Daily Power Moves
The features that separate casual use from genuinely getting the most out of Hermes.
Hermes remembers who you are, your preferences, environment details, and lessons learned across sessions. Correct it once β never again.
Hermes saves reusable procedures as skills that load automatically in future sessions. It literally learns from experience.
The same agent runs on Telegram, Discord, Slack, WhatsApp, iMessage, Email and a dozen more platforms β full tool access everywhere.
Works with OpenRouter, Anthropic, OpenAI, Google, DeepSeek, xAI, local models and 20+ others. Swap models mid-workflow.
Schedule recurring tasks, run long missions in the background, chain jobs together β durable and retry-safe.
Spawn subagents or independent Hermes processes for parallel workstreams, each with isolated context.
01 Essential slash commands
Type these inside any session:
/status # session, model, token & context info
/model [name] # switch model (session-scoped)
/compress # compress context when it gets long
/skills # search & install skills interactively
/tools # enable/disable toolsets
/cron # manage scheduled tasks
/memory # review pending memory writes
/new # fresh session (clears context = saves tokens!)
02 Key CLI commands
hermes # interactive chat (default surface)
hermes setup # guided setup wizard
hermes doctor # health check dependencies & config
hermes tools list # enumerate toolsets per platform
hermes skills browse # explore the skills hub catalog
hermes mcp add NAME ... # connect an MCP server
hermes desktop # native desktop app
hermes dashboard # web admin panel + embedded chat
03 Background systems worth knowing
| System | What it does |
|---|---|
delegate_task | Spawn subagents with isolated context for parallel subtasks β single, batch, or background mode. |
cronjob | Durable scheduler: "30m", "every monday 9am", cron expressions, ISO timestamps. Jobs can load skills, override models, and deliver to any platform. |
| Curator | Maintains agent-created skills automatically β tracks usage, archives stale ones (never deletes), keeps backups. |
| Kanban | Multi-profile work-queue board for coordinating multiple agents on shared tasks. |
/goal to set a standing objective that persists across turns, and /steer to inject course corrections mid-task without waiting for the current work to finish.MCP: Model Context Protocol
Plug external capabilities straight into every conversation.
? What is MCP and why it matters
MCP is an open standard that lets AI agents connect to external tools and data sources through a universal protocol β like USB-C for AI capabilities. Instead of writing custom integrations for every service, you install a server once and its tools appear natively in the agent.
- Universal plug-in system β one protocol, hundreds of community servers: filesystems, GitHub, databases, browsers, Slack, mapsβ¦
- Auto-discovery β Hermes connects at startup, discovers each server's tools, and registers them as first-class tools alongside built-ins. No bridging, no glue code.
- Available everywhere β MCP tools are injected into every platform's toolset automatically: CLI, desktop, Telegram, Discord, all of them.
- Security built in β stdio servers get a filtered environment (no accidental credential leaks), and credentials in error messages are auto-redacted before reaching the LLM.
- Resilient connections β persistent sessions with automatic reconnection (exponential backoff, up to 5 retries).
1 Install the prerequisites
pip install mcp # MCP SDK (optional dep β without it MCP is disabled)
# Node.js needed for `npx` servers Β· uv needed for `uvx` (Python) servers
2 Find MCP servers
- Built-in curated catalog:
hermes mcp catalogthenhermes mcp install NAMEβ the easiest path. - Official registry: browse github.com/modelcontextprotocol/servers.
- Community hubs: search "MCP server" + your tool name on GitHub, npm (
npx-based) or PyPI (uvx-based). - Your own: any script speaking MCP over stdio, or any HTTP endpoint exposing
/mcp.
3 Connect a server
Via the CLI (recommended):
hermes mcp add time --command uvx mcp-server-time
hermes mcp add github --command npx -y @modelcontextprotocol/server-github
hermes mcp add myapi --url https://mcp.example.com/mcp
hermes mcp list # see what's configured
hermes mcp test github # verify connectivity
Or edit ~/.hermes/config.yaml directly under the mcp_servers key:
mcp_servers:
time:
command: "uvx"
args: ["mcp-server-time"]
github:
command: "npx"
args: ["-y", "@modelcontextprotocol/server-github"]
env:
GITHUB_PERSONAL_ACCESS_TOKEN: "ghp_..." # only passed to THIS server
remote_api:
url: "https://mcp.example.com/mcp"
headers:
Authorization: "Bearer sk-..."
timeout: 180
Restart Hermes β it connects, discovers tools, and registers them as mcp_{server}_{tool} (e.g. mcp_time_get_current_time). Then just ask naturally: "what time is it in Tokyo?"
Config options reference
command/argsβ executable + arguments (stdio transport)envβ extra env vars passed to the subprocess (secrets go here, explicitly)url/headersβ remote HTTP transport (use one transport or the other, not both)timeoutβ per-tool-call timeout (default 120s) Β·connect_timeoutβ startup timeout (default 60s)
Toggle which tools from a server are exposed with hermes mcp configure NAME. Reload live with /reload-mcp.
Troubleshooting quick hits
- "MCP SDK not available" β
pip install mcp - "No MCP servers configured" β check the key is exactly
mcp_serversin config.yaml - "Failed to connect" β command not on PATH? package needs
-y? bumpconnect_timeout? - Tools not appearing β look for the
mcp_{server}_{tool}prefix; check YAML indentation
env block. Disable sampling for untrusted servers with sampling: {enabled: false}.Skills Available
Skills are Hermes' procedural memory β reusable playbooks loaded on demand. Search or filter the library below.
Create & Add New Skills
Three ways to grow your skill library β install from the hub, learn from experience, or author by hand.
01 Install from the hub
hermes skills browse # interactive catalog
hermes skills search "pdf" # find by keyword
hermes skills install ID # by hub ID...
hermes skills install https://example.com/SKILL.md # ...or direct URL
hermes skills tap add REPO # add a GitHub repo as a skill source
02 Let Hermes learn it itself
The most natural way β just ask in conversation:
- "Remember how you did that as a skill." β after completing a tricky task, Hermes distills the workflow into a reusable SKILL.md.
/learn <source>β learn a procedure directly from directories, URLs, or the current chat.- Skills auto-load when relevant in future sessions β no manual invocation needed.
03 Author one by hand
Skills live in ~/.hermes/skills/<name>/SKILL.md (or a category subdirectory). Structure:
---
name: my-skill
description: "Use when X happens. Does Y." # β trigger lives here; first ~57 chars show in the index
version: 1.0.0
---
# My Skill
## When to Use
Clear trigger conditions.
## Steps
1. Numbered steps with exact commands.
## Pitfalls
Known gotchas and how to avoid them.
Then share it: hermes skills publish PATH publishes to the hub. Keep supporting files under references/, templates/, or scripts/ within the skill directory.
04 Managing skills over time
hermes skills list | browse | searchβ explore installed + hub skillshermes skills install IDβ from hub ID or a direct SKILL.md URLhermes skills tap add REPOβ add a GitHub repo as a skill sourcehermes curator statusβ background lifecycle manager tracks usage, marks stale skills, archives (never deletes) unused oneshermes bundlesβ bundle several skills behind one/namealias
Token Efficiency
Context window is money and attention. Ranked tactics by impact.
β Highest impact habits
$ Check your burn rate
/usage shows token usage and rate limits for the session. /insights 7 gives usage analytics over days. /status shows current context fill level β compress before you hit the ceiling.
/reset applies tool changes), not mid-chat.