Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Neonous Skill · leoyeai | DecimalAI

leoyeai/neonous

SkillScore95Maintained

Operate the Neonous AI agent platform — create agents, chat, manage tools, run workflows.

agent-toolingby leoyeai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/leoyeai-neonous/SKILL.md

decimalai skills pull leoyeai-neonous --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/leoyeai-neonous/SKILL.md https://app.decimal.ai/s/leoyeai-neonous/SKILL.md

Raw file: /s/leoyeai-neonous/SKILL.md ↗ · machine-readable summary at /s/leoyeai-neonous.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 51d ago

—+446% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	939%	0%
case-02	✗→✓	▲ Improved	130%	0%
case-04	✗→✓	▲ Improved	458%	0%
case-05	✗→✓	▲ Improved	253%	0%
case-06	✗→✓	▲ Improved	479%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/neonous/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

Neonous Skill

You can operate the Neonous AI agent platform on behalf of the user. Neonous lets users create, configure, and deploy AI agents through a web interface — with tools, MCP servers, workflows, templates, and more.

When to Use API vs Web Interface

Prefer suggesting the web interface for complex or visual tasks:

Creating/editing agents with detailed instructions → Web UI has a rich editor, AI-assisted instruction enhancement, and template gallery
Building workflows → Web UI has a visual canvas editor (drag & drop)
Browsing MCP catalog → Web UI has a searchable catalog with one-click install
Managing MCP server environment variables → Web UI handles secrets securely
Browsing community templates → Web UI has categories, previews, and one-click clone

Use the API for quick operations:

Listing agents, tools, workflows (quick status checks)
Chatting with an agent
Executing a workflow
Checking token balance
Simple agent creation with known parameters
Scripting and automation

The web interface is at $NEONOUS_URL — guide the user there for anything visual or complex.

Authentication

All API requests require the user's API key:

-H "x-api-key: $NEONOUS_API_KEY"

Base URL: $NEONOUS_URL (e.g., https://app.neonous-ai.com).

How to Get an API Key

Users generate API keys from the Settings page in Neonous. The key starts with nn_ and is only shown once. If not set up yet:

Log in to Neonous at $NEONOUS_URL
Go to Settings > API Keys
Click Create API Key, give it a name
Copy the key (won't be shown again) and set it as NEONOUS_API_KEY

Agents

List Agents

bash
curl -s "$NEONOUS_URL/custom/builder/agents" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.[]| {id, name, model, enabled}'

Get Agent Details

bash
curl -s "$NEONOUS_URL/custom/builder/agents/<AGENT_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Returns full config including instructions, predefined_tools, custom_tools, mcp_servers.

List Available Models

Always fetch models before creating an agent — do not hardcode model IDs:

bash
curl -s "$NEONOUS_URL/custom/builder/agents/available-models" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.models[]| {id, provider, display_name, is_default}'

Use the model marked is_default: true unless the user requests a specific one.

List Available Tools

bash
curl -s "$NEONOUS_URL/custom/builder/agents/available-tools" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.tools[]| {id, name, description}'

Returns pre-defined tools that can be assigned to agents via predefined_tools.

Create an Agent

For complex agents, recommend the web UI — it has AI-assisted generation and a template gallery. For simple agents via API:

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/agents" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My Agent",
    "description": "A helpful assistant",
    "instructions": "You are a helpful assistant that...",
    "model": "<MODEL_ID from available-models>",
    "enabled": true,
    "predefined_tools": [],
    "custom_tools": [],
    "mcp_servers": []
  }' | jq .

AI-Generate Agent Config

Let Neonous AI generate a full agent config from a name and description:

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/agents/generate" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Code Reviewer",
    "description": "Reviews pull requests and suggests improvements"
  }' | jq .

Returns a complete agent config (name, instructions, model, tools) ready to use with the create endpoint.

AI-Enhance Instructions

Improve existing agent instructions with AI:

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/enhance-instructions" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"instructions": "You help with code"}' | jq '.enhanced'

Update an Agent

bash
curl -s -X PUT "$NEONOUS_URL/custom/builder/agents/<AGENT_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Updated Name",
    "instructions": "Updated instructions..."
  }' | jq .

Only include fields you want to change.

