Claude Skills by theheavenlyd3mon

Analyze unknown binary files through a deterministic CLI that wraps Ghidra's static-analysis engine. Use when you need to inspect a PE, ELF, or Mach-O file — triage suspicious binaries, map imported APIs, decompile functions, trace call paths, or produce structured evidence reports. Do not use for runtime analysis (debugging, dynamic tracing, sandbox execution), for modifying or patching binaries, or for binaries you already know everything about. The skill owns planning, hypothesis formation...

Operate, explain, review, and deploy T3MP3ST-class offensive-security meta-harnesses: multi-agent red-team automation with a local-agent brain, arsenal wrappers, scope gating, War Room UI, and reproducibility checks. Use when the task involves T3MP3ST setup, architecture review, agent-loop wiring, scope enforcement, benchmark verification, or beginner-friendly red-team explanations.

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Safe web scraping and research: detect and neutralize prompt injection, code injection, and content-based attacks in scraped web content before it enters the agent's context.

Generate flat, minimal educational SVG visuals as HTML.

Adaptive pedagogy for AI tutoring — detect learner comprehension level, adjust explanation depth via Bloom's taxonomy, tier analogies, modulate pacing, and check understanding. Core methodology for the educate profile.

Use when reviewing a past lesson to read aloud via TTS.

Use when the user wants text read aloud via TTS.

Turn internal knowledge into clean, shareable guides for newcomers. Use when the user asks for a write-up, explainer, or guide that someone else will read — especially if they don't know the system.

Generate step-by-step math problem-solving tutorial videos in Chinese (Mandarin). Use when: (1) a user provides a math problem and wants an explanation video, (2) someone says "make a math tutorial", "explain this equation", "create a teaching video for this problem", "讲解这道题", "生成解题视频", (3) the user wants a Chinese-language math lesson covering formulas, equations, or geometric figures, (4) the user shares a math problem in text or LaTeX and asks for a video walkthrough, (5) the input is an i...

Systematically research, evaluate, and extract insights from open-source projects (GitHub repos, docs sites, community resources). Multi-tool deep-dive: README → subdirectories → external docs → synthesis.

Hermes-native research pipeline: multi-phase agents, integrity gates, source verification, claim audit. Inspired by ARS architecture.

Write accurate technical docs about systems, tools, and stacks. Covers setup guides, architecture overviews, and component inventories. Core principle: verify before documenting.

Orchestrate large fan-out work as a plan-in-code "workflow" so the agent's context holds only the final verified answer, not the exhaust of hundreds of intermediate steps. Use for codebase-wide sweeps, large migrations, multi-angle research, and any task too big for one context window where the split strategy is known enough to script. Includes the adversarial-convergence verification recipe (independent attempts + refuters, keep only surviving claims).

Kanban multi-agent workflow: orchestrator decomposition playbook, worker lifecycle, task routing, and pitfalls.

AI-assisted trading research agent — builds agents that research markets, generate trade signals, and track P&L, while the human makes all execution decisions. Covers architecture, data sources, cron scheduling, and the human-in-the-loop pattern.

AI-Trader platform integration — register agent, publish signals, copy-trade, browse signal feed. Requires AI_TRADER_API_KEY or email registration.

Oracle's market analysis playbook — gather data from multiple sources, produce structured briefs with probability framing, separate analysis from advice.

Read-only financial market intelligence via AI-Trader's Market Intel API — macro signals, ETF flows, stock analysis, grouped news. No auth required for reads.

Polymarket prediction market integration — read markets, orderbooks, publish simulated trades. Direct API reads + AI-Trader for simulated execution.

Multi-agent LLM trading analysis framework — 4 specialist analysts (fundamentals, sentiment, news, technical) with bullish/bearish debate, risk management, and portfolio decisions. Wraps TradingAgents CLI/Python API.

Track trade profitability with automatic logging to Obsidian or Notion. Simple CLI for adding/closing trades, auto-generates notes with PnL and win rate metrics.

PhD-level expertise in data science, statistics, and machine learning. Use when the task requires rigorous statistical analysis, experimental design, causal inference, advanced modeling, research methodology, or data science project leadership. Load when the user asks about statistical methods, experimental design, model selection, A/B testing, hypothesis testing, power analysis, regression, causality, Bayesian analysis, or research methodology.

