automated query optimization and schema design. When to Apply Reference these guidelines when: Writing SQL queries or designing schemas Implementing indexes or query optimization Reviewing database performance issues Configuring connection pooling or scaling Optimizing for Postgres-specific features Working with Row...
 329
9837 analytics-tracking davila7/claude-code-templates
Analytics Tracking You are an expert in analytics implementation and measurement. Your goal is to help set up tracking that provides actionable insights for marketing and product decisions. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Before implementi...
 329
9838 bankr agent - transfers bankrbot/claude-plugins
Bankr Transfers Transfer tokens to addresses, ENS names, or social handles. Supported Transfers EVM Chains : Base, Polygon, Ethereum, Unichain (ETH, MATIC, ERC20 tokens) Solana : SOL and SPL tokens Recipient Formats Format Example Description Address 0x1234...abcd Direct wallet address ENS vitalik.eth Ethereum Name Service Twitter @elonmusk Twitter/X username Farcaster @dwr.eth Farcaster username Telegram @username Telegram handle Show more
 329
9839 router-first-architecture parcadei/continuous-claude-v3
Router-First Architecture Route through domain routers before using individual tools. Routers abstract tool selection. Pattern Domain routers (like math-router) provide deterministic mapping from user intent to exact CLI commands. Always use the router first; only bypass for edge cases. DO Call math-router route "<intent>" before any math operation Let domain skills co-activate with their router (via coActivate in skill-rules.json) Trust the router's confidence score; only fall back if comma...
 329
9840 readwise-cli readwiseio/readwise-skills
Readwise CLI Use the readwise command to access the user's Readwise highlights and Reader documents. Readwise has two products: Readwise — highlights from books, articles, podcasts, and more. Includes daily review and spaced repetition. Reader — a read-later app for saving and reading articles, PDFs, EPUBs, RSS feeds, emails, tweets, and videos. Setup If readwise is not installed: npm install -g @readwise/cli If not authenticated, ask the user for their Readwise access token (they can get one at...
 329
9841 nansen-portfolio-tracker nansen-ai/nansen-cli
Portfolio History Answers: "How has this wallet's portfolio evolved over the past month?" ADDR = < address > CHAIN = ethereum nansen research profiler historical-balances --address $ADDR --chain $CHAIN --days 30 --limit 20 → block_timestamp, token_symbol, token_amount, value_usd, chain nansen research profiler balance --address $ADDR --chain $CHAIN → token_symbol, token_name, token_amount, price_usd, value_usd nansen research profiler pnl --address $ADDR --chain $CHAIN --days 30 --limit 20 → ...
 329
9842 ln-522-manual-tester levnikolaevich/claude-code-skills
Paths: File paths ( shared/ , references/ , ../ln-* ) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Inputs Input Required Source Description storyId Yes args, git branch, kanban, user Story to process Resolution: Story Resolution Chain. Status filter: To Review Manual Tester Manually verifies Story AC on running code and reports structured results for the quality gate. Purpose & Scope Create executable test scripts in tes...
 329
9843 sandbox-guard useai-pro/openclaw-skills-security
Sandbox Guard You are a sandbox configuration generator for OpenClaw. When a user wants to run an untrusted skill, you generate a secure Docker-based sandbox that isolates the skill from the host system. Why Sandbox OpenClaw skills run with the permissions they request. A malicious skill with shell access can compromise your entire system. Sandboxing limits the blast radius. Sandbox Profiles Profile: Minimal (for read-only skills) FROM node:20-alpine RUN adduser -D -h /workspace openclaw WORKDIR...
 329
9844 alphaear-search rkiding/awesome-finance-skills
AlphaEar Search Skill Overview Unified search capabilities: web search (Jina/DDG/Baidu) and local RAG search. Capabilities 1. Web Search Use scripts/search_tools.py via SearchTools . Search : search(query, engine, max_results) Engines: jina , ddg , baidu , local . Returns: JSON string (summary) or List[Dict] (via search_list ). Smart Cache (Agentic) : If you want to avoid redundant searches, use the Search Cache Relevance Prompt in references/PROMPTS.md . Read the cache first and decide if it's ...
 329
9845 pdf-reader childbamboo/claude-code-marketplace-sample
PDF Reader PDF ファイルをテキスト抽出して Markdown 形式に変換するスキルです。 クイックスタート 基本的な使い方 WSL環境でPythonスクリプトを実行 wsl python3 scripts/read_pdf.py "/mnt/c/path/to/file.pdf" Markdown形式で保存 スクリプトでテキスト抽出 Write ツールで .md ファイルに保存 前提条件 pdfplumber パッケージが必要です： wsl pip3 install pdfplumber 使用例 例1: PDF ファイルを読み込んで内容を表示 User: "C:\Users\keita\repos\guideline.pdf を読み込んで" Assistant: 1. Windowsパスを WSL パスに変換: /mnt/c/Users/keita/repos/guideline.pdf 2. wsl python3 scripts/read_pdf.py を実行 3. 抽出されたテキストを Markdown 形式で表示 例2: PDF を Markdown に変換して...
 329
9846 infrastructure-monitoring aj-geddes/useful-ai-prompts
Infrastructure Monitoring Overview Implement comprehensive infrastructure monitoring to track system health, performance metrics, and resource utilization with alerting and visualization across your entire stack. When to Use Real-time performance monitoring Capacity planning and trends Incident detection and alerting Service health tracking Resource utilization analysis Performance troubleshooting Compliance and audit trails Historical data analysis Implementation Examples 1. Prometheus Config...
 329
9847 api-versioning-strategy aj-geddes/useful-ai-prompts
API Versioning Strategy Overview Comprehensive guide to API versioning approaches, deprecation strategies, backward compatibility techniques, and migration planning for REST APIs, GraphQL, and gRPC services. When to Use Designing new APIs with versioning from the start Adding breaking changes to existing APIs Deprecating old API versions Planning API migrations Ensuring backward compatibility Managing multiple API versions simultaneously Creating API documentation for different versions Implem...
 329
9848 harmonyos-app majiayu000/claude-arsenal
HarmonyOS Application Development Core Principles ArkTS First — Use ArkTS with strict type safety, no any or dynamic types Declarative UI — Build UI with ArkUI's declarative components and state management Stage Model — Use modern Stage model (UIAbility), not legacy FA model Distributed by Design — Leverage cross-device capabilities from the start Atomic Services — Consider atomic services and cards for lightweight experiences One-time Development — Design for multi-device adaptation (phone, tab...
 329
9849 excel-automation daymade/claude-code-skills
Excel Automation Skill Overview This skill enables advanced Excel automation using xlwings - a library that can interact with live Excel instances. Unlike openpyxl (file-only), xlwings can control Excel in real-time, execute VBA, update dashboards, and automate complex workflows. How to Use Describe the Excel automation task you need Specify if you need live Excel interaction or file processing I'll generate xlwings code and execute it Example prompts: "Update this live Excel dashboard with new ...
 329
9850 email-sequence davila7/claude-code-templates
Email Sequence Design You are an expert in email marketing and automation. Your goal is to create email sequences that nurture relationships, drive action, and move people toward conversion. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Before creating ...
 328