hermes-v7

Funny animal podcast creation assistant. Given a topic, automatically generates a comedic podcast video hosted by two animal "hosts." Full pipeline: character design, comedy script, character portraits, TTS voice + Seedance 2.0 video generation, subtitle/pop-text/sound-effect post-production. Trigger words: animal podcast, funny podcast, pet podcast, animal talk show, pet talk show.

Professional anime/2D art style generation skill. Covers 14 sub-styles (modern Japanese anime/moe, retro Japanese cel-shading, Japanese shonen, Japanese shojo, Ghibli, Makoto Shinkai, Chinese xianxia/ink wash, modern Chinese anime, Chinese 3D fantasy, Korean webtoon, Korean impasto, Western cartoon, chibi/moe, 2D cyberpunk) + 5 anti-failure iron laws + cross-style shared rules (character lock / facial proportion spec / stroke consistency / universal negative). Core capabilities: precise style targeting, consistent character identity, cross-style conversion. Trigger: "anime", "2D art", "manga", "illustration", "Japanese anime", "Chinese anime", "Korean webtoon", "webtoon", "Western cartoon", "ghibli", "shinkai", "ufotable", "trigger style", "cel-shading", "impasto", "chibi", "moe", "catgirl", "Chinese 3D fantasy", "xianxia", "ink wash", "hanfu character", "cyberpunk anime", "draw an anime character", "make an anime avatar", "anime character", "anime style". NOT for: photorealistic (use image agent default) / s

Specialized in anime/2D/character stylization for image generation and conversion. Covers Japanese, Chinese, Korean, and Western art style families. Uses provenance analysis to trace reference images' style DNA, performs a 10-dimension analysis → 3-dimension collapse to precisely lock the style's essence, then matches the optimal tool and prompt approach for generation. Trigger on: "anime-ify", "2D style", "convert to anime", "cel-shading", "ghibli style", "Korean watercolor", "fantasy 3D", "chibi", "Japanese anime style", "style conversion", "manga style", "character illustration", "anime style", "webtoon style", or any request involving converting content into a specific anime/2D art style. Key distinction: User requests generation or conversion to a specific anime/2D art style. Do NOT trigger for: photorealistic photography style, pure logo design, general image editing (crop/background removal etc.).

Audiobook creation assistant. Converts book text into multi-character narrated audio, supporting audiobook production, multi-character voiceover, novel narration, TTS voiceover, and read-aloud scenarios. Automatically identifies dialogue and narration, assigns a distinct voice to each character, intelligently adds pause markers, and generates natural, fluent audiobook audio. Trigger phrases: audiobook, read aloud, TTS book, multi-character voiceover, novel narration, book narration, voice acting, narration, 有声书, 朗读, 读书, 多角色配音, 小说朗读, 读书配音. Supports chapter-level generation — user confirms the first chapter, then remaining chapters continue sequentially.

Beat-sync video editing skill. Input music (URL / local file / AI-generated) + video or image assets, automatically performs energy-tension analysis → smart trimming → beat detection → beat-synced timeline generation → asset matching → ffmpeg concatenation, outputting a beat-synced video perfectly aligned to the music. Supports image slideshows, video clips, and mixed assets as input. Supports every-N-beat asset switching, automatic intro/chorus segmentation, user-annotated keypoints, and other beat-sync modes. Trigger words include: music beat sync, beat-sync editing, beat sync, beat-sync video, beat-synced editing, beat-sync video, music rhythm editing, rhythm beat sync, beat detection, edit to the beat, auto beat sync, music sync edit.

Video project push tool. Programmatically creates editing projects via Python scripts, with one-click push to JianyingPro or CapCut. Direct mode creates project files directly in the local JianyingPro/CapCut draft directory — open the app and start editing. Built on pyJianYingDraft (PyPI). Trigger words include: JianyingPro, CapCut, push, push to JianyingPro, capcut, export to JianyingPro.

Generate a complete design system (tokens, colors, typography, spacing scale) as JSON/CSS variables from a brief. Trigger phrases: creative/ui, design, system. Converted from Hermes-Skill (Yuno's mastery library).