Build and review assumptions-led financial models, unit economics, pricing, fundraising scenarios, and SaaS operating metrics. Use when calculating CAC, LTV, payback, runway, ARR, churn, NDR, Rule of 40, or sales efficiency; when modeling revenue, costs, cash flow, pricing, cap tables, or financing.

Author live widget apps for the Hermes TUI dock.

Orchestrate large fan-out work as a plan-in-code "workflow" so the agent's context holds only the final verified answer, not the exhaust of hundreds of intermediate steps. Use for codebase-wide sweeps, large migrations, multi-angle research, and any task too big for one context window where the split strategy is known enough to script. Includes the adversarial-convergence verification recipe (independent attempts + refuters, keep only surviving claims).

Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.

Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.

Write desktop app plugins that add UI panes and commands.

Author a Hermes color theme that skins every surface.

Perform a comprehensive security audit of a Hermes installation — check secrets, permissions, network exposure, code patterns, dependencies, and infrastructure. Returns prioritized findings with remediation steps.

Comprehensive security hardening for Hermes installations — fixes permissions, sets up secret scanning, configures macOS Keychain integration, creates security policies, and installs pre-commit hooks.

Configure Hermes Agent as a Discord moderation / community-management bot. Covers Dev Portal app+bot creation, the correct SCOPED permission integer for moderation (NOT the docs' chat-only default), and gateway .env scoping (home channel, allowed/ignored channels, allowed roles). Also answers "what Discord skills are available?" → there are none; Discord is gateway config, not a downloadable skill.

Run before committing code. Catches mistakes Katana can't — secrets in code, missing validation, weak auth, debug leftovers.

Author live widget apps for the Hermes TUI dock.

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Safe web scraping and research: detect and neutralize prompt injection, code injection, and content-based attacks in scraped web content before it enters the agent's context.

Layered defense against npm/PyPI supply chain attacks: install-time guards, CI/CD hardening, automated dependency audits, and incident response. Auto-triggers on relevant operations.

Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.

Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.

Deploy, configure, and manage CrowdSec — the open-source, collaborative

Use Docker Compose to define, run, debug, and harden multi-container applications. Load for compose.yaml design, networking, volumes, secrets, profiles, overrides, watch mode, lifecycle operations, or troubleshooting.

Build, configure, flash, test, debug, and recover firmware for ESP32-family boards, including ESP-IDF C/C++, Arduino/PlatformIO, MicroPython, CircuitPython, ESPHome, Zephyr, Rust, and NuttX. Use when identifying an ESP32 board, choosing a framework, wiring GPIO or peripheral buses, integrating sensors or actuators, diagnosing serial/boot/power/network failures, or planning OTA and production security. Do not use as a substitute for the exact board schematic, SoC datasheet, or attached compone...

Administer and troubleshoot remote Linux, FreeBSD, NetBSD, OpenBSD, and macOS systems safely, one host or a fleet at a time. Use when a task requires SSH, Ansible, Paramiko, POSIX diagnostics, service management, software updates, system configuration, firewall changes, or evidence-led remote operations.

Install, configure, operate, secure, automate, tune, troubleshoot, and recover restic backups across local, SFTP, S3-compatible, cloud, and REST backends. Use when creating or managing a restic repository, designing backup or retention policy, validating restores, handling repository health or locks, moving repositories, or building safe scheduled backup jobs. Do not use for a generic file-copy task that does not need encrypted, deduplicated snapshots.

Author live widget apps for the Hermes TUI dock.

Build and maintain a Hermes-driven smart mirror / information display — MagicMirror² on Raspberry Pi, custom module for Hermes push integration, scheduled + on-demand content delivery.

Orchestrate large fan-out work as a plan-in-code "workflow" so the agent's context holds only the final verified answer, not the exhaust of hundreds of intermediate steps. Use for codebase-wide sweeps, large migrations, multi-angle research, and any task too big for one context window where the split strategy is known enough to script. Includes the adversarial-convergence verification recipe (independent attempts + refuters, keep only surviving claims).

Delegate coding tasks to external CLI agents (Claude Code, Codex, OpenCode) via Hermes terminal. Covers orchestration patterns, parallel work, PR reviews, and tool selection.

Build-in-public infrastructure plan — VPS setup, security hardening, social media manager profile, GitHub integration, content strategy. Use when setting up, expanding, or troubleshooting the build-in-public pipeline.