claude-code-daodan

Comprehensive Python web scraping knowledge base covering stealth browser automation (Patchright, Camoufox, Nodriver), TLS/HTTP fingerprint impersonation (curl_cffi, primp), anti-bot bypass (Cloudflare, DataDome, PerimeterX), CAPTCHA solving, proxy architecture, AI-assisted extraction (Crawl4AI, Firecrawl, ScrapeGraphAI), framework selection (Scrapy, Crawlee), rate limiting, and production observability. TRIGGER WHEN: building, implementing, writing, coding, creating, optimizing, or debugging Python web scrapers. DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Brand naming strategist - generates, filters, scores, and validates brand names through a lateral thinking workflow. Uses 4 lateral thinking techniques (semantic collision, vocabulary shift, invisible hinge, polarization) for creative generation, then filters with 7 naming archetypes, linguistic/phonotactic rules, weighted scoring, domain availability checks, market saturation analysis (existing apps, websites, businesses with same name), trademark pre-screening, and SEO analysis. TRIGGER WHEN: "brand name", "naming", "name my app", "name my product", "product name", "startup name", "come up with a name", "nome del brand", "naming strategico". DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Proactive git worktree orchestration - detects WIP state (uncommitted changes, stashes, unpushed commits) and offers to isolate work into worktrees. MUST activate BEFORE any implementation task (add, create, build, implement, develop, make, fix, refactor) when the working directory has uncommitted changes or stashes. Also provides dashboard, context recovery, multi-worktree creation, cleanup advisor, and conflict early warning across parallel development sessions. Triggers: any implementation request when WIP exists, "show my worktrees", "what am I working on", "help me manage parallel tasks", "worktree status", "coordinate my work". TRIGGER WHEN: before any implementation task (add, create, build, fix, refactor) when the working directory has uncommitted changes, stashes, or unpushed commits; when the user asks about worktrees, branches, or parallel development. DO NOT TRIGGER WHEN: the repo state is clean and the user is doing a single-file read-only task.

"Brainstorm and generate a Buzan-style structured mindmap JSON outline from any content. Use this skill whenever the user asks to create a mind map, mappa mentale, concept map, or visual summary. The skill prioritizes COGNITIVE EFFECTIVENESS over structural efficiency: it uses single keywords, strong visual associations (emojis), organic radiant thinking, and cross-linking to maximize memory retention and idea generation.". TRIGGER WHEN: the user asks to create a mind map, mappa mentale, concept map, or visual summary - typically to learn, brainstorm, or structure knowledge around a topic. DO NOT TRIGGER WHEN: the user wants a traditional outline, flowchart, or diagram (use Mermaid directly) rather than a radiant Buzan-style mind map.

Guided creation of Claude Code plugin components - skills, agents, commands, and full plugins. Walks through requirements gathering, generates production-ready files with real content (not placeholders), registers in marketplace.json, and bumps versions. Also trigger on "new skill", "new agent", "new plugin", "add a skill", "add an agent", "skills-creator", "skills-hammer". Also helps decide skill vs agent architecture when reorganizing plugins. DO NOT TRIGGER for editing or updating existing components - only for new creation or architectural decisions (skill vs agent). TRIGGER WHEN: the user asks to create, add, scaffold, or build a new skill, agent, command, or plugin DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Comprehensive defect taxonomy knowledge base - 16 macro-categories, 140+ subcategories of source code defects with CWE/OWASP mappings, detection strategies, fix patterns, and review frameworks. Used by senior-review agents (code-auditor, security-auditor, ui-race-auditor) to enrich analysis with structured defect knowledge.

Stripe payments knowledge base - API patterns, checkout optimization, subscription lifecycle, pricing strategies, webhook reliability, Firebase integration, cost analysis, and revenue modeling. Loaded by stripe-integrator and revenue-optimizer agents; also consumable directly when the user asks for Stripe-specific patterns without needing an agent. TRIGGER WHEN: working with Stripe API (Payment Intents, Customers, Subscriptions, Checkout Sessions, Connect, webhooks, tax, usage-based billing), pricing strategy, or revenue modeling. DO NOT TRIGGER WHEN: payment work is non-Stripe (PayPal, Square, crypto) or the task is generic e-commerce unrelated to payments.