Drama original soundtrack creation assistant. Creates complete soundtrack suites for TV series, films, and short dramas, including character theme songs, opening themes (OP), ending themes (ED), and scene background music (BGM). Deeply analyzes the plot based on scripts and character biographies, creating custom theme songs for each main character, composing opening and ending themes for the entire show, and crafting background music for key dramatic moments. Supports importing scripts from the short-drama-screenwriter skill, as well as external scripts and character biographies. Trigger words include: soundtrack, score, theme song, opening theme, ending theme, BGM, OST, drama soundtrack, film score, series score, character theme, character theme song, compose music for a drama, film and TV music, create a theme song, create an ending theme, climax BGM.

Dynamic poster / motion graphic creator for product marketing. Transforms brand assets (logo, product photos) into surreal short video posters using "impossible juxtaposition" — products in physics-defying scenes, shot with realism. Trigger: "dynamic poster," "motion poster," "animated poster," "video poster," "product poster video," "social media poster," "event teaser," "motion graphics," "animated visual," "brand motion design," "poster animation." NOT for: long-form promo (use promo-video), MV (use mv-creator), static posters.

Professional film storyboard / film still / character card design skill. Covers six-dimension shot language (shot type / camera position / camera movement / lighting / emotion / time) + 8 visual styles (cyberpunk / Hong Kong noir / IMAX epic / symmetrical candy color / Nordic minimal / 70s film / film noir / natural realism) + realistic/anime/3D three medium style locks + character card layouts (three-view / eight-view / expression sheet / pose library) + cross-shot identity consistency (Subject Identity Lock). Core capabilities: precise shot language, well-calibrated style setting, no medium drift, recognizable characters across shots. Trigger: "storyboard", "cinematic", "film still", "movie feel", "shot", "shot type", "camera angle", "camera movement", "lighting", "composition", "three-view", "four-view", "eight-view", "multi-view", "multi-angle", "character sheet", "character card", "character design", "character illustration", "expression sheet", "expression variant", "pose library", "pose sheet", "cyberp

Yuno's persistent memory bank. When user prompt seems ambiguous or context-dependent (e.g. "what did we decide yesterday", "how did we set up X", "remember that bug"), check this skill for relevant past context. Memory is keyed by subject. Converted from Hermes/Mnemosyne. Trigger phrases: memory, hermes, context, yuno, remember, recall.

Invoke when a user shares a reference image and wants new images with the same "feel" — composition, color palette, lighting, style, or mood — but different content. Analyzes the image across 10 aesthetic dimensions, collapses into 3 axes (Form / Aesthetic / Mood), then generates using a model matched to the original's origin with adapted prompt style. Supports iterative refinement. Trigger on: "remix this image," "make something like this," "same vibe different content," "I like this style make me…," "replicate this feel," "same style different content," "make one with this feeling," "create something in this style," "I like how this image feels," "recreate this effect," "style transfer," "image remix," or any request where someone shares an image and wants new images inspired by its aesthetic. Key distinction: user wants images INSPIRED BY the reference, not a copy or edit of it. Do NOT trigger for: image editing, upscaling, format conversion, image-to-video generation.

Orchestrate parallel AI agent workstreams — multi-agent deep research (3 parallel experts), research orchestration Trigger phrases: orchestration/multi, agent, orchestration. Converted from Hermes-Skill (Yuno's mastery library).

Trigger-watchlist with the 20 most common pitfalls when spawning delegate_task subagents — symptom-based quick reference. Load BEFORE every delegate_task call to catch common mistakes (phantom fixes, timeouts, missing output paths, ignored model param, etc). Complement to multi-agent-orchestration which covers the pattern; this skill covers the failure modes. Trigger phrases: orchestration/multi, agent, pitfalls, cheatsheet. Converted from Hermes-Skill (Yuno's mastery library).

Quick-reference navigator for all 169 active Hermes skills. Groups skills by domain-cluster (multi-agent, greyhack, mlops, creative, etc), tells you which skill to load for which task, flags clusters with overlap or gaps. Built from a real scan on 2026-07-02. Companion to the skill_view function — load this FIRST to decide which skill to load next. Trigger phrases: orchestration/skill, navigator. Converted from Hermes-Skill (Yuno's mastery library).

