Delegate coding to Claude Code CLI (features, PRs).

Delegate coding to OpenAI Codex CLI (features, PRs).

Configure, extend, or contribute to Hermes Agent.

Manage Hermes Agent configuration — providers, models, fallbacks, terminal backends, and common config pitfalls. Use when changing or verifying Hermes settings, switching providers, or diagnosing config-related issues.

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

Route tasks to the right model — when to use DeepSeek V4 Pro (primary), when to delegate to Claude Code (taste/editorial/troubleshooting), and when other models fit. Proactive handoff triggers and decision framework.

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

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

Infographics: 21 layouts x 21 styles (信息图, 可视化).

Design one-off HTML artifacts (landing, deck, prototype).

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

Author/validate/export Google's DESIGN.md token spec files.

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

Humanize text: strip AI-isms and add real voice.

Manim CE animations: 3Blue1Brown math/algo videos.

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

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.

Throwaway HTML mockups: 2-3 design variants to compare.

Songwriting craft and Suno AI music prompts.

Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

Iterative Python via live Jupyter kernel (hamelnb).

Skill for beelink gti14

Check Claude session usage before delegating — reads the Claude Usage Widget config and warns when approaching rate limits.

Deploy static websites, dashboards, and files to web servers via FTP. Use when Peter asks to upload, deploy, or publish a site, dashboard, portal, or files to his server (ftp.peterbdowell.com or others).

Connect MCP servers to Hermes — discovery, setup, config, auth, troubleshooting.

Set up and configure Hermes memory providers — Hindsight, Holographic, Honcho, Mem0, etc. Covers interactive setup, manual config, package installation, Windows quirks, and verification.

Skill for hermes remote machine

Post-reboot recovery verification, system diagnostics, and performance tuning for Hermes Agent

Safe workflow for applying Hermes Agent updates on Windows without venv-lock loops, merge conflicts, or gateway failures.

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.

Diagnose and disable stale automation from other AI/automation tools (Clairvoyance, Claude Desktop, etc.) when migrating to Hermes. Use when the user reports a schedule, script, or email that was set up in another tool and needs to be found and stopped.

Silent watchdog cron jobs for website uptime and price monitoring using no_agent=True scripts

Diagnose and repair Windows disks, USB drives, and partition issues via PowerShell. Use when Peter reports a drive not showing full capacity, "needs to be formatted" errors, corrupted filesystems, or needing to wipe/reformat a drive.

Track and fix Windows console pop-up windows in Hermes Agent — subprocess calls missing CREATE_NO_WINDOW, MCP desktop app retries, and launcher quirks.

Suppress uv.exe and pip console popups on Windows by adding CREATE_NO_WINDOW to ALL subprocess calls across the Hermes codebase.

Himalaya CLI: IMAP/SMTP email from terminal.

Skill for wtw member support

Skill for wtw membership email

Inspect codebases w/ pygount: LOC, languages, ratios.

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

Review PRs: diffs, inline comments via gh or REST.

Create, triage, label, assign GitHub issues via gh or REST.

GitHub PR lifecycle: branch, commit, open, CI, merge.

Clone/create/fork repos; manage remotes, releases.

Skill for dee dee voice

Skill for paul voice

Skill for rx home test

Skill for touchstone essentials

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

HuggingFace hf CLI: search/download/upload models, datasets.

llama.cpp local GGUF inference + HF Hub model discovery.

SAM: zero-shot image segmentation via points, boxes, masks.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

W&B: log ML experiments, sweeps, model registry, dashboards.

Integrate with Descript via REST API — import media, AI edit (Underlord), publish, export transcripts.

Search/download GIFs from Tenor via curl + jq.

HeartMuLa: Suno-like song generation from lyrics + tags.

Audio spectrograms/features (mel, chroma, MFCC) via CLI.

YouTube transcripts to summaries, threads, blogs.

Weekly newspaper upload workflow for Inside Publications / insideonline.com — archive old files, generate above-the-fold JPGs, and upload to Articulation Sites.

Read, search, create, and edit notes in the Obsidian vault.

Connect Hermes Agent to Obsidian via Local REST API plugin for vault search, read, write, and UI control.

Connect Obsidian to Hermes Agent via MCP for vault search, note read/write, and wiki features — including Windows cross-drive junction setup.

Airtable REST API via curl. Records CRUD, filters, upserts.

Content production for MediaCor clients — blog posts, newsletters, SEO, social media, show notes, and site work using client-specific canonical instructions.

Skill for daily recap

Skill for descript tone tags

Connect bank accounts, retirement accounts, and investment accounts to Hermes Agent — aggregator comparison, MCP setup, costs, and provider-specific notes.

Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.

Evaluate, recommend, and set up MCP servers for Peter's Hermes Agent — matching MCP tools to his actual workflows (WordPress, Obsidian, Google Workspace, etc.)

Skill for hermes timer

Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.

Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).

Notion API + ntn CLI: pages, databases, markdown, Workers.

Connect Hermes Agent to Obsidian for vault search, read, write, and file-open via REST API + MCP.

Extract text from PDFs/scans (pymupdf, marker-pdf).

Install and select animated petdex mascots for Hermes.

Write or speak in Peter B Dowell's authentic voice — for blog posts, emails, podcast show notes, social media, client communications, or any content where Peter asks you to write as him.

End-to-end podcast episode production — transcript intake through all deliverables. Use whenever user starts an episode or mentions production workflow.

Create, read, edit .pptx decks, slides, notes, templates.

Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.

Skill for windows content delivery

Skill for rrp financial tracking

Skill for rrp grant preparation

Skill for rrp ledger update

Search arXiv papers by keyword, author, category, or ID.

Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Query Polymarket: markets, prices, orderbooks, history.

Control Philips Hue lights, scenes, rooms via OpenHue CLI.

Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

Plan mode: write an actionable markdown plan to .hermes/plans/, no execution. Bite-sized tasks, exact paths, complete code.

Pre-commit review: security scan, quality gates, auto-fix.

Skill for rrp episode production

Parallel 3-agent cleanup of recent code changes.

Throwaway experiments to validate an idea before build.

4-phase root cause debugging: understand bugs before fixing.

TDD: enforce RED-GREEN-REFACTOR, tests before code.

Skill for website audit

Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers Hermes' built-in scheduler and external clock patterns for other agents.

Generate or edit images through Hermes Web UI using the selected/requested profile's fun-codex provider from config.yaml.

Beelink GTi14 BIOS update via USB — FAT32 formatting, file structure, and the Flash.nsh → startup.nsh fix for UEFI Shell auto-boot.

Extract project vision, decisions, and preferences from your head into clear documentation (README + ADRs) through a back-and-forth Q&A loop. Triggers on "brain-to-docs", "build out the docs", "extract the vision", "let's document this project".

Skill for computer use

Reference principles for concise, authentic copywriting — a lightweight template for creating new voice skills. Use as a starting point when building voice profiles for new clients, brands, or personas. Differentiator from existing voice skills: this is a minimalist reference framework, not a fully-developed voice profile like peter-voice or paul-voice.

How to delegate work to another AI agent (Claude Code, Hermes subagents) — picking the right agent, formatting prompts, polling progress. Read BEFORE delegating, spawning, or orchestrating agent-to-agent work.

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

How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Animate a local image into a short mp4 video through Hermes Web UI using xAI Grok Imagine.

Compact the current conversation into a single, detailed handoff message — everything that happened, why it happened, and what's left — output in a code block so it can be copy-pasted into a fresh agent session. Use when hitting context limits, switching focus, ending a work session, or partitioning a task across fresh contexts.

Create AI videos with HyperFrames in Hermes using HTML, CSS, and JavaScript compositions, then validate and render them to MP4. Use for short video intros, cinematic trailers, product promos, subtitle animations, HUD/tech visuals, web-to-video work, and motion graphics.

Skill for kff blog production

Create rich diagrams, data visualizations, technical architecture views, and editorial content cards directly in Markdown using the Markdown Viewer Agent Skills pack. Use for Mermaid-like diagram requests, PlantUML architecture diagrams, Vega charts, JSON Canvas maps, infographics, UML, cloud/network/security/data/IoT diagrams, and polished Markdown documentation visuals.

Skill for mediacor client work

Create editable AI video projects with Remotion and React, then preview and render them to MP4. Use for vertical short videos, product demos, story-driven animations, HUD/tech visuals, feed ads, tutorial videos, subtitles, voiceover, sound effects, and code-based video iteration.

Manually-invoked skill that forces the agent to compress its current answer — strip filler, simplify wording, and cut length while keeping the substance. Use when the user says "short", "shorter", "simpler", "too long", "tl;dr", or wants a more concise version of the previous response.

Teach the user a new skill or concept through structured lessons, reference documents, and interactive practice — all tracked in a teaching workspace. Triggers on "teach me", "I want to learn", "can you teach me", or when the user wants to build knowledge systematically over multiple sessions.

Skill for tms time logging

Skill for todoist integration

Poll RSS, JSON APIs, and GitHub with watermark dedup.

Skill for wtw episode production

Yuanbao (元宝) groups: @mention users, query info/members.