Knowledge base for pure-architecture decisions on when to unify duplicated logic into a shared abstraction versus leave it duplicated. Covers the canonical theory (Rule of Three, DRY/WET/AHA, Wrong Abstraction, Locality of Behaviour, Bounded Contexts, Tidy First options framing, CUPID vs SOLID), 12 essential-duplication patterns that justify unification, 12 wrong-abstraction patterns that justify inlining or decomposition, an operational decision frame, and a verified reading list. TRIGGER WHEN: the user is making an architectural decision about whether to centralize, extract, or remove a layer; reviewing an abstraction for premature generality; auditing scattered cross-cutting concerns; spawned by the abstraction-architect agent during /abstraction-architect:audit or as the Abstraction dimension of /senior-review:team-review or /senior-review:code-review; the user asks "should I extract this into a service" / "is this DRY enough" / "is this wrong abstraction". DO NOT TRIGGER WHEN: the task is code formatting

Skill activation engine that ensures relevant marketplace skills are invoked for every task. TRIGGER WHEN: ALWAYS at conversation start and before every task. DO NOT TRIGGER WHEN: dispatched as a subagent.

AI-powered systematic codebase analysis. Combines structure extraction with semantic understanding to produce documentation capturing WHAT, WHY, HOW, and CONSEQUENCES. Multi-language: Python, Java, JavaScript, TypeScript, SQL, PL/SQL, Rust. Includes pattern recognition, red flag detection, flow tracing, and quality assessment. TRIGGER WHEN: encountering unfamiliar code, before major refactoring, or when documentation is stale or missing DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Quality gates for multi-reviewer code review pipelines: adversarial verification panel, completeness critic, reviewer pipeline conventions, and the context sharing pattern for parallel reviewers. TRIGGER WHEN: running /senior-review:team-review quality gates; running /senior-review:code-review Steps 4b/4c (adversarial verification and completeness check); consolidating or deduplicating findings from multiple parallel reviewers. DO NOT TRIGGER WHEN: single-reviewer style review without a consolidation phase, or generic team coordination (the upstream agent-teams skills cover that).

Comprehensive Interactive Brokers algotrading knowledge base covering TWS API 10.45 architecture, ib_async event-driven programming, market data subscriptions, order execution with bracket orders, historical data with pacing rules, reconnection resilience, IBC automation, and Windows production deployment. TRIGGER WHEN: building, implementing, writing, coding, creating, optimizing, or debugging IB trading systems with Python. DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Knowledge base for implementing Google Analytics 4 (GA4) and Google Tag Manager (GTM) on websites, with deep coverage of EU/GDPR Consent Mode v2 compliance, CMP selection (iubenda, Orestbida CookieConsent), event taxonomy, conversion (Key Event) configuration, remarketing audiences, framework-specific integration (vanilla HTML, Next.js, React, WordPress), Microsoft Clarity and Search Console integration, and diagnostic patterns for low-traffic sites. TRIGGER WHEN: implementing or auditing GA4, GTM, gtag, dataLayer, Consent Mode v2, cookie banner, conversion tracking, Key Events, remarketing audiences, Google Ads conversion import, Enhanced Conversions, or diagnosing why a site has traffic but no conversions. DO NOT TRIGGER WHEN: the task involves non-Google analytics (Matomo, Plausible, Fathom), server-side analytics infrastructure unrelated to GA4/GTM, BigQuery export pipelines, or pure SEO work without a measurement layer.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Build apps with the Claude Agent SDK (formerly Claude Code SDK). Covers programmatic agent loops, tool integration, subagent orchestration, prompt caching, and migration between Claude model versions. TRIGGER WHEN: code references claude-agent-sdk, user says "agent sdk", "build an agent", "programmatic claude", "claude code sdk", "sidecar", "run claude programmatically". DO NOT TRIGGER WHEN: user is using the Claude API client SDK (`anthropic`/`@anthropic-ai/sdk`) for direct chat completions, or doing general programming unrelated to agent orchestration.

Idiomatic Kotlin implementation patterns: coroutines and structured concurrency, Flow / StateFlow / SharedFlow, Kotlin Multiplatform (KMP) shared-code architecture, Jetpack Compose UI, Ktor server with JWT auth and Exposed, and type-safe DSL design (lambdas with receivers, delegated properties, inline reified, value classes). TRIGGER WHEN: building, writing, or reviewing Kotlin code using coroutines / Flow / suspend functions, expect/actual, Compose composables / ViewModels, Ktor routing, sealed-class state modeling, scope functions, or DSL builders. DO NOT TRIGGER WHEN: libGDX game work (use libgdx-development), Android Java without Kotlin, or pure JVM tuning unrelated to Kotlin language features.

Comprehensive MetaTrader 5 Python algotrading knowledge base covering the official synchronous API, polling-based event systems, order execution with fill modes, historical data functions, reconnection resilience, and Windows production deployment. Includes aiomql and ZeroMQ bridge alternatives. TRIGGER WHEN: building, implementing, writing, coding, creating, optimizing, or debugging MT5 trading systems with Python. DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

OpenTelemetry Python instrumentation knowledge base covering distributed tracing, async context propagation, custom transport propagators, sampling strategies, exporter configuration, and production observability patterns. SDK v1.42.1 target. TRIGGER WHEN: working with OpenTelemetry, distributed tracing, span instrumentation, context propagation, OTLP exporters, sampling strategies, or observability pipelines. DO NOT TRIGGER WHEN: general logging without trace correlation, or application monitoring tools unrelated to OTel.

