Skill Creator

2389-research

26 published skills · 76 GitHub stars across the catalog. View on GitHub ↗

gtm-partner

2389-research's avatarfrom 2389-research★ 4

Strategic go-to-market partner that recommends channels, validates strategy with the user, and generates only the assets that matter. Use when a user has a validated business idea and needs tailored GTM strategy, not generic marketing assets.

building-multiagent-systems

2389-research's avatarfrom 2389-research★ 3

Use when designing or implementing systems with orchestrators, sub-agents, and tool coordination - guides through architecture patterns, coordination mechanisms, and production-ready implementations for multi-agent workflows

ceo-personal-os

2389-research's avatarfrom 2389-research★ 3

Use when building a personal productivity or operating system for a CEO, founder, or executive - when user mentions annual reviews, personal OS, life planning, goal setting systems, executive coaching frameworks, or Bill Campbell / Trillion Dollar Coach principles

css-developmentcreate-component

2389-research's avatarfrom 2389-research★ 3

Guide creating new CSS components following Tailwind + semantic component patterns with dark mode support and test coverage

css-developmentrefactor

2389-research's avatarfrom 2389-research★ 3

Transform existing CSS (inline styles, utility classes in markup, scattered CSS) into semantic component patterns with dark mode support and tests

css-development

2389-research's avatarfrom 2389-research★ 3

Use when working with CSS, creating components, styling elements, refactoring styles, or reviewing CSS code. Guides CSS development following Tailwind + semantic component patterns with dark mode support and test coverage.

css-developmentvalidate

2389-research's avatarfrom 2389-research★ 3

Review existing CSS against established Tailwind + semantic component patterns, checking naming, dark mode, tests, and documentation

firebase-developmentproject-setup

2389-research's avatarfrom 2389-research★ 3

Initialize new Firebase project with proven architecture. Guides through firebase init, choosing hosting/auth/functions patterns, emulator configuration, and initial project structure setup.

firebase-development

2389-research's avatarfrom 2389-research★ 3

Comprehensive Firebase development guidance covering project setup, feature development, debugging, and validation. Auto-detects intent and routes to specialized sub-skills. Patterns extracted from production projects.

firebase-developmentvalidate

2389-research's avatarfrom 2389-research★ 3

Review Firebase code against security model and best practices. Validates firebase.json structure, firestore.rules patterns, functions architecture, authentication implementation, test coverage, and emulator configuration.

fresh-eyes-review

2389-research's avatarfrom 2389-research★ 3

Use before git commit, before PR creation, before declaring done - mandatory final sanity check after tests pass; catches SQL injection, security vulnerabilities, edge cases, and business logic errors that slip through despite passing tests; the last line of defense before code ships

remote-system-maintenance

2389-research's avatarfrom 2389-research★ 3

Use when performing system maintenance or diagnostics on remote Linux systems via tmux - provides structured checklists for Ubuntu/Debian cleanup (apt, journal, snap revisions), diagnostic procedures, and log file templates with quantification patterns

scenario-testing

2389-research's avatarfrom 2389-research★ 3

Use when writing tests, validating features, or tempted to use mocks - enforces scenario-driven end-to-end testing with real dependencies; mocks are lies that hide bugs; scenarios with real data are the only source of truth

terminal-title

2389-research's avatarfrom 2389-research★ 3

MANDATORY at session start. REQUIRED when user topic shifts (from debugging to docs, from frontend to backend, etc). Updates terminal title with emoji + project + topic. SessionStart hook auto-invokes. Claude must also invoke on all topic changes.

cookoff

2389-research's avatarfrom 2389-research★ 3

MANDATORY implementation wrapper. ALWAYS invoke when moving from design→code. Present 3 options: (1) Cookoff - 2-5 parallel agents compete, each creates own plan, pick best, (2) Single subagent, (3) Local. Triggers: "let's build", "implement", "looks good", user picks implementation option, ANY signal to start coding after design. This skill MUST run before writing-plans/executing-plans at design boundaries. For exploring DIFFERENT designs, use omakase-off.

