Sylph Setup Agent logo

Sylph Setup Agent

Organization
getnao
sylph-setup-agent

Set up an AI agent by validating her scope, schedule, and delivery channel. Run as `/sylph-setup-agent <agent-name>` or `/sylph-setup-agent all`.

Overview

Publishergetnao
Repositorysylph
Skill namesylph-setup-agent
Stars
216
Forks
62
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by getnao on GitHub. Read the source before you install it.

Installation

Install the Sylph Setup Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/getnao/sylph/tree/main/.claude/skills/sylph-setup-agent
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/getnao/sylph.git /tmp/sylph
mkdir -p .claude/skills
cp -r /tmp/sylph/.claude/skills/sylph-setup-agent .claude/skills/sylph-setup-agent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sylph Setup Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sylph Setup Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sylph Setup Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Setup Agent

MCP connectors

ConnectorPurpose
SlackValidate the Chief of Staff delivery channel

Core principle: derive from ROLE.md, confirm with the CAO

Each agent already has a ROLE.md and PROMPT.md in agents/<name>/. Read them first. Derive scope, tasks, and cadence from those files. Only ask the CAO to confirm.

When to use

Run /sylph-setup-agent <name> after completing /sylph-setup (global setup) and before scheduling any agent. Run it once per agent you want to activate.

Usage

/sylph-setup-agent chief-of-staff
/sylph-setup-agent cmo
/sylph-setup-agent all

Available agents

AgentDirectoryDefault cadence
chief-of-staffagents/chief-of-staff/Daily 08:00
cmoagents/cmo/Daily (content), Weekly (planning)
product-manageragents/product-manager/Daily
customer-successagents/customer-success/Weekly (Monday)
head-of-dataagents/head-of-data/Daily
head-of-salesagents/head-of-sales/Daily
executive-assistantagents/executive-assistant/Daily
brand-designeragents/brand-designer/On-demand

How it works

Step 1: Read the agent definition

  1. Read agents/<name>/ROLE.md for identity, responsibilities, decision boundaries, and tone
  2. Read agents/<name>/PROMPT.md for the execution routine
  3. Read CONTEXT.md for company context

From these files, derive:

  • Scope: what this agent owns (list of responsibilities from ROLE.md)
  • Tasks: the concrete steps she runs (from PROMPT.md routine)
  • Default cadence: how often she runs (from ROLE.md "Working rhythm" or similar)
  • Outputs: what she produces and where it goes (from ROLE.md "Output rules")
  • Dependencies: which other agents or tools she needs

Step 2: Confirm scope and schedule

Present the derived scope to the CAO:

Here's what [agent name] will do:

Scope:

  • [responsibility 1 from ROLE.md]
  • [responsibility 2]
  • [responsibility 3]

She produces:

  • [output 1 and where it goes]
  • [output 2]

She escalates to you:

  • [escalation 1 from decision boundaries]
  • [escalation 2]

Proposed schedule: [cadence from ROLE.md, e.g. "Daily at 08:00"]

Anything to add, remove, or change?

Incorporate the CAO's corrections. If the CAO adjusts the schedule, note it.

Step 3: Chief of Staff only - validate Slack delivery

The Chief of Staff is the only agent that writes to Slack. She delivers her daily briefing as a Slack DM to the CAO.

Only for chief-of-staff:

  1. Connect to Slack - if not already connected, ask the CAO to connect the Slack MCP
  2. Ask the CAO:

Where should the Chief of Staff deliver her daily briefing? (Slack DM to you, or a specific channel?)

  1. Validate the channel or DM exists via Slack MCP
  2. Save the Slack user ID or channel ID for delivery

For all other agents, skip this step. Other agents write to the repo (_drafts/, _logs/, _plans/) and deliver in chat. They don't post to Slack.