This skill enriches vague prompts with targeted research and clarification before execution. Should be used when a prompt is determined to be vague and requires systematic research, question generation, and execution guidance. TRIGGER WHEN: the UserPromptSubmit hook flags a prompt as vague and the agent needs to research, generate clarifying questions, and wrap the prompt in an evaluation block. DO NOT TRIGGER WHEN: the prompt is already specific, or the user is invoking a slash command (the hook bypasses those via the /, #, @, ! prefixes).

Comprehensive RAG development knowledge base covering chunking, embeddings, vector databases, retrieval strategies, advanced patterns (Graph RAG, CRAG, Self-RAG, Agentic RAG), evaluation, and production deployment. TRIGGER WHEN: building, implementing, writing, coding, creating, optimizing, or auditing RAG systems. DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Master binary analysis patterns including disassembly, decompilation, control flow analysis, and code pattern recognition. Use when analyzing executables, understanding compiled code, or performing static analysis on binaries.

Master memory forensics techniques including memory acquisition, process analysis, and artifact extraction using Volatility and related tools. Use when analyzing memory dumps, investigating incidents, or performing malware analysis from RAM captures.

Reviews code against all Obsidian automated plugin review rules and reports violations with fixes. Use PROACTIVELY before any git push on an Obsidian plugin project. TRIGGER WHEN: preparing an Obsidian plugin for submission or before pushing code DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Ensures compliance with Obsidian's automated plugin review (community.obsidian.md), eslint-plugin-obsidianmd rules, and official Obsidian plugin guidelines. TRIGGER WHEN: writing, reviewing, or fixing Obsidian community plugin code DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Scaffolds project structure, manifest, tsconfig, esbuild config, and a minimal plugin class that passes Obsidian's automated plugin review. TRIGGER WHEN: the user asks to start, create, bootstrap, or initialize a new Obsidian community plugin DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Knowledge base for the codebase-mapper plugin. Provides writing guidelines, tone rules, and diagram conventions for generating human-readable project guides. Referenced by all codebase-mapper agents during document generation. TRIGGER WHEN: referenced by codebase-mapper pipeline agents (codebase-explorer, overview-writer, tech-writer, flow-writer, onboarding-writer, ops-writer, config-writer, guide-reviewer) during document generation. DO NOT TRIGGER WHEN: outside the /map-codebase pipeline (general documentation work should use docs:readme-craft or codebase-mapper:docs-create).

Progressive Web App knowledge base for 2025-2026: Web App Manifest, Service Workers (Workbox 7, Serwist), Web Push (VAPID, RFC 8030/8291/8292, Declarative Push for Safari 18.4+), install flows (beforeinstallprompt, Window Controls Overlay), OPFS storage, Project Fugu, Core Web Vitals (INP < 200ms), security (HTTPS, CSP, COOP/COEP), and distribution (Bubblewrap, PWA Builder MSIX, Capacitor). TRIGGER WHEN: building, auditing, or debugging PWAs, including manifest, service worker, Web Push, install flow, OPFS, Background Sync, Wake Lock, vite-plugin-pwa, Next.js Serwist, @angular/pwa, @vite-pwa/nuxt, Bubblewrap, TWA, PWA Builder, or Capacitor wrapping. DO NOT TRIGGER WHEN: the task is generic frontend styling (use frontend), React performance (use react-development:review-react), cross-platform security unrelated to PWA (use platform-engineering), Tauri or Electron wrappers (use tauri-development), or GA4 / analytics (use digital-marketing).

Enterprise-grade TypeScript depth covering the advanced type system (generics, mapped/conditional types, satisfies operator, branded types, discriminated unions, template literal types), JS-to-TS migration playbooks, modern toolchain setup (tsconfig strict, Vite 7, Vitest, ESLint 9 flat config, pnpm), validation patterns with Zod, type-safe React integration, NestJS API design, and LangChain.js typing. TRIGGER WHEN: migrating a JavaScript codebase to TypeScript, bootstrapping a new TS project (tsconfig + ESLint + Vite/Vitest), writing or refactoring code that uses advanced type patterns (generics, mapped/conditional types, satisfies, branded types), designing Zod schemas for runtime validation, building type-safe NestJS APIs, doing deep React + TypeScript work (typed hooks, generic components, discriminated props), or typing LangChain.js applications. Also trigger when comparing TypeScript with Java/Python enterprise approaches. DO NOT TRIGGER WHEN: writing routine TS/JS without advanced type work (use typesc

Reference knowledge base for Firefox WebExtension development. Contains browser API reference, manifest schema, AMO publishing guide, MDN URL index, and best practices. Used by the firefox-extension-dev agent for documentation lookup. TRIGGER WHEN: building, implementing, writing, coding, creating, debugging, or publishing a Firefox/WebExtension add-on (manifest.json, browser.* APIs, AMO submission, web-ext CLI). DO NOT TRIGGER WHEN: targeting Chrome-only extensions, Safari extensions, or userscripts/bookmarklets.

