Sentio Platform logo

Sentio Platform

Organization
sentioxyz
sentio-platform

Build, modify, or troubleshoot Sentio projects across processors, Sentio SQL in Data Studio, alerting, and dashboards. Use for tasks involving @sentio/sdk handlers in processor.ts, sentio.yaml config, metrics/event logs/entity store, running or sharing Sentio SQL queries, creating/updating alert rules and notification channels, or managing dashboards and panels.

Overview

Publishersentioxyz
Repositorysentio-ai-kit
Skill namesentio-platform
Stars
84
Forks
1
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Sentio Platform 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/sentioxyz/sentio-ai-kit/tree/main/skills/sentio-platform
  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/sentioxyz/sentio-ai-kit.git /tmp/sentio-ai-kit
mkdir -p .claude/skills
cp -r /tmp/sentio-ai-kit/skills/sentio-platform .claude/skills/sentio-platform
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sentio Platform 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 Sentio Platform 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 Sentio Platform 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.

sentio-platform

Use npx @sentio/cli@latest for SQL, data queries, alerts, endpoints, and project management.

Setup

  1. Check login status: npx @sentio/cli@latest login --status
  2. If not logged in, ask the user for api key and run: npx @sentio/cli@latest login --api-key <key>

SQL

  • Execute: sentio data sql --project <owner>/<slug> --query "SELECT * FROM transfer LIMIT 10"
  • Async: sentio data sql --project <owner>/<slug> --query "..." --async
  • Fetch async result: sentio data sql --project <owner>/<slug> --result <execution-id>
  • Paginate: sentio data sql --project <owner>/<slug> --cursor <cursor>
  • From file: sentio data sql --project <owner>/<slug> --file query.yaml
  • No cache: add --no-cache; control TTL with --cache-ttl-secs <s> and --cache-refresh-ttl-secs <s>
  • Specific processor version: --version <version>

Data queries

  • List events: sentio data events --project <owner>/<slug>
  • List metrics: sentio data metrics --project <owner>/<slug>
  • Query event: sentio data query --project <owner>/<slug> --event Transfer --aggr total --group-by timestamp
  • Query metric: sentio data query --project <owner>/<slug> --metric burn --aggr avg --filter meta.chain=1
  • Query price: sentio data query --project <owner>/<slug> --price ETH
  • With functions: --func 'topk(5)', --func 'delta(1m)'
  • Time range: --start <time> --end <time> --step <seconds>
  • Limit/offset: --limit <count> --offset <count>
  • Timezone: --timezone <tz>
  • File format docs: sentio data query --doc

Alerts

  • List: sentio alert list --project <owner>/<slug>
  • Get: sentio alert get <rule-id> --project <owner>/<slug>
  • Create metric: sentio alert create --project <owner>/<slug> --type METRIC --subject "Burn spike" --metric burn --aggr avg --op '>' --threshold 100
  • Create event: sentio alert create --project <owner>/<slug> --type METRIC --subject "Transfer anomaly" --event Transfer --filter amount>0 --aggr total --func 'delta(1m)' --op '>' --threshold 100
  • Create log: sentio alert create --project <owner>/<slug> --type LOG --subject "Large transfers" --query 'amount:>1000' --op '>' --threshold 0
  • Create SQL: sentio alert create --project <owner>/<slug> --type SQL --subject "Alert" --query 'select timestamp, amount from transfer where amount > 1000' --time-column timestamp --value-column amount --sql-aggr MAX --op '>' --threshold 1000
  • From file: sentio alert create --project <owner>/<slug> --file alert.yaml
  • Update: sentio alert update <rule-id> --project <owner>/<slug> --file updated.yaml
  • Delete: sentio alert delete <rule-id> --project <owner>/<slug>
  • Duration/interval: --for 5m --interval 1m; between condition: --op between --threshold 10 --threshold2 100
  • File format docs: sentio alert create --doc

Endpoints

  • Create: sentio endpoint create --project <owner>/<slug> --query "SELECT * FROM t WHERE amount > \${min}" --args '{"min":"int"}'
  • List: sentio endpoint list --project <owner>/<slug>
  • Get: sentio endpoint get --project <owner>/<slug> --id <id>
  • Test: sentio endpoint test --project <owner>/<slug> --id <id> --args '{"min":1000}'
  • Delete: sentio endpoint delete --project <owner>/<slug> --id <id>

Dashboards

  • List: sentio dashboard list --project <owner>/<slug>
  • Create: sentio dashboard create --project <owner>/<slug> --title "My Dashboard"
  • Create from file: sentio dashboard create --project <owner>/<slug> --file dashboard.json
  • Export: sentio dashboard export <dashboardId> --project <owner>/<slug>
  • Import: sentio dashboard import <dashboardId> --project <owner>/<slug> --file dashboard.json
  • Import from stdin: sentio dashboard import <dashboardId> --project <owner>/<slug> --stdin
  • Import override layout: sentio dashboard import <dashboardId> --project <owner>/<slug> --file dashboard.json --override-layouts
  • Add SQL panel: sentio dashboard add-panel <dashboardId> --project <owner>/<slug> --panel-name "Top Holders" --type TABLE --sql "SELECT * FROM CoinBalance ORDER BY balance DESC LIMIT 50"
  • Add event panel: sentio dashboard add-panel <dashboardId> --project <owner>/<slug> --panel-name "Transfer Count" --type LINE --event Transfer --aggr total
  • Add metric panel: sentio dashboard add-panel <dashboardId> --project <owner>/<slug> --panel-name "ETH Price" --type LINE --metric cbETH_price
  • Panel with filters/groups: --filter amount>1000 --group-by meta.address --func 'topk(5)'
  • Panel time range: --time-range-start -24h --time-range-end now --time-range-step 3600
  • Chart types: TABLE, LINE, BAR, PIE, QUERY_VALUE, AREA, BAR_GAUGE, SCATTER
  • Event aggr options: total, unique, AAU, DAU, WAU, MAU
  • Metric aggr options: avg, sum, min, max, count

