Ready to supercharge your AI agents?

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

Microsoft Excel · LeoYeAI | DecimalAI

Microsoft Excel

SkillScore61Maintained

microsoft-excel

Access the Microsoft Excel API (via Microsoft Graph) with managed OAuth authentication. Read and write workbooks, worksheets, ranges, tables, and charts stored in OneDrive or SharePoint.

Databy LeoYeAI

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

Automatic

Data Analyst pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/microsoft-excel/SKILL.md

decimalai skills pull microsoft-excel --out .claude/skills/

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

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

Raw file: /s/microsoft-excel/SKILL.md ↗ · machine-readable summary at /s/microsoft-excel.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

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 54d ago

Yes — +57% lift · at higher cost+219% tokens0% turns61% of whole cases pass with skill (14/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	150%	0%
case-02	✗→✓	▲ Improved	141%	0%
case-03	✗→✓	▲ Improved	146%	0%
case-04	✗→✓	▲ Improved	139%	0%
case-05	✗→✓	▲ Improved	109%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

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/microsoft-excel/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

Microsoft Excel

Access the Microsoft Excel API (via Microsoft Graph) with managed OAuth authentication. Read and write workbooks, worksheets, ranges, tables, and charts stored in OneDrive or SharePoint.

Quick Start

bash
# List worksheets in a workbook
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Base URL

https://gateway.maton.ai/microsoft-excel/{native-api-path}

Replace {native-api-path} with the actual Microsoft Graph API endpoint path. The gateway proxies requests to graph.microsoft.com and automatically injects your OAuth token.

Authentication

All requests require the Maton API key in the Authorization header:

Authorization: Bearer $MATON_API_KEY

Environment Variable: Set your API key as MATON_API_KEY:

bash
export MATON_API_KEY="YOUR_API_KEY"

Getting Your API Key

Sign in or create an account at maton.ai
Go to maton.ai/settings
Copy your API key

Connection Management

Manage your Microsoft Excel OAuth connections at https://ctrl.maton.ai.

List Connections

bash
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections?app=microsoft-excel&status=ACTIVE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Create Connection

bash
python <<'EOF'
import urllib.request, os, json
data = json.dumps({'app': 'microsoft-excel'}).encode()
req = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Get Connection

bash
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

json
{
  "connection": {
    "connection_id": "4751ac89-3970-47e1-872c-eacdf4291732",
    "status": "ACTIVE",
    "creation_time": "2026-02-07T00:43:18.565932Z",
    "last_updated_time": "2026-02-07T00:43:29.729782Z",
    "url": "https://connect.maton.ai/?session_token=...",
    "app": "microsoft-excel",
    "metadata": {}
  }
}

Open the returned url in a browser to complete OAuth authorization.

Delete Connection

bash
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Specifying Connection

If you have multiple Microsoft Excel connections, specify which one to use with the Maton-Connection header:

bash
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/microsoft-excel/v1.0/me/drive')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Maton-Connection', '4751ac89-3970-47e1-872c-eacdf4291732')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

If omitted, the gateway uses the default (oldest) active connection.

Workbook Access Patterns

You can access workbooks using either ID-based or path-based patterns:

By File ID:

/microsoft-excel/v1.0/me/drive/items/{file-id}/workbook/...

By File Path:

/microsoft-excel/v1.0/me/drive/root:/{path-to-file}:/workbook/...

API Reference

Drive Operations

Get Drive Info

bash
GET /microsoft-excel/v1.0/me/drive

List Root Files

bash
GET /microsoft-excel/v1.0/me/drive/root/children

Search for Excel Files

bash
GET /microsoft-excel/v1.0/me/drive/root/search(q='.xlsx')

Upload Excel File

bash
PUT /microsoft-excel/v1.0/me/drive/root:/{filename}.xlsx:/content
Content-Type: application/vnd.openxmlformats-officedocument.spreadsheetml.sheet

{binary xlsx content}

Session Management

Sessions improve performance for multiple operations. Recommended for batch operations.

Create Session

bash
POST /microsoft-excel/v1.0/me/drive/root:/{path}:/workbook/createSession
Content-Type: application/json

{
  "persistChanges": true
}

Response:

json
{
  "persistChanges": true,
  "id": "cluster=PUS7&session=..."
}

Use the session ID in subsequent requests:

workbook-session-id: {session-id}

Close Session

bash
POST /microsoft-excel/v1.0/me/drive/root:/{path}:/workbook/closeSession
workbook-session-id: {session-id}

Worksheet Operations

List Worksheets

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets

Response:

json
{
  "value": [
    {
      "id": "{00000000-0001-0000-0000-000000000000}",
      "name": "Sheet1",
      "position": 0,
      "visibility": "Visible"
    }
  ]
}

Get Worksheet

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')

Create Worksheet

bash
POST /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets
Content-Type: application/json

{
  "name": "NewSheet"
}

Update Worksheet

bash
PATCH /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')
Content-Type: application/json

{
  "name": "RenamedSheet",
  "position": 2
}

Delete Worksheet

bash
DELETE /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('{worksheet-id}')

Returns 204 No Content on success.