Delete an Agent

bash
curl -s -X DELETE "$NEONOUS_URL/custom/builder/agents/<AGENT_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Chat

Chat with an Agent

Non-streaming generate endpoint — returns a complete JSON response:

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/chat/generate" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "x-agent-id: <AGENT_ID>" \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "Hello, what can you do?"}]}' | jq .

Response:

json
{
  "response": "Hi! I can help you with...",
  "usage": { "inputTokens": 42, "outputTokens": 18, "totalTokens": 60 }
}

For multi-turn conversations, include the full message history:

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/chat/generate" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "x-agent-id: <AGENT_ID>" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "What is 2+2?"},
      {"role": "assistant", "content": "4"},
      {"role": "user", "content": "Multiply that by 10"}
    ]
  }' | jq .

List Chat Sessions

bash
curl -s "$NEONOUS_URL/custom/builder/chat/sessions" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.sessions[]| {id, title, agentId, created_at}'

Filter by agent: append ?agentId=<AGENT_ID>.

Get Chat Session (with Messages)

bash
curl -s "$NEONOUS_URL/custom/builder/chat/sessions/<SESSION_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Create a Chat Session

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/chat/sessions" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"agentId": "<AGENT_ID>", "title": "My Session"}' | jq .

Delete a Chat Session

bash
curl -s -X DELETE "$NEONOUS_URL/custom/builder/chat/sessions/<SESSION_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

MCP Servers

For adding MCP servers, recommend the web UI — it has a searchable catalog with one-click install and secure environment variable management.

List MCP Servers

bash
curl -s "$NEONOUS_URL/custom/builder/mcp" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.[]| {id, name, type, enabled}'

Get MCP Server Details

bash
curl -s "$NEONOUS_URL/custom/builder/mcp/<MCP_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

List Tools from an MCP Server

bash
curl -s "$NEONOUS_URL/custom/builder/mcp/<MCP_ID>/tools" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.tools[]| {name, description}'

Add an MCP Server (stdio)

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/mcp" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "id": "my-mcp",
    "name": "My MCP Server",
    "description": "Provides extra tools",
    "config": {
      "connectionType": "stdio",
      "command": "npx",
      "args": ["-y", "@example/mcp-server"],
      "envVars": []
    }
  }' | jq .

Add an MCP Server (http)

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/mcp" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "id": "my-http-mcp",
    "name": "My HTTP MCP",
    "config": {
      "connectionType": "http",
      "url": "https://mcp.example.com/sse",
      "headers": {}
    }
  }' | jq .

Delete an MCP Server

bash
curl -s -X DELETE "$NEONOUS_URL/custom/builder/mcp/<MCP_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Add ?force=true to delete even if agents are using it.

Test MCP Server Connection

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/mcp/<MCP_ID>/test" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Workflows

For building workflows, always recommend the web UI — it has a visual drag-and-drop canvas editor that's far easier than raw JSON.

List Workflows

bash
curl -s "$NEONOUS_URL/custom/builder/workflows" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.[]| {id, name, enabled}'

Get Workflow Details

bash
curl -s "$NEONOUS_URL/custom/builder/workflows/<WORKFLOW_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Execute a Workflow

bash
curl -s -X POST "$NEONOUS_URL/custom/builder/workflows/<WORKFLOW_ID>/execute" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": {"key": "value"}}' | jq .

List Workflow Runs

bash
curl -s "$NEONOUS_URL/custom/builder/workflows/<WORKFLOW_ID>/runs?limit=10" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.runs[]| {id, status, created_at}'

Get Workflow Run Details

bash
curl -s "$NEONOUS_URL/custom/builder/workflows/runs/<RUN_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Get Workflow Run Logs

bash
curl -s "$NEONOUS_URL/custom/builder/workflows/runs/<RUN_ID>/logs" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.logs'

Templates & Community

List Agent Templates

bash
curl -s "$NEONOUS_URL/custom/builder/templates" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.templates[]| {id, name, category}'

Filter by category: append ?category=<CATEGORY>.