Dashboard import JSON format

When constructing or editing dashboard.json for import, refer to references/openapi.swagger.json for the full schema. Key structure:

json
{
  "dashboardId": "<target-dashboard-id>",
  "dashboardJson": {
    "name": "My Dashboard",
    "panels": {
      "<panelId>": {
        "id": "<panelId>",
        "name": "Panel Name",
        "chart": {
          "type": "<ChartType>",
          "datasourceType": "<DataSourceType>",
          "sqlQuery": "SELECT ...",          // for SQL panels
          "queries": [...],                  // for metric/event panels
          "formulas": [...],
          "config": { ... }
        }
      }
    },
    "layouts": { ... }
  },
  "overrideLayouts": false
}
  • Chart.type values: TABLE, LINE, BAR, PIE, QUERY_VALUE, AREA, BAR_GAUGE, SCATTER
  • Chart.datasourceType: determines query shape — SQL panels use sqlQuery string; metric/event panels use queries array
  • panels is a map keyed by panel ID; each panel contains a chart object
  • layouts controls responsive grid placement; omit or set overrideLayouts: true to auto-arrange
  • See references/openapi.swagger.json definitions web_service.Dashboard, web_service.Panel, web_service.Chart, common.Query for complete field lists

Project management

  • List projects: sentio project list
  • Get project: sentio project get <owner>/<slug>
  • Create project: sentio project create --owner <owner> --name <name> --type sentio --visibility private
  • Delete project: sentio project delete <owner>/<slug>
  • Project types: sentio, subgraph, action

Processor management

  • Status: sentio processor status --project <owner>/<slug>
  • Source files: sentio processor source --project <owner>/<slug>
  • Activate pending version: sentio processor activate-pending --project <owner>/<slug>
  • Pause: sentio processor pause --project <owner>/<slug> --reason "maintenance" -y
  • Resume: sentio processor resume --project <owner>/<slug>
  • Stop: sentio processor stop --project <owner>/<slug>
  • Logs: sentio processor logs --project <owner>/<slug> --limit 100
  • Follow logs: sentio processor logs --project <owner>/<slug> -f
  • Filter logs: --log-type execution --level ERROR --query "timeout"

Price

  • Get price: sentio price get --coin ETH or --symbol ETH or --address 0x... --chain 1
  • Historical price: sentio price get --coin ETH --timestamp <unix-ts>
  • Batch prices: sentio price batch --file prices.yaml
  • List supported coins: sentio price coins
  • Check latest available prices: sentio price check-latest

Simulation

  • Run transaction simulation: sentio simulation run --project <owner>/<slug> --file sim.yaml
  • Run bundle simulation: sentio simulation run-bundle --project <owner>/<slug> --chain-id <id> --file bundle.yaml
  • List simulations: sentio simulation list --project <owner>/<slug>
  • Get simulation: sentio simulation get <simulation-id> --project <owner>/<slug>
  • Get bundles: sentio simulation bundle --project <owner>/<slug>
  • Fetch call traces: sentio simulation trace --project <owner>/<slug>

Notes

  • All commands accept --api-key <key> or use saved credentials from sentio login.
  • All commands accept --token <token> for bearer token auth.
  • Use --json or --yaml for machine-readable output.
  • Use --project <owner>/<slug> to target a project, or --owner + --name separately, or --project-id <id>.
  • For long SQL queries, use --async then fetch with --result <id>.
  • SQL alert queries must include a time column and a numeric value column; use $startTime/$endTime placeholders.
  • references/openapi.swagger.json contains the full Sentio REST API spec — read it when constructing dashboard JSON payloads, debugging CLI calls, or building custom integrations. Key definitions for dashboards: web_service.ImportDashboardRequest, web_service.Dashboard, web_service.Panel, web_service.Chart, common.Query.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sentio Platform AI skill do?

Build, modify, or troubleshoot Sentio projects across processors, Sentio SQL in Data Studio, alerting, and dashboards. Use for tasks involving @sentio/sdk handlers in processor.ts, sentio.yaml config, metrics/event logs/entity store, running or sharing Sentio SQL queries, creating/updating alert rules and notification channels, or managing dashboards and panels.

Why use Sentio Platform on TypingMind?

Because you install it once and use it with any model. Sentio Platform 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 Sentio Platform in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sentioxyz/sentio-ai-kit/tree/main/skills/sentio-platform. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sentio Platform?

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 Sentio Platform?

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

Is the Sentio Platform AI skill free?

It is published on GitHub by sentioxyz. 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 👇