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...
25,529
总 Skills
98.3M
总安装量
2,626
贡献者
# Skill 仓库 描述 安装量
4501 douyin-video yzfly/douyin-mcp-server
抖音无水印视频下载和文案提取 从抖音分享链接获取无水印视频下载链接, 下载视频, 并使用语音识别提取视频中的文案, 自动保存到文件. 功能概述 获取下载链接 : 从抖音分享链接解析出无水印视频的直接下载地址 (无需 API 密钥) 下载视频 : 将无水印视频下载到本地指定目录 提取文案 : 通过语音识别从视频中提取文字内容 (需要硅基流动 API 密钥) 自动保存 : 每个视频的文案自动保存到独立文件夹 (视频ID为文件夹名) 环境要求 依赖安装 pip install requests ffmpeg-python 系统要求 FFmpeg 必须安装在系统中 (用于音视频处理) macOS: brew install ffmpeg Ubuntu: apt install ffmpeg API 密钥配置 (仅文案提取需要) 文案提取功能使用硅基流动 API, 需要设置环境变量: export API_KEY = "your-siliconflow-api-key" 获取 API 密钥: https://cloud.siliconflow.cn/ 使用方法 方法一: 使用脚本 (推荐) 获...
 1.7K
4502 building-dashboards axiomhq/skills
Building Dashboards You design dashboards that help humans make decisions quickly. Dashboards are products: audience, questions, and actions matter more than chart count. Philosophy Decisions first. Every panel answers a question that leads to an action. Overview → drilldown → evidence. Start broad, narrow on click/filter, end with raw logs. Rates and percentiles over averages. Averages hide problems; p95/p99 expose them. Simple beats dense. One question per panel. No chart junk. Validate with...
 1.7K
4503 pencil-design chiroro-jr/pencil-design-skill
Pencil Design Skill Design production-quality UIs in Pencil and generate clean, maintainable code from them. This skill enforces best practices for design system reuse, variable usage, layout correctness, visual verification, and design-to-code workflows. When to Use This Skill Designing screens, pages, or components in a .pen file Generating code (React, Next.js, Vue, Svelte, HTML/CSS) from Pencil designs Building or extending a design system in Pencil Syncing design tokens between Pencil and c...
 1.7K
4504 browserenginekit dpearson2699/swift-ios-skills
BrowserEngineKit Framework for building web browsers with alternative (non-WebKit) rendering engines on iOS and iPadOS. Provides process isolation, XPC communication, capability management, and system integration for browser apps that implement their own HTML/CSS/JavaScript engine. Targets Swift 6.3 / iOS 26+. BrowserEngineKit is a specialized framework. Alternative browser engines are currently supported for distribution in the EU. Japan requires Memory Integrity Enforcement (MIE) for alternati...
 1.7K
4505 sensorkit dpearson2699/swift-ios-skills
SensorKit Collect research-grade sensor data from iOS and watchOS devices for approved research studies. SensorKit provides access to ambient light, motion, device usage, keyboard metrics, visits, phone/messaging usage, speech metrics, face metrics, wrist temperature, heart rate, ECG, and PPG data. Targets Swift 6.3 / iOS 26+. SensorKit is restricted to Apple-approved research studies. Apps must submit a research proposal to Apple and receive the com.apple.developer.sensorkit.reader.allow entitl...
 1.7K
4506 metrics-dashboard phuryn/pm-skills
Product Metrics Dashboard Design a comprehensive product metrics dashboard with the right metrics, visualizations, and alert thresholds. Context You are designing a metrics dashboard for $ARGUMENTS . If the user provides files (existing dashboards, analytics data, OKRs, or strategy docs), read them first. Domain Context Metrics vs KPIs vs NSM : Metrics = all measurable things. KPIs = a few key quantitative metrics tracked over a longer period. North Star Metric = a single customer-centric KPI th...
 1.7K
4507 relevancekit dpearson2699/swift-ios-skills
RelevanceKit Provide on-device contextual clues that increase a widget's visibility in the Smart Stack on Apple Watch. RelevanceKit tells the system when a widget is relevant -- by time, location, fitness state, sleep schedule, or connected hardware -- so the Smart Stack can surface the right widget at the right moment. Targets Swift 6.3 / watchOS 26+. Beta-sensitive. RelevanceKit shipped with watchOS 26. Re-check Apple documentation before making strong claims about API availability or behavior...
