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...
25,639
总 Skills
101.7M
总安装量
2,629
贡献者
# Skill 仓库 描述 安装量
8451 antv-g2-chart antvis/chart-visualization-skills
G2 v5 Chart Code Generator You are an expert in AntV G2 v5 charting library. Generate accurate, runnable code following G2 v5 best practices. 1. Core Constraints / 核心约束 (MUST follow) container is mandatory : new Chart({ container: 'container', ... }) Use Spec Mode ONLY : chart.options({ type: 'interval', data, encode: {...} }) （V4 链式 API 见 Forbidden Patterns） chart.options() 只能调用一次 ：多次调用会完整覆盖前一次配置，只有最后一次生效。多 mark 叠加必须用 type: 'view' + children 数组，而不是多次调用 chart.options() encode object : encode: { ...
 845
8452 docx ailabs-393/ai-labs-claude-skills
DOCX creation, editing, and analysis Overview A .docx file is a ZIP archive containing XML files. Quick Reference Task Approach Read/analyze content pandoc or unpack for raw XML Create new document Use docx-js - see Creating New Documents below Edit existing document Unpack → edit XML → repack - see Editing Existing Documents below Converting .doc to .docx Legacy .doc files must be converted before editing: python scripts/office/soffice.py --headless --convert-to docx document.doc Reading Conten...
 845
8453 test-scenario owl-listener/designer-skills
Test Scenario You are an expert in writing usability test scenarios that reveal genuine user behavior. What You Do You write test scenarios with realistic tasks, clear success criteria, and structured observation guides. Scenario Structure Context Setting Brief, realistic backstory that gives the participant a reason to act without leading them. Task Specific goal to accomplish. Action-oriented, not question-based. Avoids UI terminology that hints at the answer. Success Criteria Task completion ...
 845
8454 pattern-library owl-listener/designer-skills
Pattern Library You are an expert in documenting reusable design patterns that solve recurring UX problems. What You Do You create pattern library entries capturing design knowledge in a reusable format. Pattern Entry Structure Problem Statement — What need does this address? What contexts? Solution — The pattern, key principles, visual/interaction description Anatomy — Components, layout, required vs optional elements Variants — Context-specific implementations, responsive adaptations Behavior ...
 845
8455 pyqt6-ui-development-rules oimiragieo/agent-studio
Pyqt6 Ui Development Rules Skill Create stunning, responsive user interfaces that rival the best web designs. Implement advanced PyQt6 features for smooth user experiences. Optimize performance and resource usage in GUI applications. Craft visually appealing interfaces with attention to color theory and layout. Ensure accessibility and cross-platform compatibility. Implement responsive designs that adapt to various screen sizes. Memory Protocol (MANDATORY) Before starting: cat .claude/context/...
 845
8456 design-rationale owl-listener/designer-skills
Design Rationale You are an expert in articulating the reasoning behind design decisions. What You Do You write clear design rationale that connects decisions to evidence, principles, and goals. Rationale Structure 1. Decision What design decision was made? Be specific about what was chosen. 2. Context What problem or need prompted this decision? What constraints exist? 3. Options Considered What alternatives were explored? Brief description of each. 4. Evidence What informed the decision? User ...
 845
8457 m07-concurrency zhanghandong/rust-skills
Concurrency Layer 1: Language Mechanics Core Question Is this CPU-bound or I/O-bound, and what's the sharing model? Before choosing concurrency primitives: What's the workload type? What data needs to be shared? What's the thread safety requirement? Error → Design Question Show more
 844
8458 link-building kostja94/marketing-skills
SEO Off-Page: Link Building Guides link building strategy: acquiring quality backlinks to improve domain authority and rankings. When invoking : On first use , if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Scope (Off-Page SEO) Link building : Acquire backlinks from relevant, authoritative sites Broken link building : Find broken links on others' sites...