omakase-off

2389-research's avatarfrom 2389-research★ 3

ALWAYS invoke FIRST on ANY "build/create/implement/add feature" request. This skill WRAPS brainstorming - it decides the approach. Present choice BEFORE any brainstorming starts: (1) Brainstorm together step-by-step, OR (2) Omakase - I generate 3-5 best approaches, implement in parallel, tests pick winner. If user picks brainstorming, check if brainstorming skill exists - if yes use it, if no do brainstorming yourself (ask questions, propose options, validate). Also triggers DURING brainstorming on 2+ "not sure"/"don't know" responses. For same design competing implementations, use cookoff.

test-kitchen

2389-research's avatarfrom 2389-research★ 3

Parallel implementation framework. Omakase-off triggers FIRST on build/create requests (wraps brainstorming). Cookoff triggers at design→implementation transition (wraps execution). Together they provide entry and exit gates for the Test Kitchen workflow.

worldview-synthesis

2389-research's avatarfrom 2389-research★ 3

Use when someone wants to articulate, explore, or document their personal worldview, values, or philosophy. Systematic interrogation that surfaces beliefs, identifies tensions, and generates narrative outputs.

using-xtool

2389-research's avatarfrom 2389-research★ 3

Use when building iOS apps with xtool (Xcode-free iOS development), creating xtool projects, adding app extensions (widgets, share extensions), or configuring xtool.yml. Triggers on mentions of xtool, SwiftPM iOS apps, building iOS on Linux/Windows, or app extension setup.

binary-retriage

2389-research's avatarfrom 2389-research★ 3

Use when first encountering an unknown binary, ELF file, executable, or firmware blob. Fast fingerprinting via rabin2 - architecture detection (ARM, x86, MIPS), ABI identification, dependency mapping, string extraction. Keywords - "what is this binary", "identify architecture", "check file type", "rabin2", "file analysis", "quick scan"

binary-resynthesis

2389-research's avatarfrom 2389-research★ 3

Use when ready to document findings, generate a report, or summarize binary analysis results. Compiles analysis findings into structured reports - correlates facts from triage/static/dynamic phases, validates hypotheses, generates documentation with evidence chains. Keywords - "summarize findings", "generate report", "document analysis", "what did we find", "write up results", "export findings"

binary-restatic-analysis

2389-research's avatarfrom 2389-research★ 3

Use when analyzing binary structure, disassembling code, or decompiling functions. Deep static analysis via radare2 (r2) and Ghidra headless - function enumeration, cross-references (xrefs), decompilation, control flow graphs. Keywords - "disassemble", "decompile", "what does this function do", "find functions", "analyze code", "r2", "ghidra", "pdg", "afl"

binary-redynamic-analysis

2389-research's avatarfrom 2389-research★ 3

Use when you need to run a binary, trace execution, or observe runtime behavior. Runtime analysis via QEMU emulation, GDB debugging, and Frida hooking - syscall tracing (strace), breakpoints, memory inspection, function interception. Keywords - "run binary", "execute", "debug", "trace syscalls", "set breakpoint", "qemu", "gdb", "frida", "strace", "watch memory"

binary-re

2389-research's avatarfrom 2389-research★ 3

Use when user has a binary/executable/bytecode and wants to understand what it does, how it works, or analyze its behavior. Triggers on "I have a binary", "this executable", "what does this binary do", "how does this work", "can you analyze", "figure out what", "reverse engineer", "disassemble", "decompile", "pyc file", "python bytecode", "obfuscated python", "marshal". Covers ELF, shared libraries, kernel modules, firmware, Python bytecode for ARM64, ARMv7, x86_64, MIPS, RISC-V using radare2, Ghidra, GDB, QEMU, pycdc.