 1.7K
4508 zoom-out vinvcn/mattpocock-skills-zh-cn
I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers.
 1.7K
4509 literature-review davila7/claude-code-templates
Literature Review Conduct deep literature reviews through multi-perspective dialogue and systematic search. Input $0 — Research topic or question $1 — Optional: specific focus or angle References Multi-perspective dialogue prompts (STORM): ~/.claude/skills/literature-review/references/dialogue-prompts.md Literature review workflow (AgentLaboratory): ~/.claude/skills/literature-review/references/review-workflow.md Scripts (from literature-search skill) Search Semantic Scholar python ~/.claude/sk...
 1.7K
4510 pubmed-database affaan-m/everything-claude-code
PubMed Database Use this skill when a task needs biomedical literature from PubMed rather than general web search. When to Use Searching MEDLINE or life-sciences literature. Building PubMed queries with MeSH terms, field tags, dates, or article types. Looking up PMIDs, abstracts, publication metadata, or related citations. Running systematic-review search passes that need repeatable search strings. Using NCBI E-utilities directly from Python, shell, or another HTTP client. Query Construction Sta...
 1.7K
4511 windows-desktop-e2e affaan-m/everything-claude-code
Windows Desktop E2E Testing End-to-end testing for Windows native desktop applications using pywinauto backed by Windows UI Automation (UIA). Covers WPF, WinForms, Win32/MFC, and Qt (5.x / 6.x) — with Qt-specific guidance as a dedicated section. When to Activate Writing or running E2E tests for a Windows native desktop application Setting up a desktop GUI test suite from scratch Diagnosing flaky or failing desktop automation tests Adding testability (AutomationId, accessible names) to an existin...
 1.7K
4512 write-a-skill vinvcn/mattpocock-skills-zh-cn
Writing Skills Process Gather requirements - ask user about: What task/domain does the skill cover? What specific use cases should it handle? Does it need executable scripts or just instructions? Any reference materials to include? Draft the skill - create: SKILL.md with concise instructions Additional reference files if content exceeds 500 lines Utility scripts if deterministic operations needed Review with user - present draft and ask: Does this cover your use cases? Anything missing or unclea...
 1.7K
4513 retention-engagement refoundai/lenny-skills
Retention & Engagement Help the user improve retention and engagement using frameworks from 29 product leaders. How to Help When the user asks for help with retention: Understand the retention curve - Ask about their current retention shape and where drop-off occurs Identify the aha moment - Help them define what first experience of value looks like for their users Assess habit formation - Determine if they're building for habitual vs. occasional use Design retention loops - Create mechanisms th...
 1.7K
4514 measuring-product-market-fit refoundai/lenny-skills
Measuring Product-Market Fit Help the user assess and achieve product-market fit using frameworks from 46 product leaders. How to Help When the user asks about product-market fit: Understand their stage - Ask how many customers they have, what their retention looks like, and what signals they're seeing (or not seeing) Diagnose the situation - Determine if they're confusing vanity metrics with PMF, if they have PMF in a specific segment, or if they're clearly pre-PMF Apply the right framework - H...
 1.7K
4515 unauthorized-access-common-services yaklang/hack-skills
SKILL: Unauthorized Access to Common Services — Expert Attack Playbook AI LOAD INSTRUCTION : Expert techniques for exploiting unauthenticated or weakly authenticated management services. Covers Redis write-to-RCE, Rsync data theft, PHP-FPM code execution, Ghostcat AJP file read, Hadoop YARN job submission, and H2 Console JNDI. These are infrastructure-level findings distinct from web application vulnerabilities. 0. RELATED ROUTING ssrf-server-side-request-forgery when these services are reachabl...
 1.7K
4516 pricing-strategy refoundai/lenny-skills
Pricing Strategy You are an expert in SaaS pricing and monetization strategy. Your goal is to help design pricing that captures value, drives growth, and aligns with customer willingness to pay. Before Starting 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. Gather this con...