 844
8459 blog-schema agricidaniel/claude-blog
Blog Schema: JSON-LD Structured Data Generation Generates complete, validated JSON-LD schema markup for blog posts using the @graph pattern. Combines multiple schema types into a single script tag with stable @id references for entity linking. Workflow Step 1: Read Content Show more Installs 722 Repository agricidaniel/claude-blog GitHub Stars 1.3K First Seen Feb 26, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 844
8460 metrics-definition owl-listener/designer-skills
Metrics Definition You are an expert in defining meaningful UX metrics that demonstrate design impact. What You Do You help teams define metrics connecting design work to measurable outcomes. Metric Categories Behavioral : Task completion, time on task, error rate, feature adoption Attitudinal : SUS, NPS, CSAT, perceived ease of use Business : Conversion, retention, support volume, onboarding completion Engagement : DAU/MAU, session duration, feature discovery, return visits HEART Framework Happ...
 844
8461 design-sprint-plan owl-listener/designer-skills
Design Sprint Plan You are an expert in planning and facilitating design sprints. What You Do You plan structured design sprints that take teams from challenge to tested prototype in a focused timeframe. Sprint Structure (5-Day Classic) Day 1: Understand Define the challenge and sprint questions Expert interviews and lightning talks Map the user journey Choose a target area to focus on Day 2: Diverge Lightning demos of inspiration Individual sketching (Crazy 8s, solution sketches) Silent critiqu...
 844
8462 tracing-downstream-lineage astronomer/agents
Downstream Lineage: Impacts Answer the critical question: "What breaks if I change this?" Use this BEFORE making changes to understand the blast radius. Impact Analysis Step 1: Identify Direct Consumers Find everything that reads from this target: For Tables: Search DAG source code: Look for DAGs that SELECT from this table Use list_dags to get all DAGs Use get_dag_source to search for table references Look for: FROM target_table, JOIN target_table Check for dependent views: -- Snowflak...
 844
8463 profiling-tables astronomer/agents
Data Profile Generate a comprehensive profile of a table that a new team member could use to understand the data. Step 1: Basic Metadata Query column metadata: SELECT COLUMN_NAME, DATA_TYPE, COMMENT FROM <database>.INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = '<schema>' AND TABLE_NAME = '<table>' ORDER BY ORDINAL_POSITION If the table name isn't fully qualified, search INFORMATION_SCHEMA.TABLES to locate it first. Step 2: Size and Shape Run via run_sql: SELECT COUNT(*) as total_r...
 844
8464 retro boshu2/agentops
Sprint Retrospective Facilitator Run a structured retrospective that surfaces insights and produces actionable improvements. Context You are facilitating a retrospective for $ARGUMENTS . If the user provides files (sprint data, velocity charts, team feedback, or previous retro notes), read them first. Instructions Choose a retro format based on context (or let the user pick): Format A — Start / Stop / Continue : Start : What should we begin doing? Stop : What should we stop doing? Continue : Wha...
 843
8465 trace boshu2/agentops
Trace Skill Quick Ref: Trace design decisions through CASS sessions, handoffs, git, and artifacts. Output: .agents/research/YYYY-MM-DD-trace-*.md YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it. When to Use Trace HOW architectural decisions evolved Find WHEN a concept was introduced Understand WHY something was designed a certain way Build provenance chain for design decisions For knowledge artifact lineage (learnings, patterns, tiers), use /provenance instead. CLI dependencies: cass (se...
 843
8466 feishu-cli-import riba2534/feishu-cli
Markdown 导入技能 从本地 Markdown 文件创建或更新飞书云文档。 支持 Mermaid/PlantUML 图表转飞书画板、大表格自动拆分 。 CRITICAL： 每次创建新文档后， 必须立即 执行以下两步： 授予 full_access 权限： feishu-cli perm add <document_id> --doc-type docx --member-type email --member-id user@example.com --perm full_access --notification 转移文档所有权： feishu-cli perm transfer-owner <document_id> --doc-type docx --member-type email --member-id user@example.com --notification 详见下方"执行流程 → 创建新文档"。 核心特性 三阶段并发管道 ：顺序创建块 → 并发处理图表/表格 → 失败回退 Mermaid/PlantUML → 飞书画板 ： mermaid / plantum...
 843
8467 muapi-media-editing samuraigpt/generative-media-skills
✏️ MuAPI Media Editing & Enhancement Advanced editing and enhancement operations for images and videos. Apply AI-powered edits, enhancements, and effects to existing media. Supports prompt-based editing with Flux Kontext, GPT-4o, and Midjourney, plus one-click operations like upscaling and background removal. Available Scripts Script Description edit-image.sh Prompt-based image editing (Flux Kontext, GPT-4o, Midjourney, Qwen, and more) enhance-image.sh One-click operations: upscale, background r...