Create new Skills, modify existing Skills, save the current conversation workflow as a reusable Skill, guide users to install Skills from the marketplace, and understand directory structure. Trigger words: create skill, modify skill, save as skill, save this, turn into a skill, solidify workflow, remember this approach, want to do this again, install skill, download skill, skill marketplace, manage skill, create skill, save as skill, turn this into a skill, make this reusable, update skill, install skill, setup skill. Also trigger when the user reviews a completed creative output and expresses intent to repeat the same process with different inputs.

Skill quality review tool. Reviews SKILL.md structure, description quality, trigger-word coverage, and best-practice compliance. Read-only analysis — never modifies files. Trigger phrases: review skill, audit skill, skill quality check, check skill quality.

AI video/image prompt engineering expert. Triggered when users need to write or optimize prompts for AI video or image generation tools. Helps users craft high-quality generation prompts for various models (Kling, Veo3, Wan, Gemini, Midjourney, Seedance, proprietary models, etc.), incorporating model-specific best practices and formatting requirements. Trigger phrases: video prompt, image prompt, prompt engineering, how to write prompts, optimize prompt, prompt writing.

Voice cloning assistant. Clone a voice from a reference audio sample and return a voice_id for subsequent TTS generation via audios_generation. Built-in legal compliance confirmation (mandatory), audio duration preprocessing (auto loop/trim), noise reduction & volume normalization, language detection & demo generation, post-clone metadata collection. Trigger phrases: voice clone, clone voice, 音色克隆, 声音克隆, 复刻音色, 复刻声音.

YouTube video creation assistant. Pipeline from topic planning to high-CTR thumbnail generation. Covers topic planning, retention-optimized scripting, and high-conversion YouTube thumbnail generation. Stops after thumbnail — does NOT generate concept images, voice, video clips, or final assembly. Trigger phrases: YouTube, youtube creator, YouTube video, make a video, YouTube script, thumbnail, YouTube SEO.

Basti's working-style preferences — honest testing over claims, concrete options for decisions, DB-edit safety, whitelist-based cleanup, documentation policy. Load when starting a new session with Basti to align style/approach. Trigger phrases: yuno, user, preferences. Converted from Hermes-Skill (Yuno's mastery library).

Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.

Configure, extend, or contribute to Hermes Agent.

Delegate coding to OpenCode CLI (features, PR review).

ASCII video: convert video/audio to colored ASCII MP4/GIF.

Manim CE animations: 3Blue1Brown math/algo videos.

p5.js sketches: gen art, shaders, interactive, 3D.

Songwriting craft and Suno AI music prompts.

Hermes gateway: messaging platform setup, DM authorization, and troubleshooting.

Post-update checks, CLI quirks, troubleshooting patterns, and hardening workflows for Hermes Agent. Covers the gaps the bundled hermes-agent skill doesn't address: real-world maintenance, update side-effects, provider security, Ollama integration, and gotchas.

Audit and harden the host security baseline of a Linux laptop or workstation — fwupd HSI levels, TPM / BootGuard / Secure Boot / kernel lockdown, kernel taint diagnosis, ACPI BIOS bug triage, and Linux power management (s2idle, suspend inhibitors, GNOME gsd-power). Use when the user mentions a Device Security Report, fwupd, HSI, host security, firmware updates, "laptop security", or asks to fix a specific HSI failure.

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.

Fix Linux display issues: broken EDID, custom modelines, multi-monitor setup, GPU driver diagnosis, and refresh rate configuration. Covers xrandr workflows, autostart persistence, and NVIDIA G-Sync activation.

Sichere Installation, Konfiguration und vollständige Entfernung lokaler AI-Services (Ollama, llama.cpp, etc.) inklusive Hermes-Config-Synchronisation und Offline/Online-Fallback-Strategien.

Maximize gaming performance on NVIDIA Optimus laptops under Linux: enable Dynamic Boost (nvidia-powerd) when the driver ships no service/DBus policy, set up Feral GameMode, and handle the intel_pstate/EPP governor quirk.

Linux-Sicherheitsaudit: offene Ports, Dienste, Berechtigungen, Firewall, Benutzer, Updates, schnelle Fixes. Mit Dokumentation.

Webhook subscriptions: event-driven agent runs.

Leitfaden für Docker-Installation auf Ubuntu Server (frische VM).

Exploratory QA of web apps: find bugs, evidence, reports.