Get Template Details

bash
curl -s "$NEONOUS_URL/custom/builder/templates/<TEMPLATE_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Browse Community Templates

bash
curl -s "$NEONOUS_URL/custom/builder/community-templates" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.templates[]| {id, name, category, author}'

For browsing and cloning templates, recommend the web UI — it has previews, categories, and one-click clone.

Browse Community MCP Servers

bash
curl -s "$NEONOUS_URL/custom/builder/community-mcp" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.[]| {id, name, categories}'

Artifacts & Spaces

Agents generate artifacts during chat — code files, documents, charts, diagrams, and more. These are automatically saved and versioned. Users organize artifacts into spaces (project-based collections). For full artifact management, recommend the web UI — it has a file-manager interface with drag-and-drop, folders, and visual previews.

Browse Artifacts

bash
# List all artifacts
curl -s "$NEONOUS_URL/custom/builder/artifacts" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.[]| {id, title, type, created_at}'

# Get artifact details
curl -s "$NEONOUS_URL/custom/builder/artifacts/<ARTIFACT_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Search artifacts
curl -s "$NEONOUS_URL/custom/builder/artifacts/search?q=<QUERY>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Quick search
curl -s "$NEONOUS_URL/custom/builder/artifacts/quick-search?q=<QUERY>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Recent / Starred / Trash
curl -s "$NEONOUS_URL/custom/builder/artifacts/recent" -H "x-api-key: $NEONOUS_API_KEY" | jq .
curl -s "$NEONOUS_URL/custom/builder/artifacts/starred" -H "x-api-key: $NEONOUS_API_KEY" | jq .
curl -s "$NEONOUS_URL/custom/builder/artifacts/trash" -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Stats and tags
curl -s "$NEONOUS_URL/custom/builder/artifacts/stats" -H "x-api-key: $NEONOUS_API_KEY" | jq .
curl -s "$NEONOUS_URL/custom/builder/artifacts/tags" -H "x-api-key: $NEONOUS_API_KEY" | jq .

Artifact Versions

bash
# List versions
curl -s "$NEONOUS_URL/custom/builder/artifacts/<ARTIFACT_ID>/versions" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Restore a version
curl -s -X POST "$NEONOUS_URL/custom/builder/artifacts/<ARTIFACT_ID>/versions/<VERSION>/restore" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Folders

bash
# Create folder
curl -s -X POST "$NEONOUS_URL/custom/builder/artifacts/folders" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "My Folder"}' | jq .

# Get folder contents
curl -s "$NEONOUS_URL/custom/builder/artifacts/folders/<FOLDER_ID>/contents" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Move artifacts to folder
curl -s -X POST "$NEONOUS_URL/custom/builder/artifacts/move" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"artifactIds": ["<ID1>", "<ID2>"], "folderId": "<FOLDER_ID>"}' | jq .

Sharing

bash
# Share artifact (returns a public share link)
curl -s -X POST "$NEONOUS_URL/custom/builder/artifacts/<ARTIFACT_ID>/share" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Revoke share
curl -s -X DELETE "$NEONOUS_URL/custom/builder/artifacts/shares/<SHARE_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Other Artifact Operations

bash
# Delete (moves to trash)
curl -s -X DELETE "$NEONOUS_URL/custom/builder/artifacts/<ARTIFACT_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Restore from trash
curl -s -X POST "$NEONOUS_URL/custom/builder/artifacts/<ARTIFACT_ID>/restore" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Duplicate
curl -s -X POST "$NEONOUS_URL/custom/builder/artifacts/<ARTIFACT_ID>/duplicate" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Empty trash
curl -s -X DELETE "$NEONOUS_URL/custom/builder/artifacts/trash" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Spaces

Spaces group artifacts by project or topic. An artifact can belong to multiple spaces.

bash
# List spaces
curl -s "$NEONOUS_URL/custom/builder/spaces" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq '.spaces[]| {id, name, description}'

# Get space (with its artifacts)
curl -s "$NEONOUS_URL/custom/builder/spaces/<SPACE_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Create space
curl -s -X POST "$NEONOUS_URL/custom/builder/spaces" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "My Project", "description": "Artifacts for my project", "icon": "📁", "color": "#3B82F6"}' | jq .

# Update space
curl -s -X PUT "$NEONOUS_URL/custom/builder/spaces/<SPACE_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "Renamed Space"}' | jq .

