hermes-skills

Diagnose and fix Hermes messaging gateway connectivity issues (Telegram/Discord down, stale locks, PM2 problems)

Backup Hermes agent to GitHub and restore on a new VPS. Covers what to include/exclude, GitHub token requirements, and restore steps. Includes automated scripts.

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

Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

Fetch YouTube video transcripts and transform them into structured content (chapters, summaries, threads, blog posts). Use when the user shares a YouTube URL or video link, asks to summarize a video, requests a transcript, or wants to extract and reformat content from any YouTube video.

Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. Uses API key auth (no OAuth needed). All operations via curl — no dependencies.

Give Hermes phone capabilities without core tool changes. Provision and persist a Twilio number, send and receive SMS/MMS, make direct calls, and place AI-driven outbound calls through Bland.ai or Vapi.

Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime.

Bitwarden CLI per credential management — usa BW_SESSION dal bashrc

Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).

Multi-agent coordination. Delegates tasks, monitors progress, handles failures.

Autonomous crypto/stock trading agent using Alpaca API. Monitors markets, executes paper trades, manages portfolio.

Autonomous deep research agent. Searches web, analyzes sources, synthesizes reports with source verification.

Khoj AI second brain. 34k+ stars. Semantic search, chat with docs, research agents, Obsidian integration.

Automated research using Khoj. Searches knowledge base + web, synthesizes reports, morning briefings.

Advanced video analyzer. Extracts transcripts, key frames, summaries. Works with YouTube, local videos.

Single-agent mission orchestrator. Decomposes mission into tasks, spawns workers, verifies exit criteria, chains tasks.

Setup cron job for automatic Hermes Agent code updates — git pull + dependency install + gateway restart, with Discord notification.

Cerca API gratuite in public-apis (340k stellette, 1436 API gratuite su GitHub). Usa SEMPRE prima di cercare API esterne o pagare per un servizio.

Real-time voice calling with Hermes Agent via Pipecat + Daily.co WebRTC on VPS

Proactive failure pattern detection — monitors cron jobs, subagent failures, and repeated errors; offers investigations before user notices

Evolutionary self-improvement loop for Hermes Agent using DSPy + GEPA. Evolve skills, prompts, and tool descriptions through reflective genetic search.

Act as Marco's proactive autonomous employee. Review business state, goals, and completed work each night at 2am. Execute ONE high-impact task that advances goals by one step.

Act as COO orchestrator - delegate ALL tasks to sandboxed subagents, never execute directly. Based on Hermes Orchestrator prompt from Notion.

Install and run Space Agent on Surface Pro 3 — release AppImage or dev clone, user creation, startup

High-performance supervisory AI system - orchestrator, decision engine, and R&D loop with 5 specialized agents. Maximizes output with minimal user input.

Design spec for a fully automated Content Factory inside Discord - multi-agent architecture for trending topics, scripts, visuals, and organized output.

Generate video, animation, and PDF output directly. Integrates content-factory (video pipeline), Remotion (animations), and pandoc/Python PDF generation. Use when users request: "make me a video", "create an animation", "generate a PDF report", "render this as video", "export to PDF", "create an animated explainer", or any task requiring direct output in video/animation/PDF format.

Real-time SSE-based communication bus between Hermes and Leo/OpenClaw agents on port 18900

Automatic context window maintenance for Hermes Agent — checkpoints state every 3-5 tool calls to prevent context loss during long sessions.

Real-time communication between Hermes and Leo/OpenClaw via SSE-enhanced interop-server on port 18900

Real-time SSE communication between Hermes and Leo/OpenClaw via interop-server.py on port 18900. Includes debug lessons and architecture.

Fix token conflicts when Hermes and OpenClaw both try to use the same Discord/Telegram bot tokens

Operate and troubleshoot Hermes WebUI on Surface Pro 3 — start, restart, LAN access, and common issues.

Single command system health overview — active fronts, cron jobs, gateway, disk/memory, recent failures

System maintenance and resilience layer - memory hygiene, backup, version control, security. Based on Hermes maintenance prompt from Notion.

Omi + Obsidian integration status - what's available on macOS vs Linux

OpenClaw v2026.4.21 setup and management on Surface Pro 3 — gateway, config, channels, and known issues.

Automatically select the best LLM model for a given task based on task characteristics using lightweight rules-based routing.

Install Ollama (local bare-metal) + Open WebUI (docker) on Ubuntu/Linux when official install script fails or sudo unavailable. Covers tmpfs /tmp space issues, tar structure quirks, Docker networking, and standalone docker-compose.