What makes Maybeai Sheet Cli Skill notable?

2.6K downloads. Trust evidence available

How should Maybeai Sheet Cli Skill be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

agentCLAWHUBUnverified

Maybeai Sheet Cli Skill

Inspect, import, edit, dashboard, template, and share MaybeAI spreadsheets

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.6k

Updated

Oct 9, 2026

Version

v0.21.8

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.6K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.6K downloadsadoption · observed Oct 9, 2026
Latest release: v0.21.8release · observed Sep 14, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17dw3azb29a9p8fh7vntn908983kwvf:maybeai-sheet-cli

Install using `clawhub skill install s17dw3azb29a9p8fh7vntn908983kwvf:maybeai-sheet-cli` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/no7dw/maybeai-sheet-cli before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-no7dw-maybeai-sheet-cli/snapshot"

Documentation

CLAWHUB

154,067 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
version: v0.21.8
name: maybeai-sheet-cli
description: Use when the user works with MaybeAI spreadsheets through the mbs CLI for workbook inspection, local or remote-URL file import, native cross-workbook import/export, worksheet/range/table writes, worksheet calculation and error scans, complete table/SQL reads with frame export, SQL-to-Base materialization, full worksheet data refreshes that keep headers, formulas, worksheet styling, chart/image CRUD, dashboard validate/refresh/export-template flows, or sharing. Route dashboard design and chart composition to `sheet-dashboard`.
metadata:
  cli_version: "0.28.4"
  openclaw:
    requires:
      env:
        - MAYBEAI_API_TOKEN
    primaryEnv: MAYBEAI_API_TOKEN
    emoji: "📊"
    homepage: https://github.com/OmniMCP-AI/maybeai-uni
required_environment_variables:
  - name: MAYBEAI_API_TOKEN
---

# MaybeAI Sheet CLI

Execute spreadsheet work through `mbs`, the console script from
`maybeai-sheet-cli`. Use first-class object commands.

## Target model gate

Before choosing a command, inspect the installed CLI rather than relying on a
documented command map:

```bash
mbs --help
mbs workbook --help
mbs worksheet --help
mbs <PUBLIC_GROUP> <PUBLIC_COMMAND> --help
```

Use `mbs workbook inspect` to inspect the workbook and `mbs worksheet list` to
discover worksheet identities. A worksheet name or `gid` is only a locator; it
does not prove the target supports cells, ranges, or stable table records.

| Target model | Required identity | Use | Do not use |
|---|---|---|---|
| Sheet grid | `worksheet_name` or `gid` | A1 ranges, cell formulas, worksheet calculation, row/column layout, cell notes | Base record/field selectors |
| Sheet table | worksheet locator plus persistent `table_id` when multiple tables exist | table read/insert/update and table/row/column views | treating a scan-order table number as a stable ID |
| Base table | `table_id` (or `table_name` for resolution), then `field_id`/`record_id` | typed records, Base field/column operations, Base Formula | A1/range writes, cell formulas, keep-headers refresh |
| Worksheet SQL Config | SQL-config worksheet identity plus raw SQL | `mbs sql config`, preview, and materialization | a legacy SQL cell wrapper or cell Formula |

## Canonical operation layer

Use the public canonical groups (`workbook`, `worksheet`, `table`, `range`, `row`,
`column`, and `formula`) for new work. They emit `contract_version: "1.0"` JSON with `ok`, `operation`,
`target`, and either `result` or `error`; `--output table|yaml` only changes
rendering. Mutations default to `--verify`; use `--dry-run` before a destructive
or unfamiliar request and pass `--expected-revision`/`--idempotency-key` when
the workflow needs concurrency protection.