# Delete space
curl -s -X DELETE "$NEONOUS_URL/custom/builder/spaces/<SPACE_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Add artifact to space
curl -s -X POST "$NEONOUS_URL/custom/builder/spaces/<SPACE_ID>/artifacts" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"artifactId": "<ARTIFACT_ID>"}' | jq .

# Remove artifact from space
curl -s -X DELETE "$NEONOUS_URL/custom/builder/spaces/<SPACE_ID>/artifacts/<ARTIFACT_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Bookmarks

Save important messages from chat sessions.

bash
# List bookmarks
curl -s "$NEONOUS_URL/custom/builder/bookmarks" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# List bookmark tags
curl -s "$NEONOUS_URL/custom/builder/bookmarks/tags" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Get bookmarks for a session
curl -s "$NEONOUS_URL/custom/builder/bookmarks/session/<SESSION_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Create bookmark
curl -s -X POST "$NEONOUS_URL/custom/builder/bookmarks" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"sessionId": "<SESSION_ID>", "messageId": "<MSG_ID>", "tags": ["important"]}' | jq .

# Delete bookmark
curl -s -X DELETE "$NEONOUS_URL/custom/builder/bookmarks/<BOOKMARK_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Skills

Agent skills extend what agents can do.

bash
# List skills
curl -s "$NEONOUS_URL/custom/builder/skills" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Get skill details
curl -s "$NEONOUS_URL/custom/builder/skills/<SKILL_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Reminders & Notifications

Agents can set reminders that trigger notifications or AI-generated follow-ups.

bash
# List reminders
curl -s "$NEONOUS_URL/custom/builder/reminders" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Create reminder (schedule is a cron expression)
curl -s -X POST "$NEONOUS_URL/custom/builder/reminders" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Check deployment",
    "message": "Verify the production deploy succeeded",
    "agentId": "<AGENT_ID>",
    "schedule": "0 9 * * *"
  }' | jq .

# Toggle reminder on/off
curl -s -X POST "$NEONOUS_URL/custom/builder/reminders/<REMINDER_ID>/toggle" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Delete reminder
curl -s -X DELETE "$NEONOUS_URL/custom/builder/reminders/<REMINDER_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# List notifications
curl -s "$NEONOUS_URL/custom/builder/notifications" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Unread count
curl -s "$NEONOUS_URL/custom/builder/notifications/unread-count" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Mark all notifications read
curl -s -X POST "$NEONOUS_URL/custom/builder/notifications/read-all" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Telegram

Connect agents to Telegram bots. For setup, recommend the web UI — it handles bot token configuration.

bash
# List Telegram connections
curl -s "$NEONOUS_URL/custom/builder/telegram/connections" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Connect agent to Telegram
curl -s -X POST "$NEONOUS_URL/custom/builder/telegram/connect" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"agentId": "<AGENT_ID>", "botToken": "<TELEGRAM_BOT_TOKEN>"}' | jq .

# Disconnect
curl -s -X DELETE "$NEONOUS_URL/custom/builder/telegram/connections/<CONNECTION_ID>" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Working Memory

Agents remember context across conversations via working memory.

bash
# Get working memory
curl -s "$NEONOUS_URL/custom/builder/users/working-memory" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Reset working memory
curl -s -X DELETE "$NEONOUS_URL/custom/builder/users/working-memory" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Wishlist

Users can submit and vote on feature wishes.

bash
# List wishes
curl -s "$NEONOUS_URL/custom/builder/wishes" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Create wish
curl -s -X POST "$NEONOUS_URL/custom/builder/wishes" \
  -H "x-api-key: $NEONOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"title": "Feature request", "description": "I would like..."}' | jq .

# Upvote/un-upvote
curl -s -X POST "$NEONOUS_URL/custom/builder/wishes/<WISH_ID>/upvote" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Account & Tokens

Get Token Balance

bash
curl -s "$NEONOUS_URL/tokens/balance" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Token Usage History

bash
curl -s "$NEONOUS_URL/tokens/usage" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Monthly Usage Summary

bash
curl -s "$NEONOUS_URL/tokens/summary" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

Billing, Plans & Subscriptions

Subscribing, upgrading plans, and purchasing tokens all go through Stripe checkout in the browser. Always direct users to the web UI at $NEONOUS_URL/settings (or the billing/pricing page) to subscribe or buy tokens — these cannot be completed via API alone.