 1.7K
4517 spring-boot-security-jwt giuseppe-trisciuoglio/developer-kit
Spring Boot JWT Security Comprehensive JWT (JSON Web Token) authentication and authorization patterns for Spring Boot 3.5.x applications using Spring Security 6.x and the JJWT library. This skill provides production-ready implementations for stateless authentication, role-based access control, and integration with modern authentication providers. Overview JWT authentication enables stateless, scalable security for Spring Boot applications. This skill covers complete JWT lifecycle management incl...
 1.7K
4518 release-notes phuryn/pm-skills
Release Notes Generator Transform technical tickets, PRDs, or internal changelogs into polished, user-facing release notes. Context You are writing release notes for $ARGUMENTS . If the user provides files (JIRA exports, Linear tickets, PRDs, Git logs, or internal changelogs), read them first. If they mention a product URL, use web search to understand the product and audience. Instructions Gather raw material : Read all provided tickets, changelogs, or descriptions. Extract: What changed (featu...
 1.7K
4519 mysql-patterns affaan-m/everything-claude-code
MySQL Patterns Use this skill when working on MySQL or MariaDB schema design, migrations, slow-query investigation, queue-style transactions, connection pools, or production database configuration. Prefer exact version checks before applying a feature-specific pattern because MySQL and MariaDB have diverged in several SQL details. Activation Designing MySQL or MariaDB tables, indexes, and constraints Reviewing migrations before they run on large production tables Debugging slow queries, lock wai...
 1.7K
4520 atxp atxp-dev/cli
ATXP Tools Access ATXP's paid API tools via CLI. Authentication Check if authenticated echo $ATXP_CONNECTION If not set, login: npx atxp login source ~/.atxp/config Commands Command Description npx atxp search <query> Real-time web search npx atxp image <prompt> AI image generation npx atxp music <prompt> AI music generation npx atxp video <prompt> AI video generation npx atxp x <query> X/Twitter search PaaS Tools Deploy serverless applications with functions, databases, object storage, c...
 1.7K
4521 akshare succ985/openclaw-akshare-skill
AkShare - Chinese Financial Data Overview AkShare is a free, open-source Python library for accessing Chinese financial market data. This skill provides guidance for fetching data from Chinese exchanges including Shanghai Stock Exchange, Shenzhen Stock Exchange, Hong Kong Exchange, and more. Quick Start Install AkShare: pip install akshare Basic stock quote: import akshare as ak df = ak . stock_zh_a_spot_em ( ) Real-time A-share data Stock Data A-Shares (A股) Real-time quotes: All A-shares real...
 1.7K
4522 discovery-process deanpeters/product-manager-skills
Purpose Guide product managers through a complete discovery cycle—from initial problem hypothesis to validated solution—by orchestrating problem framing, customer interviews, synthesis, and experimentation skills into a structured process. Use this to systematically explore problem spaces, validate assumptions, and build confidence before committing to full development—avoiding "build it and they will come" syndrome and ensuring you're solving real customer problems. This is not a one-time resea...
 1.7K
4523 ideal-customer-profile phuryn/pm-skills
Ideal Customer Profile Overview Identify your Ideal Customer Profile (ICP) from research and survey data. This skill synthesizes customer research to define the customer most likely to find value, retain, and expand with your product. When to Use Defining ICP from product-market fit survey data Targeting high-value customer segments Analyzing customer success and expansion patterns Prioritizing sales and marketing efforts Evaluating new customer opportunities for fit Refining target market defin...
 1.7K
4524 vite-patterns affaan-m/everything-claude-code
Vite Patterns Build tool and dev server patterns for Vite 8+ projects. Covers configuration, environment variables, proxy setup, library mode, dependency pre-bundling, and common production pitfalls. When to Use Configuring vite.config.ts or vite.config.js Setting up environment variables or .env files Configuring dev server proxy for API backends Optimizing build output (chunks, minification, assets) Publishing libraries with build.lib Troubleshooting dependency pre-bundling or CJS/ESM interop ...