 843
8468 gdpr-dsgvo-expert alirezarezvani/claude-skills
GDPR/DSGVO Expert Tools and guidance for EU General Data Protection Regulation (GDPR) and German Bundesdatenschutzgesetz (BDSG) compliance. Table of Contents Tools GDPR Compliance Checker DPIA Generator Data Subject Rights Tracker Reference Guides Workflows Tools Show more
 843
8469 mvcc tursodatabase/turso
Multi-Version Concurrency Control. Work in progress, not production-ready. CRITICAL: Ignore MVCC when debugging unless the bug is MVCC-specific. Enabling MVCC ``` PRAGMA journal_mode = 'experimental_mvcc'; ``` Runtime configuration, not a compile-time feature flag. Per-database setting. How It Works Standard WAL: single version per page, readers see snapshot at read mark time. MVCC: multiple row versions, snapshot isolation. Each transaction sees consistent snapshot at begin time. Ke...
 843
8470 ticket-resolution hubspot/agent-cli-skills
Read bulk-operations/SKILL.md first — JSONL piping, batch read, pagination, dry-run/digest/confirm, and hubspot history recovery live there. hubspot <command> --help is authoritative. Tickets use the tickets object type (plural, e.g. tickets:45123 ). 1. Discover pipeline + stages (portal-specific, run every session) Stage IDs differ in every portal — never hard-code them. hubspot pipelines list --type tickets --format table hubspot pipelines stages --type tickets --pipeline < pipeline_id > --for...
 843
8471 seedance infsh-skills/skills
Install the belt CLI skill: npx skills add belt-sh/cli Seedance 2.0 Video Generation Generate videos with synchronized audio using ByteDance's Seedance 2.0 via inference.sh CLI. Quick Start Requires inference.sh CLI ( belt ). Install instructions belt login belt app run bytedance/seedance-2-0 --input '{ "prompt": "a jazz band performing in a dimly lit club", "generate_audio": true }' Show more Installs – Repository inference-sh-sk…s/skills GitHub Stars 585 First Seen – Security Audits Gen Agent ...
 842
8472 nemoclaw-user-configure-inference nvidia/skills
Use a Local Inference Server Gotchas Ollama is convenient for local chat, but some model/template combinations can return tool calls as plain text under realistic agent load. Prerequisites NemoClaw installed. A local model server running, or a supported Ollama, vLLM, or NIM setup that the NemoClaw onboard wizard can use, start, or install. NemoClaw can route inference to a model server running on your machine instead of a cloud API. This page covers Ollama, compatible-endpoint paths for other se...
 842
8473 investigating-agentforce-architecture forcedotcom/sf-skills
investigating-agentforce-architecture — declared architecture snapshot Design-time metadata tree for one Agentforce agent: planner → topics → actions → flows → Apex → prompts → NGA plugins. Reads declared metadata only — BotDefinition , GenAiPlanner* , GenAiPlugin* , GenAiFunction* , Flow , ApexClass , GenAiPromptTemplate . Does not read runtime audit rows. Runtime budget: 30–45s typical, ≤60s hard cap on reference fixtures. Sequential baseline would be 90–220s; parallel Tooling SOQL fan-out del...
 842
8474 ux-researcher-designer alirezarezvani/claude-skills
UX Researcher & Designer Comprehensive toolkit for user-centered research and experience design. Core Capabilities Data-driven persona generation Customer journey mapping Usability testing frameworks Research synthesis and insights Design validation methods Key Scripts persona_generator.py Creates research-backed personas from user data and interviews. Usage: python scripts/persona_generator.py [json] Features: Analyzes user behavior patterns Identifies persona archetypes Extracts psychogr...
 842
8475 design-review-process owl-listener/designer-skills
Design Review Process You are an expert in establishing design review processes that maintain quality without slowing teams down. What You Do You create review processes with clear gates, criteria, and workflows that ensure design quality. Review Gates Gate 1: Concept Review Problem clearly defined User needs supported by research Multiple concepts explored Strategic alignment confirmed Stakeholder input gathered Gate 2: Design Review Visual design meets brand standards Interaction patterns are ...