Range Operations

Get Range

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')/range(address='A1:B2')

Response:

json
{
  "address": "Sheet1!A1:B2",
  "values": [
    ["Hello", "World"],
    [1, 2]
  ],
  "formulas": [
    ["Hello", "World"],
    [1, 2]
  ],
  "text": [
    ["Hello", "World"],
    ["1", "2"]
  ],
  "numberFormat": [
    ["General", "General"],
    ["General", "General"]
  ],
  "rowCount": 2,
  "columnCount": 2
}

Get Used Range

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')/usedRange

Update Range

bash
PATCH /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')/range(address='A1:B2')
Content-Type: application/json

{
  "values": [
    ["Updated", "Values"],
    [100, 200]
  ]
}

Clear Range

bash
POST /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')/range(address='A1:B2')/clear
Content-Type: application/json

{
  "applyTo": "All"
}

Options: All, Formats, Contents

Table Operations

List Tables

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')/tables

Create Table from Range

bash
POST /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')/tables/add
Content-Type: application/json

{
  "address": "A1:C4",
  "hasHeaders": true
}

Response:

json
{
  "id": "{6D182180-5F5F-448B-9E9C-377A5251CFC5}",
  "name": "Table1",
  "showHeaders": true,
  "showTotals": false,
  "style": "TableStyleMedium2"
}

Get Table

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/tables('Table1')

Update Table

bash
PATCH /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/tables('Table1')
Content-Type: application/json

{
  "name": "PeopleTable",
  "showTotals": true
}

Get Table Rows

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/tables('Table1')/rows

Response:

json
{
  "value": [
    {
      "index": 0,
      "values": [["Alice", 30, "NYC"]]
    },
    {
      "index": 1,
      "values": [["Bob", 25, "LA"]]
    }
  ]
}

Add Table Row

bash
POST /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/tables('Table1')/rows
Content-Type: application/json

{
  "values": [["Carol", 35, "Chicago"]]
}

Delete Table Row

bash
DELETE /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/tables('Table1')/rows/itemAt(index=0)

Returns 204 No Content on success.

Get Table Columns

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/tables('Table1')/columns

Add Table Column

bash
POST /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/tables('Table1')/columns
Content-Type: application/json

{
  "values": [["Email"], ["alice@example.com"], ["bob@example.com"]]
}

Named Items

List Named Items

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/names

Charts

List Charts

bash
GET /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')/charts

Add Chart

bash
POST /microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets('Sheet1')/charts/add
Content-Type: application/json

{
  "type": "ColumnClustered",
  "sourceData": "A1:C4",
  "seriesBy": "Auto"
}

Code Examples

JavaScript

javascript
// Get range values
const response = await fetch(
  "https://gateway.maton.ai/microsoft-excel/v1.0/me/drive/root:/data.xlsx:/workbook/worksheets('Sheet1')/range(address='A1:B10')",
  {
    headers: {
      'Authorization': `Bearer ${process.env.MATON_API_KEY}`
    }
  }
);
const data = await response.json();
console.log(data.values);

Python

python
import os
import requests

# Update range values
response = requests.patch(
    "https://gateway.maton.ai/microsoft-excel/v1.0/me/drive/root:/data.xlsx:/workbook/worksheets('Sheet1')/range(address='A1:B2')",
    headers={'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}'},
    json={'values': [['Name', 'Age'], ['Alice', 30]]}
)
print(response.json())

Notes

Only .xlsx files are supported (not legacy .xls)
Worksheet names with special characters need URL encoding
Table and worksheet IDs containing { and } must be URL-encoded (%7B and %7D)
Sessions expire after ~5 minutes of inactivity (persistent) or ~7 minutes (non-persistent)
Use null in value arrays to skip updating specific cells
Blank cells should use "" (empty string)
Range addresses use A1 notation (e.g., A1:C10, Sheet1!A1:B5)
IMPORTANT: When using curl commands, use curl -g when URLs contain parentheses to disable glob parsing
IMPORTANT: When piping curl output to jq or other commands, environment variables like $MATON_API_KEY may not expand correctly in some shell environments

Error Handling

| Status | Meaning | |--------|---------| | 400 | Missing Microsoft Excel connection or invalid request | | 401 | Invalid or missing Maton API key | | 404 | Item not found or session expired | | 429 | Rate limited | | 4xx/5xx | Passthrough error from Microsoft Graph API |