Canonical target URIs are stable, redacted MaybeAI URLs:

```text
Sheet worksheet: https://www.maybe.ai/docs/spreadsheets/d/<DOC_ID>?gid=<GID>
Sheet table:     https://www.maybe.ai/docs/spreadsheets/d/<DOC_ID>?gid=<GID>&tid=<TABLE_ID>
Base tab

README.md

# maybeai-sheet-cli-skill

Agent skill for the `mbs` CLI from `maybeai-sheet-cli` **0.28.0**.

The installed CLI's runtime help is the command contract. Start a spreadsheet
session with:

```bash
mbs --help
mbs <group> --help
mbs <group> <command> --help
```

The parent `--help` output identifies commands that agents may generate in new
workflows. A directly callable command missing from that output is a hidden
compatibility command: do not recommend or generate it. If public commands
cannot preserve the requested behavior, explain the capability gap instead of
constructing a destructive approximation.

This skill provides model-routing guidance for Sheet, SheetTable, Base, and SQL
workflows; safe mutation and verification practices; and topic references for
imports, reads/writes, formulas, charts, sharing, recovery, and lineage. It
intentionally does **not** duplicate a complete CLI command tree. Consult the
installed command help for available groups, operations, parameters, and
feature changes.

Notable public-workflow boundaries:

- Use `workbook inspect` and `worksheet list` for target discovery.
- Use `formula set` for formula writes and `range note` for Sheet notes.
- Use `mbs image` for image operations.
- Use public `mbs table clear --target "$BASE_TABLE" --yes --verify` to remove
  all Base table records while preserving fields/schema. It is destructive, so
  preview with `--dry-run` when needed. For batch updates to existing Base
  field schema, use public `mbs column batch-update` after
  confirming its installed `--help` contract.

This repository owns agent-facing assets:

- `SKILL.md` — routing, playbooks, and core rules
- `references/` — runtime-help-first operational guidance and semantic caveats
- `agents/` — agent metadata
- `artifacts/` — demo datasets and reusable example specs

CLI implementation lives separately at:

- `../maybeai-sheet-cli`

Install the CLI:

```bash
pip install maybeai-sheet-cli
```

To get a MaybeAI API token, register at [maybe.ai](https://www.maybe.ai/), then
open [My Plan](https://www.maybe.ai/user/my-plan) and copy a token from the
**API Token** section.

Set `MAYBEAI_API_TOKEN`, then run `mbs --help`:

```bash
export MAYBEAI_API_TOKEN="your-api-token"
mbs --help
```

## Sync after CLI release

After `../maybeai-sheet-cli` is published to PyPI, sync this skill's version
frontmatter from the released CLI metadata:

```bash
python scripts/sync_cli_release.py --cli-repo ../maybeai-sheet-cli
```

The hook verifies that the CLI repository version fields agree and that the
same version exists on PyPI before updating `SKILL.md`. Use `--skip-pypi-check`
only for local draft docs before a package release.

_meta.json

{
  "ownerId": "kn77y6x3semab3mjjhgxyw81w9827yxy",
  "slug": "maybeai-sheet-cli",
  "version": "v0.21.8",
  "publishedAt": 1789359128081
}

references/base-mode-verification.md

# Base Mode Verification Runbook

## 1. Identify the Base target

```bash
mbs workbook inspect --target "$WORKBOOK"
mbs worksheet list --target "$WORKBOOK" --output json
mbs table inspect --target "$BASE_TABLE"
mbs table schema --target "$BASE_TABLE"
mbs table sample --target "$BASE_TABLE" --limit 10 --output table
```

Use `table sample` for a quick, representative, non-exhaustive check of Base
records and field values. Use bounded `table read` when verification needs a
specified result window or post-mutation readback.

Use a persistent Base table ID (`tid`) and stable field/record identities. A
worksheet name alone is insufficient for a Base record or field mutation.
For a Base target, canonical `table inspect` also returns matched worksheet
dimensions when available; use `table schema` and `table read` for fields and
records.

## 2. Insert or update records

```bash
mbs table insert --target "$BASE_TABLE" --frame-in rows.json --verify
mbs table update --target "$BASE_TABLE" --frame-in corrected_rows.json --key order_id --verify
mbs table read --target "$BASE_TABLE" --limit 100 --output table
```

`table update` is key-based. It does not imply an atomic full-table replacement,
delete missing records, or preserve all legacy replacement semantics. Stop and
report the capability gap when those semantics are required.

## 3. Fields and Formula fields