 842
8476 setting-up-astro-project astronomer/agents
Astro Project Setup This skill helps you initialize and configure Airflow projects using the Astro CLI. To run the local environment, see the managing-astro-local-env skill. To write DAGs, see the authoring-dags skill. Initialize a New Project astro dev init Creates this structure: project/ ├── dags/ DAG files ├── include/ SQL, configs, supporting files ├── plugins/ Custom Airflow plugins ├── tests/ Unit tests ├── Dockerfile ...
 842
8477 differential-fuzzer tursodatabase/turso
Always load [Debugging skill for reference](https://github.com/tursodatabase/turso/blob/main/.claude/skills/differential-fuzzer/../debugging/) The differential fuzzer compares Turso results against SQLite for generated SQL statements to find correctness bugs. Location `testing/differential-oracle/fuzzer/` Running the Fuzzer Single Run ``` Basic run (100 statements, random seed) cargo run --bin differential_fuzzer With specific seed for reproducibility cargo run --bin differential_fuz...
 842
8478 recoup-platform-email-helper recoupable/skills
Sending email from a task Send email by running the bundled Node script — do not assemble JSON in the shell. Why this exists Hand-rolling the send ( curl -sS … -d "{… \"html\": $(echo "$HTML" | jq -R -s '.') …}" ) is fragile: depending on quoting/escaping it produces a malformed body , and the API used to silently deliver an empty footer-only email titled "Message from Recoup" with success:true . The model gets this wrong stochastically. This script removes shell serialization entirely. How to s...
 842
8479 rag-engineer sickn33/antigravity-awesome-skills
RAG Engineer Role: RAG Systems Architect I bridge the gap between raw documents and LLM understanding. I know that retrieval quality determines generation quality - garbage in, garbage out. I obsess over chunking boundaries, embedding dimensions, and similarity metrics because they make the difference between helpful and hallucinating. Capabilities Vector embeddings and similarity search Document chunking and preprocessing Retrieval pipeline design Semantic search implementation Context windo...
 842
8480 handle-complaint anthropics/knowledge-work-plugins
Run the complaint resolution workflow by chaining two skills. Read the complaint, gather context, draft a response, and suggest a fix so it doesn't happen again. Parse arguments: EMAIL_OR_TICKET_ID (optional) — Gmail thread ID, HubSpot ticket ID, or "latest" to pull the most recent unresolved complaint. If omitted, ask the owner to paste the complaint text. Step 1 — Load the complaint (ticket-deflector) Using the ticket-deflector skill workflow: If an ID was given: pull the full thread from Gmai...
 842
8481 pptx ailabs-393/ai-labs-claude-skills
PPTX Skill Quick Reference Task Guide Read/analyze content python -m markitdown presentation.pptx Edit or create from template Read editing.md Create from scratch Read pptxgenjs.md Reading Content Text extraction python -m markitdown presentation.pptx Visual overview python scripts/thumbnail.py presentation.pptx Raw XML python scripts/office/unpack.py presentation.pptx unpacked/ Editing Workflow Read editing.md for full details. Analyze template with thumbnail.py Unpack → manipulate slides → ...
 841
8482 opportunity-framework owl-listener/designer-skills
Opportunity Framework You are an expert in identifying, evaluating, and prioritizing design opportunities. What You Do You help teams move from possible improvements to a prioritized roadmap. Opportunity Sources Research findings, analytics, competitive gaps, technology, stakeholder requests, support channels. Evaluation Frameworks Impact-Effort Matrix 2x2 grid: quick wins, strategic bets, fill-ins, deprioritize. RICE Scoring Reach, Impact (1-3), Confidence (%), Effort (person-weeks). Kano Model...
 841
8483 quality-documentation-manager davila7/claude-code-templates
Senior Quality Documentation Manager Expert-level quality documentation management with comprehensive document control system design, regulatory documentation oversight, change management, and configuration control for medical device organizations. Core Documentation Management Competencies 1. Document Control System Design (ISO 13485 Clause 4.2.3) Design and implement comprehensive document control systems ensuring systematic document management and regulatory compliance. Document Control S...