Common Error Codes

| Code | Description | |------|-------------| | ItemNotFound | File or resource doesn't exist | | ItemAlreadyExists | Worksheet or table with that name already exists | | InvalidArgument | Invalid parameter or missing required field | | SessionNotFound | Session expired or doesn't exist |

Troubleshooting: API Key Issues

Check that the MATON_API_KEY environment variable is set:

bash
echo $MATON_API_KEY

Verify the API key is valid by listing connections:

bash
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Troubleshooting: Invalid App Name

Ensure your URL path starts with microsoft-excel. For example:

Correct: https://gateway.maton.ai/microsoft-excel/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets
Incorrect: https://gateway.maton.ai/v1.0/me/drive/root:/workbook.xlsx:/workbook/worksheets

Resources

Illustrative Want to see what microsoft-excel 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

7/31/2026, 12:48 UTC · 23 cases

Lift

+57%

61% vs 4%

Agent turns

1.0 vs 1.0

Tokens

+219%

5,338.52 vs 1,676.22

fail → pass · 13pass → pass · 1fail → fail · 9

Per-case results (23)

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 have a spreadsheet stored in my cloud drive at `/finance/2026_budget.xlsx`. I need to execute a set of fast updates by starting a workbook session, updating the values in range `B2:C5` on sheet 'Q1_Forecast', and closing the session once finished. Please provide an executable Python script using `requests` that handles this multi-step process and outputs the final response status.	fail→pass	8,842	7,579	-14%	1	1	0%	2,467	6,159	+150%	0	0	—
case-02 We store our customer list in an Excel file named `contacts.xlsx`. I want to convert the cell range `A1:C50` on 'Sheet1' into a structured table with headers, and then immediately append a new record with values `['Jane Doe', 'Engineering', 'jane@example.com']`. Please provide a Python script that executes these API calls and displays the created table row object.	fail→pass	12,257	12,752	+4%	1	1	0%	2,725	6,559	+141%	0	0	—
case-03 I have several Excel connections configured on my account and need to fetch all worksheets inside `/catalog/inventory.xlsx` using a specific active connection ID `4751ac89-3970-47e1-872c-eacdf4291732`. Write a Python script using standard libraries that executes this call and outputs the list of worksheet objects.	fail→pass	10,387	5,634	-46%	1	1	0%	2,315	5,699	+146%	0	0	—
case-04 Write a Python script using standard `urllib.request` to list all active connections for the Excel integration from the control API.	fail→pass	9,624	5,035	-48%	1	1	0%	2,118	5,067	+139%	0	0	—
case-05 Write a Python script using standard `urllib.request` to create a new OAuth connection entry for the Excel integration via the control plane.	fail→pass	11,885	4,349	-63%	1	1	0%	2,502	5,227	+109%	0	0	—
case-06 Write a Python script using standard `urllib.request` to remove a connection identified by ID `conn_998877` using the control endpoint.	fail→pass	7,714	3,857	-50%	1	1	0%	1,616	4,932	+205%	0	0	—
case-07 Write a cURL command to clear all contents and formatting from cells `A1:B2` on worksheet 'Sheet1' of `/reports/annual.xlsx` through the Maton Excel gateway.	fail→pass	7,075	4,069	-42%	1	1	0%	1,457	5,167	+255%	0	0	—
case-08 Write a Python snippet using `requests` to delete the first row (index 0) of table `SalesTable` in workbook `/data/sales.xlsx` via the Maton Excel gateway.	fail→pass	8,974	4,305	-52%	1	1	0%	1,903	5,241	+175%	0	0	—
case-09 Write a cURL request to rename worksheet 'Sheet1' to 'Summary2026' and reposition it to index 2 in `/docs/financials.xlsx` using the Maton gateway.	fail→fail	7,516	3,817	-49%	1	1	0%	1,422	5,127	+261%	0	0	—
case-10 Demonstrate how to structure a JSON payload for a PATCH request updating range `A1:B2` in `data.xlsx` on 'Sheet1' via the gateway, where cell A1 is updated to 'Total', cell B1 is left unchanged, cell A2 is updated to 500, and cell B2 is cleared to blank.	fail→fail	8,510	9,663	+14%	1	1	0%	1,647	5,350	+225%	0	0	—
case-11 Write a cURL request to add a clustered column chart based on range `A1:C10` on 'Sheet1' inside `/charts/dashboard.xlsx` via the Maton Excel gateway.	fail→pass	6,213	4,169	-33%	1	1	0%	1,271	5,213	+310%	0	0	—
case-12 Write a Python script using urllib.request to search for all `.xlsx` files in the root folder using the Maton Excel gateway.	fail→pass	9,018	5,450	-40%	1	1	0%	1,910	5,708	+199%	0	0	—
case-13 Write a cURL request to list all defined named items in `/models/forecast.xlsx` using the Maton Excel gateway.	fail→pass	6,017	3,206	-47%	1	1	0%	1,162	4,907	+322%	0	0	—
case-14 When targeting a specific table by its ID `{6D182180-5F5F-448B-9E9C-377A5251CFC5}` in a Maton Excel API gateway URL request, how must the opening and closing curly brackets be encoded?	fail→fail	3,633	2,663	-27%	1	1	0%	702	4,831	+588%	0	0	—
case-15 Provide the two URL path formats supported by the Maton Excel gateway for obtaining workbook worksheets — one using item ID `file_abc123` and the other using relative root path `/finance/budget.xlsx`.	pass→pass	6,641	3,003	-55%	1	1	0%	1,326	4,980	+276%	0	0	—
case-16 Write a cURL request to add a new column titled 'Status' with row values 'Active' and 'Pending' to `Table1` in `/data/users.xlsx` via the Maton gateway.	fail→pass	8,346	4,723	-43%	1	1	0%	1,732	5,288	+205%	0	0	—
case-17 When making cURL HTTP requests against Maton Excel range endpoints containing addresses such as `range(address='A1:B2')`, which cURL flag is required to prevent shell errors caused by parentheses?	fail→fail	14,275	2,589	-82%	1	1	0%	2,452	4,722	+93%	0	0	—
case-18 Write a Python script using `requests` to fetch all rows from `PeopleTable` inside `/hr/staff.xlsx` via the Maton Excel gateway.	fail→pass	8,701	6,974	-20%	1	1	0%	1,818	5,227	+188%	0	0	—
case-19 Construct the URL path to query only the used range of cells in worksheet 'DataSheet' inside `/reports/q1.xlsx` via the Maton Excel gateway.	fail→fail	6,717	3,695	-45%	1	1	0%	1,306	5,122	+292%	0	0	—
case-20 I have a local Excel file `report.xlsx` on my filesystem. I want to read sheet 'Data' into a pandas DataFrame, filter rows where 'Age' > 30, and save the result to a new local file `filtered.xlsx`. Write a Python script for this task.	fail→fail	4,613	4,075	-12%	1	1	0%	954	5,207	+446%	0	0	—
case-21 I have a local `.xlsx` workbook `calc.xlsx`. How do I write a Python script using openpyxl to open the file, set cell C1 formula to `=SUM(A1:B1)`, and save the file back to disk?	fail→fail	4,505	3,678	-18%	1	1	0%	886	4,977	+462%	0	0	—
case-22 I need to update cell range 'Sheet1!A1:B2' in a Google Sheets spreadsheet with ID `1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms` using the Google Sheets v4 API in Python. Write a script using `google-api-python-client` or HTTP requests to perform this update.	fail→fail	7,579	8,471	+12%	1	1	0%	1,661	6,242	+276%	0	0	—
case-23 I want to create a public sharing link for a generic PDF document stored at path `/documents/spec.pdf` in my OneDrive account using Microsoft Graph API directly. Write a Python snippet to make this call.	fail→fail	5,913	6,791	+15%	1	1	0%	1,201	5,834	+386%	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. 23 cases were attempted. The headline lift of +57 percentage points is the difference between those two pass rates over the 23 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 4.4%
Pass rate with the skill: 60.9%
Cases attempted: 23
Cases counted toward lift: 23
Cases that regressed: 0
Skill version measured: v1
Run completed: 7/31/2026, 12:48 UTC