Comprehensive libGDX cross-platform game development knowledge base covering project generation via gdx-liftoff, the rendering pipeline, Scene2D and Ashley ECS architecture, Box2D physics, AssetManager lifecycle, Screen management, Tiled map integration, and multi-platform deployment to Desktop (LWJGL3), Android, iOS (RoboVM), and HTML5 (GWT/TeaVM). Includes libGDX 1.14.0 breaking changes and Kotlin compatibility caveats. TRIGGER WHEN: building, implementing, writing, coding, creating, optimizing, or debugging libGDX games; scaffolding or starting new libGDX projects; migrating libGDX versions; choosing libGDX architecture patterns. DO NOT TRIGGER WHEN: the task is general Java/Kotlin work unrelated to libGDX, or the engine is not libGDX (jMonkey, KorGE, Godot, Unity).

Unified Tauri 2 development knowledge base covering core patterns, desktop, and mobile. TRIGGER WHEN: working with Tauri commands, IPC, plugins, project setup, OAuth, CI/CD, window management, shell plugin, desktop bundling, platform WebViews, mobile environment setup, emulator/ADB, mobile plugins, IAP, and store deployment. DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Understand anti-reversing, obfuscation, and protection techniques encountered during software analysis. Use this skill when analyzing malware evasion techniques, when implementing anti-debugging protections for CTF challenges, when reverse engineering packed binaries, or when building security research tools that need to detect virtualized environments.

Master network protocol reverse engineering including packet analysis, protocol dissection, and custom protocol documentation. Use when analyzing network traffic, understanding proprietary protocols, or debugging network communication.

React and Next.js performance optimization guidelines from Vercel Engineering (70 rules across 8 categories). Use when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Cross-platform development rulebook covering security, architecture, and performance for SPA, PWA, mobile (iOS/Android), and desktop (Electron/Tauri) applications. MUST/DO/DON'T framework with real-world incident references and platform-specific guidance. TRIGGER WHEN: reviewing or building cross-platform apps, checking security posture, validating architecture decisions, optimizing performance, or auditing code against industry standards (OWASP, Core Web Vitals, OAuth 2.1). DO NOT TRIGGER WHEN: the task is purely about UI design, copywriting, or business logic unrelated to platform engineering concerns.

Knowledge base defining 24 common AI writing patterns (inflated symbolism, promotional language, etc.) and guidelines on how to rewrite them to sound naturally human. TRIGGER WHEN: editing or reviewing text to remove AI traces, or when asked to humanize text. DO NOT TRIGGER WHEN: the task involves refactoring source code or when the task does not involve prose/text refinement.

Systematic code refactoring skill that transforms complex, hard-to-understand code into clear, well-documented, maintainable code while preserving correctness. Applies structured refactoring patterns with validation. TRIGGER WHEN: users request "readable", "maintainable", or "clean" code, during code reviews flagging comprehension issues, for legacy code modernization, or in educational/onboarding contexts DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Generate focused, behavior-driven Python tests using TDD methodology with pytest. TRIGGER WHEN: writing Python tests, improving coverage, reviewing test quality, or practicing red-green-refactor workflows with pytest. DO NOT TRIGGER WHEN: the target is non-Python (use testing:tdd for language-agnostic TDD or testing:e2e-testing-patterns for browser E2E).

Create optimized multi-stage Dockerfiles for any language or framework. TRIGGER WHEN: creating Dockerfiles, optimizing container images, multi-stage builds, Docker best practices. DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Pydantic v2 patterns for production Python: validators (`@field_validator`, `@model_validator`), computed fields, strict types, discriminated unions, settings management, `model_validate` / `model_dump`, `condecimal` and `Annotated[Decimal, ...]` for money, performance tips, and a v1 to v2 migration checklist. Also covers FastAPI integration (response_model serialization, request validation, error envelope customization). TRIGGER WHEN: writing or refactoring Pydantic models in Python 3.10+; migrating a codebase from Pydantic v1 to v2; choosing between `Annotated[Decimal, ...]` vs `condecimal`; hitting v2 performance or serialization surprises; designing FastAPI request/response schemas or error envelopes with Pydantic. DO NOT TRIGGER WHEN: the task is Python testing (use python-tdd), generic typing unrelated to Pydantic (use mypy / typing docs), or non-Python schema work (use typescript-development for Zod / io-ts).