You can check the user's current plan and billing status via API:

bash
# Get available plans (shows what they can subscribe to)
curl -s "$NEONOUS_URL/custom/builder/billing/plans" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Get current subscription (shows active plan)
curl -s "$NEONOUS_URL/custom/builder/billing/subscription" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Get billing status
curl -s "$NEONOUS_URL/custom/builder/billing/status" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Get token pricing (for purchasing extra tokens)
curl -s "$NEONOUS_URL/custom/builder/billing/token-pricing" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Get purchase history
curl -s "$NEONOUS_URL/custom/builder/billing/purchases" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

# Get invoices
curl -s "$NEONOUS_URL/custom/builder/billing/invoices" \
  -H "x-api-key: $NEONOUS_API_KEY" | jq .

If the user wants to subscribe, upgrade, or buy tokens, tell them to visit the Settings > Billing page in the web UI.

Health Check

bash
curl -s "$NEONOUS_URL/custom/builder/health" | jq .

No authentication required.

Guidelines

Always list agents first before chatting, so you know valid agent IDs.
Fetch models before creating — never hardcode model IDs; use available-models endpoint.
Recommend the web UI for complex tasks: building workflows (canvas editor), browsing templates/MCP catalog, editing agent instructions (AI-enhanced editor), and managing secrets/env vars.
Use the API for quick tasks: listing resources, chatting, executing workflows, checking balance.
For multi-turn chat, keep the full message history and pass it in each request.
Check token balance if you get a 402 error — the user is out of tokens.
Show the agent's response text directly to the user; omit usage details unless asked.
Format lists as clean tables or bullet points for readability.

Illustrative Want to see what leoyeai/neonous would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/8/2026, 19:06 UTC · 22 cases

Measured on 20 comparable cases — below the 22 needed to publish a lift, so this result is shown here but not on the registry card or leaderboard.