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

Prompt

I have a spreadsheet stored in my cloud drive at `/finance/2026_budget.xlsx`. I need to execute a set of fast updates by starting a workbook session, updating the values in range `B2:C5` on sheet 'Q1_Forecast', and closing the session once finished. Please provide an executable Python script using `requests` that handles this multi-step process and outputs the final response status.

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 run61

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+276% 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 53 days ago

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

Ready to supercharge your AI agents?

Microsoft Excel

SkillSafety

Source

Microsoft Excel

Quick Start

Base URL

Authentication

Getting Your API Key

Connection Management

List Connections

Create Connection

Get Connection

Delete Connection

Specifying Connection

Workbook Access Patterns

API Reference

Drive Operations

Get Drive Info

List Root Files

Search for Excel Files

Upload Excel File

Session Management

Create Session

Close Session

Worksheet Operations

List Worksheets

Get Worksheet

Create Worksheet

Update Worksheet

Delete Worksheet

Range Operations

Get Range

Get Used Range

Update Range

Clear Range

Table Operations

List Tables

Create Table from Range

Get Table

Update Table

Get Table Rows

Add Table Row

Delete Table Row

Get Table Columns

Add Table Column

Named Items

List Named Items

Charts

List Charts

Add Chart

Code Examples

JavaScript

Python

Notes

Error Handling

Common Error Codes

Troubleshooting: API Key Issues

Troubleshooting: Invalid App Name

Resources

How this skill was measured

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

Related skills