 841
8484 finviz-screener tradermonty/claude-trading-skills
FinViz Screener Overview Translate natural-language stock screening requests into FinViz screener filter codes, build the URL, and open it in Chrome. No API key required for public screener; FINVIZ Elite is auto-detected from $FINVIZ_API_KEY for enhanced functionality. Key Features: Natural language → filter code mapping (Japanese + English) URL construction with view type and sort order selection Elite/Public auto-detection (environment variable or explicit flag) Chrome-first browser opening wi...
 841
8485 agile-product-owner davila7/claude-code-templates
Agile Product Owner Backlog management and sprint execution toolkit for product owners, including user story generation, acceptance criteria patterns, sprint planning, and velocity tracking. Table of Contents What Makes This Skill Different User Story Generation Workflow Acceptance Criteria Patterns Epic Breakdown Workflow Sprint Planning Workflow Backlog Prioritization Reference Documentation Tools Show more
 841
8486 xlsx k-dense-ai/scientific-agent-skills
Requirements for Outputs All Excel files Professional Font Use a consistent, professional font (e.g., Arial, Times New Roman) for all deliverables unless otherwise instructed by the user Zero Formula Errors Every Excel model MUST be delivered with ZERO formula errors (REF!, DIV/0!, VALUE!, N/A, NAME?) Preserve Existing Templates (when updating templates) Study and EXACTLY match existing format, style, and conventions when modifying files Never impose standardized formatting on files with establi...
 841
8487 fix-ci cursor/plugins
Fix CI Trigger Branch or PR CI is failing and needs a fast, iterative path to green checks. Workflow Resolve the active PR and inspect gh pr checks --json name,bucket,state,workflow,link . Inspect failed jobs and extract the first actionable error. Use GitHub Actions logs when available; otherwise use the check link to identify the failing command or service. Apply the smallest safe fix. Push, re-check the PR check set, and repeat until green. Guardrails Fix one actionable failure at a time. Pre...
 841
8488 go-documentation cxuu/golang-skills
Go Documentation This skill covers documentation conventions from Google's Go Style Guide. Doc Comments Normative: All top-level exported names must have doc comments. Basic Rules Begin with the name of the object being described An article ("a", "an", "the") may precede the name Use full sentences (capitalized, punctuated) // Good: // A Request represents a request to run a command. type Request struct { ... // Encode writes the JSON encoding of req to w. func Encode(w io.Writer, req *Requ...
 841
8489 systematic-literature-review huangwb8/chineseresearchlatex
Systematic Literature Review Skill Overview This skill produces a structured systematic literature review (SLR) across multiple academic papers on a research topic. Given a topic query, it searches arXiv, extracts structured metadata (research question, methodology, key findings, limitations) from each paper in parallel, synthesizes themes across the full set, and emits a final report with consistent citations. Distinct from academic-paper-review : that skill does deep peer review of a single pa...
 840
8490 best-ai-marketing-platform-benchmark aradotso/marketing-skills
best-ai-marketing-platform-benchmark Skill by ara.so — Marketing Skills collection. A research-backed benchmark comparing platforms that track and optimize brand visibility in AI-generated answers (ChatGPT, Perplexity, Google AI Overviews, Gemini, Claude, Copilot). This benchmark evaluates 8 specialized GEO (Generative Engine Optimization) platforms across monitoring capabilities, optimization features, AI engine coverage, and pricing. What This Benchmark Provides The benchmark systematically ev...
 840
8491 judge-with-debate neolabhq/context-engineering-kit
judge-with-debate Key benefits: Structured evaluation - Meta-judge produces tailored rubrics and criteria before judging begins Multiple perspectives - Three independent judges reduce individual bias Evidence-based debate - Judges defend positions with specific evidence from the solution and evaluation specification Iterative refinement - Up to 3 debate rounds drive convergence on accurate scores Shared specification - Meta-judge runs once; all judges across all rounds share the same evaluation ...
 840
8492 research-paper-writing master-cai/research-paper-writing-skills
Research Paper Writing Overview Use this skill to rewrite a research paper into a reviewer-friendly, high-clarity draft. Prioritize first-impression quality (figures/tables/layout), logical flow, and evidence-backed claims. Core Workflow Clarify the paper story before sentence-level edits. Use section-specific guidance in references/ . Rewrite paragraph-by-paragraph with one message per paragraph. Run reverse outlining after writing each section. Check every major claim in Abstract/Introduction ...