 1.7K
4525 network-interface-health affaan-m/everything-claude-code
Network Interface Health Use this skill when a network symptom might be caused by a physical link, switch port, cable, transceiver, duplex setting, or congested interface. When to Use A host or VLAN has packet loss, latency spikes, or intermittent reachability. A switch or router interface shows CRCs, runts, giants, drops, resets, or flaps. You need to compare both ends of a link before replacing hardware. A change window needs before/after interface counter evidence. Monitoring reports rising i...
 1.7K
4526 ui-typography bencium/bencium-marketplace
UI Typography Skill Attribution These rules are distilled from Matthew Butterick's Practical Typography ( https://practicaltypography.com ). Butterick is a typographer, writer, and type designer whose work bridges professional typography and everyday digital writing. Thank you, Matthew, for making this knowledge accessible and encyclopedic. If you find this skill valuable, consider supporting his work directly. Mode of Operation These are permanent rules — not trends, not opinions. They come fro...
 1.7K
4527 bibi jimmylv/bibigpt-skill
BibiGPT CLI ( bibi ) Summarize videos, audio, and podcasts from the terminal using the BibiGPT API. Installation macOS (Homebrew) brew install --cask jimmylv/bibigpt/bibigpt Windows Download the installer from: https://bibigpt.co/download/desktop winget install BibiGPT is pending review and not yet available. Verify installation bibi --version Authentication After installing, the user must log in via the desktop app at least once. The CLI reads the saved session automatically from the desktop ap...
 1.7K
4528 database-design sickn33/antigravity-awesome-skills
Database Design Learn to THINK, not copy SQL patterns. 🎯 Selective Reading Rule Read ONLY files relevant to the request! Check the content map, find what you need. File Description When to Read database-selection.md PostgreSQL vs Neon vs Turso vs SQLite Choosing database orm-selection.md Drizzle vs Prisma vs Kysely Choosing ORM schema-design.md Normalization, PKs, relationships Designing schema indexing.md Index types, composite indexes Performance tuning optimization.md N+1, EXPLAIN ANALYZE Que...
 1.7K
4529 tabletopkit dpearson2699/swift-ios-skills
TabletopKit Create multiplayer spatial board games on a virtual table surface using TabletopKit. Handles game layout, equipment interaction, player seating, turn management, state synchronization, and RealityKit rendering. visionOS 2.0+ only. Targets Swift 6.3. Contents Setup Game Configuration Table and Board Equipment (Pieces, Cards, Dice) Player Seats Game Actions and Turns Interactions RealityKit Rendering Group Activities Integration Common Mistakes Review Checklist References Setup Platfor...
 1.7K
4530 analytics-tracking kostja94/marketing-skills
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...
 1.7K
4531 paseo-loop getpaseo/paseo
Loop Skill You are setting up an autonomous loop. An agent runs repeatedly until an exit condition is met. User's arguments: $ARGUMENTS Prerequisites Load the Paseo skill first — it contains the CLI reference for all agent commands. What Is a Loop A loop runs an agent repeatedly until it's done. There are two modes: Self-terminating (no verifier) A single worker agent runs each iteration. It returns { done: boolean, reason: string } via structured output. The loop exits when done is true. Worker...
 1.7K
4532 ts-library onmax/nuxt-skills
TypeScript Library Development Patterns for authoring high-quality TypeScript libraries, extracted from studying unocss, shiki, unplugin, vite, vitest, vueuse, zod, trpc, drizzle-orm, and more. When to Use Starting a new TypeScript library (single or monorepo) Setting up package.json exports for dual CJS/ESM Configuring tsconfig for library development Choosing build tools (tsdown, unbuild) Designing type-safe APIs (builder, factory, plugin patterns) Writing advanced TypeScript types Setting u...
 1.7K
4533 c-review trailofbits/skills
C/C++ Security Review Runs in the main conversation (invoke via /c-review:c-review ). Orchestrator owns the Task* ledger as bookkeeping for retries; workers and judges have no Task tools. Workers and judges are named plugin subagents ( c-review:c-review-worker , c-review:c-review-dedup-judge , c-review:c-review-fp-judge ); tool sets are declared in plugins/c-review/agents/*.md . Findings are exchanged via markdown-with-YAML files in a shared output directory. When to Use Native C/C++ application...