Step 4: Write agent config

Create or update agents/<name>/CONFIG.md with the confirmed settings:

markdown
---
agent: [name]
status: active
---

# [Agent Name] - Configuration

## Schedule
- Cadence: [daily / weekly / on-demand]
- Time: [HH:MM local time, if scheduled]
- Special: [e.g. "Monday: extended run with weekly planning"]

## Scope
- [responsibility 1]
- [responsibility 2]
- [responsibility 3]

## Escalation rules
- [what she escalates to the CAO]

## Dependencies
- Agents: [other agents she delegates to or receives from]
- Tools: [MCP connectors she needs]

For the Chief of Staff only, add the delivery section:

markdown
## Delivery
- Channel: [Slack DM or channel name]
- Channel ID: [Slack channel/user ID]
- Fallback: chat message (if Slack fails)

Step 5: Schedule the Chief of Staff as a cloud agent

The Chief of Staff should run automatically every morning. After writing her CONFIG.md:

  1. Create a scheduled remote agent using the scheduling system (Claude Code's /schedule or equivalent)
  2. Configure the schedule:
    • Trigger: cron, daily at the CAO's preferred time (default: 08:00 local)
    • Prompt: "Run the chief-of-staff routine: load ROLE.md and PROMPT.md from agents/chief-of-staff/, execute the full daily routine, commit the briefing, and deliver via Slack DM."
    • Monday variant: the routine automatically branches for weekly planning (this is handled in PROMPT.md, no separate schedule needed)
  3. Verify the schedule is active and show the CAO a confirmation:

Chief of Staff is now scheduled to run every day at [HH:MM]. She'll deliver her briefing to [Slack channel/DM]. You can also invoke her on demand with /chief-of-staff.

For other agents with daily cadence, inform the CAO they can be scheduled the same way but don't auto-schedule them. Ask:

Want me to schedule any other agents to run automatically? (e.g., CMO daily, Head of Data daily)

Only schedule additional agents if the CAO explicitly asks.

Step 6: Test the agent

  1. Run a dry test of the agent's routine
  2. Verify she can access all required MCP connectors
  3. For the Chief of Staff: verify she can post to the configured Slack channel
  4. Show the CAO a sample output
  5. Capture any feedback in the agent's CONFIG.md

Batch mode: /sylph-setup-agent all

When the CAO runs /sylph-setup-agent all:

  1. List all agents in agents/ directory
  2. For each agent, run Steps 1-4 in sequence
  3. For the Chief of Staff, also run Step 5 (schedule)
  4. Present a summary table at the end:
| Agent | Schedule | Status |
|-------|----------|--------|
| chief-of-staff | Daily 08:00 (scheduled, Slack DM) | Active |
| cmo | Daily (on-demand) | Active |
| product-manager | Daily (on-demand) | Active |
| customer-success | Weekly Monday (on-demand) | Active |
| head-of-data | Daily (on-demand) | Active |
| head-of-sales | Daily (on-demand) | Active |
| executive-assistant | Daily (on-demand) | Active |
| brand-designer | On-demand | Active |
  1. Ask: "Chief of Staff is scheduled. Want me to schedule any other agents too?"

Adding a new agent

If the CAO asks to set up an agent that doesn't exist yet:

  1. Create the directory: agents/<name>/
  2. Ask the CAO to describe what this agent should do (2-3 sentences)
  3. Generate ROLE.md following the pattern of existing agents:
    • Identity section
    • Responsibilities (numbered)
    • Decision boundaries (you decide / you escalate)
    • Tone
    • Output rules
  4. Generate PROMPT.md with the execution routine
  5. Create the matching skill in .claude/skills/<name>/SKILL.md
  6. Add to the skill index in AGENTS.md
  7. Then proceed with the normal setup flow (Steps 2-6)

Frequently asked questions

What does the Sylph Setup Agent AI skill do?

Set up an AI agent by validating her scope, schedule, and delivery channel. Run as `/sylph-setup-agent <agent-name>` or `/sylph-setup-agent all`.

Why use Sylph Setup Agent on TypingMind?

Because you install it once and use it with any model. Sylph Setup Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sylph Setup Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/getnao/sylph/tree/main/.claude/skills/sylph-setup-agent. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Sylph Setup Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sylph Setup Agent?

As many as you like. As long as a model supports skills, you can use Sylph Setup Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sylph Setup Agent AI skill free?

It is published on GitHub by getnao. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