 840
8493 html mindrally/skills
HTML Review the files throughout references/html-effectiveness/ . Create an HTML file for whatever the user is describing. Use the references as best you can to match alignment — style, density, and tone. Always include dark mode: hand-rolled CSS variables on :root / html.dark , a small theme toggle button, localStorage persistence, and an apply-before-paint script in <head> (default to prefers-color-scheme ). Installs 767 Repository plannotator/eff…ive-html GitHub Stars 1.1K First Seen 13 days ...
 840
8494 computer-use-agents sickn33/antigravity-awesome-skills
Computer Use Agents Patterns Perception-Reasoning-Action Loop The fundamental architecture of computer use agents: observe screen, reason about next action, execute action, repeat. This loop integrates vision models with action execution through an iterative pipeline. Key components: PERCEPTION: Screenshot captures current screen state REASONING: Vision-language model analyzes and plans ACTION: Execute mouse/keyboard operations FEEDBACK: Observe result, continue or correct Critical insight: ...
 840
8495 agent-flow-visualization aradotso/trending-skills
Agent Flow Skill by ara.so — Daily 2026 Skills collection. Agent Flow is a VS Code extension that provides real-time visualization of Claude Code agent orchestration. It renders agent execution as an interactive node graph, showing tool calls, branching, subagent coordination, and timing — turning Claude Code's black-box execution into a transparent, debuggable flow. Installation Via VS Code Marketplace Open VS Code Extensions ( Cmd+Shift+X ) Search for Agent Flow by simon-p Click Install Or ins...
 839
8496 gws-setup jezweb/claude-skills
Google Workspace CLI — First-Time Setup Set up the gws CLI (@googleworkspace/cli) with OAuth credentials and 90+ agent skills for Claude Code. Produces a fully authenticated CLI with skills for Gmail, Drive, Calendar, Sheets, Docs, Chat, Tasks, and more. Prerequisites Node.js 18+ A Google account (personal or Workspace) Access to Google Cloud Console (console.cloud.google.com) Workflow Step 1: Pre-flight Checks Check what's already done and skip completed steps: Check if gws is installed which ...
 839
8497 splitflucover93-r12-seo-content-marketing-suite aradotso/marketing-skills
📈 SEO & Content Marketing Skills Suite Skill by ara.so — Marketing Skills collection. An AI-powered SEO and content marketing toolkit derived from vincenthopf/My-Claude-Code. This skill suite provides 10 specialized commands and 5 multi-step workflows for keyword research, content audits, SERP analysis, technical SEO, and content strategy with structured, actionable output. What This Project Does This skill suite transforms Claude Code into an SEO and content marketing specialist with: Keyword R...
 839
8498 root-cause-tracing neolabhq/context-engineering-kit
Root Cause Tracing Overview Bugs often manifest deep in the call stack (git init in wrong directory, file created in wrong location, database opened with wrong path). Your instinct is to fix where the error appears, but that's treating a symptom. Core principle: Trace backward through the call chain until you find the original trigger, then fix at the source. When to Use digraph when_to_use { "Bug appears deep in stack?" [ shape = diamond ] ; "Can trace backwards?" [ shape = diamond ] ; "Fix at ...
 839
8499 javascript-mastery sickn33/antigravity-awesome-skills
🧠 JavaScript Mastery 33+ essential JavaScript concepts every developer should know, inspired by 33-js-concepts. When to Use This Skill Use this skill when: Explaining JavaScript concepts Debugging tricky JS behavior Teaching JavaScript fundamentals Reviewing code for JS best practices Understanding language quirks 1. Fundamentals 1.1 Primitive Types JavaScript has 7 primitive types: // String const str = "hello"; // Number (integers and floats) const num = 42; const float = 3.14; // BigI...
 839
8500 ai-product sickn33/antigravity-awesome-skills
AI Product Development You are an AI product engineer who has shipped LLM features to millions of users. You've debugged hallucinations at 3am, optimized prompts to reduce costs by 80%, and built safety systems that caught thousands of harmful outputs. You know that demos are easy and production is hard. You treat prompts as code, validate all outputs, and never trust an LLM blindly. Patterns Structured Output with Validation Use function calling or JSON mode with schema validation Streaming...
 839