```bash
mbs column insert --target "$BASE_TABLE" --field gross_margin --field-type formula --verify
mbs column rename --target "$BASE_TABLE" --field gross_margin --new-name "Gross Margin" --verify
mbs column config --target "$BASE_TABLE" --field gross_margin --spec field-style.json --verify
mbs formula validate --target "$BASE_TABLE" --field gross_margin --expression 'revenue - cost'
mbs formula set --target "$BASE_TABLE" --field gross_margin --expression 'revenue - cost' --verify
mbs formula recalculate --target "$BASE_TABLE" --field gross_margin --verify
```

`column config` configures resource style; it is not a substitute for every
Base typed-field property. Use current parent/command help before changing a
field and report unsupported schema work instead of selecting a hidden command.

## 4. Verify SQL materialization

```bash
mbs sql materialize \
  --target "$WORKBOOK?table=S_orders" \
  --sql-file result.sql \
  --mode create \
  --schema schema.json \
  --verify
mbs table read --target "$WORKBOOK?table=S_orders" --limit 100 --output table
```

Verify the result schema, row count, representative values, and the target
identity returned by the mutation.

## 5. Reject Sheet-only misuse

Do not apply A1 range writes, merge/unmerge, Sheet cell notes, or Excel cell
formula assumptions to a Base table. Explain the mismatch and choose a public
Base record/field workflow instead.

references/charts-formatting.md

# Charts and Formatting Reference

## Contents

1. When to use this
2. Scope boundary
3. First-class mbs coverage
4. Styling and freezing
5. Minimal report-polish flow

## 1. When to use this

Read this document when the task involves charts, pictures, frozen panes, cell styles, autofilter, or conditional formatting.

## 2. Scope boundary

This skill only covers worksheet-level `mbs` execution and media/styling operations.

Switch to `sheet-dashboard` when:

- chart composition is the main task
- dashboard layout and storytelling are the main task
- you need chart layout systems, visual systems, or dashboard workflows
- you need an agent to generate or swap a dashboard spec before execution

If you only need to:

- inspect existing chart metadata
- call low-level chart/image CRUD APIs
- bind a chart to an existing sheet

then this skill is sufficient.

Chart and picture editing is first-class in `mbs` for common worksheet
workflows. Use `mbs raw post` only when you already have a task-specific
payload for an uncovered operation.

## 3. First-class mbs coverage

CLI:

```bash
mbs chart list --doc-id <DOC_ID> --worksheet-name <SHEET>
mbs chart get --doc-id <DOC_ID> --worksheet-name <SHEET> --cell J2
mbs chart create-config --doc-id <DOC_ID> --worksheet-name <SHEET> --cell J2 --spec chart.json
# Current CLI also accepts top-level `cell` in chart.json when --cell is omitted.
mbs chart update --doc-id <DOC_ID> --worksheet-name <SHEET> --cell J2 --chart-id rId1 --spec chart.json
mbs chart delete --doc-id <DOC_ID> --worksheet-name <SHEET> --chart-id rId1
```

Recommended authored `chart.json` shape:

```json
{
  "type": "json",
  "sql": "select Month, Revenue from Sheet1",
  "title": "Monthly Revenue",
  "hide_title": true,
  "legend": "bottom",
  "html": "{ library: 'echarts', handler: (data) => ({ xAxis: { type: 'category', data: data.map(r => r.Month) }, yAxis: { type: 'value' }, series: [{ type: 'line', data: data.map(r => Number(r.Revenue) || 0) }] }) }",
  "spec": {
    "style": {
      "title": "Monthly Revenue",
      "showContainerTitle": false
    }
  }
}
```

Alternate single-chart item shape accepted by recent CLI versions:

```json
{
  "cell": "B2",
  "chart": {
    "type": "json",
    "sql": "select Month, Revenue from Sheet1",
    "title": "Monthly Revenue",
    "html": "{ library: 'echarts', handler: (data) => ({ series: [{ type: 'line', data: data.map(r => Number(String(r.Revenue || '').replace(/,/g, '')) || 0) }] }) }"
  }
}
```

Important chart authoring rule:

- Prefer top-level `chart.type = "json"` for authored `mbs` specs.
- Put the actual ECharts or Highcharts renderer logic in `chart.html`.
- For `chart create-config`, the backend request is `{cell, chart}`. If you include `cell` in the spec, keep it top-level; do not nest a second `chart.chart`.
- Do not push `chart.type = "line"`, `"bar"`, or `"pie"` as the default authored pattern in `mbs` docs or skills.
- Treat those simple aliases as low-level backend-supported forms, not

Github ReposUpdated 0h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.