Lift

+82%

95% vs 14%

Agent turns

0%

1.0 vs 1.0

Tokens

+446%

8,070.75 vs 1,478.25

fail → pass · 18pass → pass · 3fail → fail · 1

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I want to set up a quick helper agent in Neonous called 'Markdown Reviewer' that proofreads documentation files. Please create this agent for me using the platform's default AI model and show me the resulting agent ID, name, and model configured.	fail→pass	5,591	11,796	+111%	1	1	0%	873	9,071	+939%	0	0	—
case-02 I need to design a complex multi-step automated workflow with visual connectors to orchestrate several MCP tools. Can you guide me on the best way to build this and display a summary list of my existing workflows?	fail→pass	17,757	6,917	-61%	1	1	0%	3,781	8,713	+130%	0	0	—
case-03 My interactions stopped working because I ran out of tokens. How can I upgrade my account plan or top up my balance, and can you print out my current token balance and billing status summary?	fail→fail	5,864	6,940	+18%	1	1	0%	941	7,805	+729%	0	0	—
case-04 I want to start a chat session with an agent in my workspace to summarize a document. Give me the curl command to send my initial message 'Please summarize this text'.	fail→pass	7,761	5,575	-28%	1	1	0%	1,515	8,457	+458%	0	0	—
case-05 I want to add a community MCP server with several environment secret keys into my setup. What is the recommended way to do this, and what curl command lists my current MCP servers?	fail→pass	12,142	3,117	-74%	1	1	0%	2,249	7,940	+253%	0	0	—
case-06 I asked an agent 'What is 10 + 15?' and it replied '25'. Now I want to ask 'Multiply that result by 4'. Provide the curl POST payload to continue this conversation with agent ID 'ag_123'.	fail→pass	7,126	3,034	-57%	1	1	0%	1,377	7,968	+479%	0	0	—
case-07 I want the system to auto-generate a full configuration for an agent named 'SQL Optimizer' that tunes slow database queries. Which API endpoint generates this complete configuration from name and description?	fail→pass	13,283	3,392	-74%	1	1	0%	2,190	7,983	+265%	0	0	—
case-08 I have existing agent instructions 'You are a python assistant'. I want to refine these instructions using AI enhancement before updating the agent. Show the curl command.	fail→pass	9,127	3,665	-60%	1	1	0%	1,543	8,110	+426%	0	0	—
case-18 Find community agent templates via API, but advise me on the preferred method to browse and clone them.	fail→pass	13,913	2,920	-79%	1	1	0%	2,213	7,838	+254%	0	0	—
case-09 I want to create a space called 'Project Titan' with icon '📁' and color '#3B82F6', then assign an existing artifact 'art_99' to it via API. Show the required API calls.	fail→pass	8,669	3,796	-56%	1	1	0%	1,706	8,114	+376%	0	0	—
case-10 I need to remove an MCP server with ID 'sqlite-db' via curl, even if agents are currently configured to use it. What URL flag handles forced removal?	fail→pass	5,870	1,932	-67%	1	1	0%	930	7,744	+733%	0	0	—
case-11 Show me how to run a workflow with ID 'wf_88' using input parameter 'file_path' set to '/data.csv', and then retrieve execution logs for run ID 'run_456'.	fail→pass	10,101	3,067	-70%	1	1	0%	2,022	7,976	+294%	0	0	—
case-12 I made a mistake in artifact 'art_77'. How can I view previous versions and restore version 2 using REST API calls?	fail→pass	11,622	2,450	-79%	1	1	0%	2,180	7,869	+261%	0	0	—
case-13 Set up a scheduled reminder titled 'Backup DB' with message 'Run database dump' for agent 'ag_123' to run every morning at 9 AM using cron syntax via API.	fail→pass	6,112	2,939	-52%	1	1	0%	389	7,967	+1948%	0	0	—
case-14 Connect agent 'ag_456' to a Telegram bot with token '123456:ABC-DEF' using the API, but note what UI alternative exists for setup.	fail→pass	6,714	4,130	-38%	1	1	0%	1,273	8,188	+543%	0	0	—
case-15 Save message 'msg_001' from chat session 'sess_100' with tag 'urgent' using the bookmark endpoint.	fail→pass	6,409	3,503	-45%	1	1	0%	1,271	8,059	+534%	0	0	—
case-16 Clear out stored user working memory across agent conversations using curl.	fail→pass	7,259	2,103	-71%	1	1	0%	1,291	7,738	+499%	0	0	—
case-17 Submit a feature wish titled 'Dark Mode' with description 'Add dark theme', then upvote wish ID 'wish_10'.	fail→pass	7,697	3,599	-53%	1	1	0%	673	7,983	+1086%	0	0	—
case-19 Create a folder named 'Reports' and move artifacts 'art_1' and 'art_2' into folder 'f_55'.	fail→pass	4,622	5,442	+18%	1	1	0%	712	7,869	+1005%	0	0	—
case-20 I am writing a custom Model Context Protocol (MCP) client in Python to communicate with a server over stdio transport. What exact JSON-RPC method string must the client send in its request payload to discover available tools from the server?	pass→pass	2,570	3,301	+28%	1	1	0%	433	7,978	+1742%	0	0	—
case-21 When establishing a stdio connection with a Model Context Protocol (MCP) server, what exact JSON-RPC method string must the client send in its initial message to perform the protocol handshake?	pass→pass	4,224	3,766	-11%	1	1	0%	706	8,029	+1037%	0	0	—
case-22 In the Model Context Protocol (MCP) specification for prompt template management, what exact JSON-RPC method string does a client send to retrieve registered prompts from the server?	pass→pass	3,809	3,103	-19%	1	1	0%	627	7,788	+1142%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 20 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +82 percentage points is the difference between those two pass rates over the 20 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 13.6%
Pass rate with the skill: 95.5%
Cases attempted: 22
Cases counted toward lift: 20
Cases that regressed: 1
Skill version measured: v1
Run completed: 8/8/2026, 19:06 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

I want to set up a quick helper agent in Neonous called 'Markdown Reviewer' that proofreads documentation files. Please create this agent for me using the platform's default AI model and show me the resulting agent ID, name, and model configured.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run95

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+1247% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 50 days ago

Other measured skills in the registry, with their headline benchmark lift.