 1.7K
4534 agent-memory-systems sickn33/antigravity-awesome-skills
Agent Memory Systems You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions. You know that the hard part isn't storing - it's retrieving the right memory at the right time. Your core insight: Memory failures look like intelligence failures. When an agent "forgets" or gives inconsistent answers, it's almost always a retrieval problem, not a storage problem. You obsess over chunking strategies, em...
 1.7K
4535 kibana-streams elastic/agent-skills
Kibana Streams Read stream metadata, settings, queries, significant events, and attachments, and manage stream lifecycle (enable, disable, resync) via the Kibana Streams REST API. Streams are an experimental way to manage data in Kibana — expect API and behavior changes. This skill covers read operations and lifecycle only; create, update, delete, fork, and other mutating operations may be added in a later version. For detailed endpoints and parameters, see references/streams-api-reference.md . ...
 1.7K
4536 paseo-committee getpaseo/paseo
Committee Skill You are forming a committee to step back from the current problem and get fresh perspective. User's additional context: $ARGUMENTS Prerequisites Load the Paseo skill first — it contains the CLI reference for all agent commands and waiting guidelines. What Is a Committee Two agents — Opus 4.6 ( --thinking on ) and GPT 5.4 ( --thinking medium ) — launched in parallel to plan a solution. Fresh context, no implementation baggage, proper root cause analysis. They stay alive after plan...
 1.7K
4537 meta-ads kostja94/marketing-skills
Paid Ads: Meta Ads Guides Meta (Facebook/Instagram) Ads setup, campaign structure, audience targeting, and creative optimization. Meta excels at demand generation and visual products; use when creating demand or when creative assets are strong. 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. Campaign Structure Hierarchy : ...
 1.7K
4538 user-story-mapping deanpeters/product-manager-skills
Purpose Visualize the user journey by creating a hierarchical map that breaks down high-level activities into steps and tasks, organized left-to-right as a narrative flow. Use this to build shared understanding across product, design, and engineering, prioritize features based on user workflows, and identify gaps or opportunities in the user experience. This is not a backlog—it's a strategic artifact that shows how users accomplish their goals, which then informs what to build. Key Concepts The ...
 1.7K
4539 jobs-to-be-done deanpeters/product-manager-skills
Jobs to Be Done Framework Framework for discovering innovation based on a fundamental truth: customers don't buy products - they "hire" them to do a specific job in their lives. Core Principle Job to Be Done = the progress a customer wants to make in specific circumstances. Key elements of the definition: Progress (not goal, not solution) - customer wants to move from current state to a better one Circumstances - context determines the job, not customer attributes (demographics are useless) Hiri...
 1.7K
4540 pricing-strategy phuryn/pm-skills
Pricing Strategy You are an expert in SaaS pricing and monetization strategy. Your goal is to help design pricing that captures value, drives growth, and aligns with customer willingness to pay. Before Starting 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. Gather this con...
 1.7K
4541 user-personas phuryn/pm-skills
User Personas Purpose Create detailed, actionable user personas from research data that capture the true diversity of your user base. This skill generates research-backed personas with jobs-to-be-done, pain points, desired outcomes, and unexpected behavioral insights to guide product decisions. Instructions You are an experienced product researcher specializing in persona development and user research synthesis. Input Your task is to create 3 refined user personas for $ARGUMENTS . If the user pr...
 1.7K
4542 grammar-check phuryn/pm-skills
Grammar and Flow Checking You are an expert copyeditor and writing specialist. Your role is to identify grammar, logical, and flow errors in text, then provide clear, actionable fix suggestions without rewriting the entire document. Purpose Analyze text for grammar, logical, and flow errors. Provide specific, focused suggestions on how to fix each issue. Focus on clarity, correctness, and readability. Input Arguments $OBJECTIVE : What is the intended purpose or goal of the text? (e.g., "persuade...
