发现 Skills

ESP32 debug knowledge base: boot sequence, error codes, MQTT topics, data flows, circuit breaker, diagnostic workflows, cross-layer commands. Trigger keywords: esp32, serial, firmware, boot, sensor, actuator, gpio, heartbeat, safemode, watchdog, circuit-breaker, wokwi

Comprehensive guide for building Model Context Protocol (MCP) servers with support for tools, resources, prompts, and authentication. Use when: (1) Creating custom MCP servers, (2) Integrating external APIs with Claude, (3) Building tool servers for specialized domains, (4) Creating resource providers for documentation, (5) Implementing authentication and security

Comprehensive PDF manipulation, extraction, and generation with support for text extraction, form filling, merging, splitting, annotations, and creation. Use when working with .pdf files for: (1) Extracting text and tables, (2) Filling PDF forms, (3) Merging/splitting PDFs, (4) Creating PDFs programmatically, (5) Adding watermarks/annotations, (6) PDF metadata management

Long-term memory and multi-agent orchestration for Claude Code. Provides persistent SQLite-backed memory across all projects and sessions, plus coordinated Planner/Coder/Debugger/Reviewer agents. Use when the user invokes /hive, /hive-memory, /hive-status, or /hive-compress.

Check CI status, view workflow runs, and inspect logs for the current git branch. Use when user types /ci or asks about CI, build status, workflow runs, or GitHub Actions.

Migrating OCaml projects from ocamlbuild/topkg to dune. Use when discussing _tags files, .mllib files, pkg/pkg.ml, topkg, or build system migration.

AI-Driven Development Life Cycle workflow. Use when user says "Using AI-DLC...", "AI-DLC로...", "Start AI-DLC", "start development", "build an app", "create a project", or wants intelligent adaptive software development workflow with requirements analysis, design, and implementation phases.

Use when tests themselves are broken, test quality is poor, or a user wants to fix or improve tests. Typical triggers: "test is broken", "test is wrong", "test is flaky", "make tests pass", "tests need updating", "green mirage", "tests pass but shouldn't", "audit report findings", "run and fix tests". Three modes: fix specific tests, process green-mirage audit findings, and run-then-fix. NOT for: bugs in production code that are correctly caught by tests (use debugging instead).

Use when building, creating, modifying, or planning any code change. Triggers: "implement X", "build Y", "add feature Z", "create X", "change how X works", "modify Y", "update the Z", "refactor X", "rework Y", "restructure Z", "make X do Y", "let's plan how to", "plan the implementation", "how should we implement", "how would you build", "what's the best way to implement", "I want to...", "We need...", "Would be great to...", "Can we add...", "Let's add...", "Let's build...", "Let's make...", "start a new project". Also for: new projects, repos, templates, greenfield development, refactoring, migrations, multi-file modifications, any code change requiring planning. PREFER THIS OVER plan mode or ad-hoc implementation for ANY substantive code change. NOT for: bug fixes (use debugging), pure research (use deep-research), questions about existing code without intent to change it, or test-only fixes (use fixing-tests).

Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.

Deploy Evolution API WhatsApp gateway dengan Docker Compose, PostgreSQL, Redis, dan Apache reverse proxy di VPS Linux. Untuk integrasi dengan n8n cloud via webhook.

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing 'goldfish brain', or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

Enter explore mode — a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think something through before or during a change.

INTERNAL-ONLY permission bootstrap. Grants MCP tool + file-op permissions for the current session (except GetTableContents / GetSqlQuery, which remain prompt-gated). MUST be invoked by a parent skill (create-program, setup, team, analyze-*, create-object) — direct user invocation is rejected with a redirect message.

Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

PDF/이미지를 Claude vision으로 OCR하여 마크다운 변환. MUST use this skill when user: (1) asks to convert PDF/image to markdown, (2) asks to OCR any file, (3) sends PDF/image file and asks to extract/read/변환/추출, (4) mentions 'OCR', 'PDF 변환', '이미지 변환', '텍스트 추출'. This skill uses Task agent to protect main context - NEVER process files directly in main context.

Scan systems and dependencies for CVEs and security vulnerabilities. Use tools like Nessus, OpenVAS, and Qualys to identify and prioritize vulnerabilities. Use when performing security assessments, compliance scanning, or vulnerability management.

Submit an implementation plan to GPT 5.2-xhigh for review by a senior engineer persona. The Oracle provides direct, honest critique focused on simplicity and pragmatic excellence. Use when you have a detailed implementation plan and want a second opinion before coding. Triggers include review my plan, get Oracle feedback, consult the Oracle, plan review, or when you want senior engineer critique on an implementation approach.

Expert guidance for creating premium, performant animations in React using Motion (motion.dev). Covers all animation types, best practices, accessibility, and performance optimization.

Engineering operating model for teams where AI agents generate a large share of implementation output.

Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.