 1.7K
4543 reverse-shell-techniques yaklang/hack-skills
SKILL: Reverse Shell Techniques — Expert Attack Playbook AI LOAD INSTRUCTION : Expert reverse shell techniques. Covers reverse/bind shell decisions, encrypted shells (OpenSSL, socat SSL, ncat), web shell patterns (PHP/ASPX/JSP), PTY upgrade sequences, file transfer methods, PowerShell download cradles, and msfvenom payload generation. Base models miss encrypted shell syntax, proper PTY stabilization, and platform-specific transfer techniques. 0. RELATED ROUTING Before going deep, consider loadin...
 1.7K
4544 marketing-ideas phuryn/pm-skills
Marketing Ideas for SaaS You are a marketing strategist with a library of 139 proven marketing ideas. Your goal is to help users find the right marketing strategies for their specific situation, stage, and resources. How to Use This Skill 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 t...
 1.7K
4545 flags-sdk vercel/flags
Flags SDK The Flags SDK ( flags npm package) is a feature flags toolkit for Next.js and SvelteKit. It turns each feature flag into a callable function, works with any flag provider via adapters, and keeps pages static using the precompute pattern. Docs: https://flags-sdk.dev Repo: https://github.com/vercel/flags Core Concepts Flags as Code Each flag is declared as a function — no string keys at call sites: import { flag } from 'flags/next' ; export const exampleFlag = flag ( { key : 'example-fla...
 1.7K
4546 push-to-registry hashicorp/agent-skills
Configure Packer templates to push build metadata to HCP Packer registry. Reference: [HCP Packer Registry](https://developer.hashicorp.com/hcp/docs/packer) Note: HCP Packer is free for basic use. Builds push metadata only (not actual images), adding minimal overhead (<1 minute). Basic Registry Configuration ``` packer { required_version = ">= 1.7.7" } variable "image_name" { type = string default = "web-server" } locals { timestamp = regex_replace(timestamp(), "[- TZ:]", "") } ...
 1.7K
4547 opentui anomalyco/opentui
OpenTUI Platform Skill Consolidated skill for building terminal user interfaces with OpenTUI. Use decision trees below to find the right framework and components, then load detailed references. Critical Rules Follow these rules in all OpenTUI code: Use create-tui for new projects. See framework README.md quick starts. create-tui options must come before arguments. bunx create-tui -t react my-app works, bunx create-tui my-app -t react does NOT. Never call process.exit() directly. Use renderer...
 1.7K
4548 writing-docs remotion-dev/remotion
Writing Remotion Documentation Documentation lives in packages/docs/docs as .mdx files. Adding a new page Create a new .mdx file in packages/docs/docs Add the document to packages/docs/sidebars.ts Write the content following guidelines below Run bun render-cards.ts in packages/docs to generate social preview cards One API per page: Each function or API should have its own dedicated documentation page. Do not combine multiple APIs (e.g., getEncodableVideoCodecs() and getEncodableAudioCodecs())...
 1.7K
4549 bailian-docs-llm-wiki modelstudioai/skills
百炼文档知识库 阿里云百炼平台的完整技术文档知识库，涵盖模型使用、应用开发、API 参考等内容。 何时使用 当用户涉及以下场景时激活此 Skill： 查询百炼平台的模型列表、模型参数、调用方式（含具体模型的 contextWindow、QPM、定价、sample code 等结构化字段 → 查 models/ ） 查阅百炼 API 参数、请求/响应格式、错误码 了解百炼应用开发（智能体、RAG、知识库、记忆、插件等） 选择模型、比较模型能力、了解模型定价与限流 使用百炼 SDK / OpenAI 兼容接口 语音识别、语音合成、图片生成、视频生成等多模态能力 Token Plan、计费、免费额度等商务问题 何时 不要 使用 下面这些场景与百炼文档无关， 不要激活 本 Skill： Show more
 1.7K
4550 agent-architecture-audit affaan-m/everything-claude-code
Agent Architecture Audit A diagnostic workflow for agent systems that hide failures behind wrapper layers, stale memory, retry loops, or transport/rendering mutations. When to Activate MANDATORY for: Releasing any agent or LLM-powered application to production Shipping features with tool calling, memory, or multi-step workflows Agent behavior degrades after adding wrapper layers User reports "the agent is getting worse" or "tools are flaky" Same model works in playground but breaks inside your w...
 1.7K