steelmorgan/img-grid
framework_eng/skills/tool-usage/browser-ui/img-grid/SKILL.md
Overlay a numbered grid on a screenshot. Use when analyzing a printed form screenshot (MXL) - measure column proportions and spans before generating a tabular document.
$ install --global
skillsauthnpx skillsauth add steelmorgan/1c-agent-based-dev-framework img-gridInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 26, 2026, 5:08 AM58.7s1 file scanned
SKILL.md
- name:
- img-grid
- description:
- Overlay a numbered grid on a screenshot. Use when analyzing a printed form screenshot (MXL) - measure column proportions and spans before generating a tabular document.
- argument-hint:
- <ImagePath> [--cell-size 50] [--cols N] [-o OUTPUT]
img-grid — Grid for layout analysis
Overlays a numbered grid on an image of a printed form. Allows you to precisely determine column boundaries, their proportions, and spans for generating an MXL document layout.
The numbers are drawn in separate margins outside the image (top and left margins), so they never cover the form contents.
Usage
python3 tools/img-grid/grid.py <ImagePath> [--cell-size 50] [--cols N] [--rows N] [-o OUTPUT]
Parameters
| Parameter | Required | Default | Description |
|---|:---:|---|---|
| ImagePath | yes | — | Path to the image (PNG, JPG) |
| --cell-size N | no | 50 | Cell size in pixels (determines cols/rows automatically) |
| -c, --cols N | no | auto | Number of vertical divisions (overrides --cell-size) |
| -r, --rows N | no | auto | Number of horizontal divisions (0 = square cells) |
| -o OUTPUT | no | <name>-grid.<ext> | Output path |
Dependencies
pip install Pillow
What the script does
- Adds margins (20 px top, 24 px left) for labels - contents are not covered.
- Draws vertical lines (red) and horizontal lines (blue) on the grid.
- Every 5th line is brighter, every 10th line is maximally bright (easy to count).
- Numbers the lines in the margins (top = column numbers, left = row numbers).
- Saves the result as an RGB PNG.
How to use the result
1. Determine column boundaries
Look at the image with the grid and write down the numbers of the vertical lines at the boundaries of each table column.
2. Find the base grid
If the form has several tables with different layouts (header + main table), combine all boundary points. Each segment between adjacent boundaries is one base MXL column.
Example for the M-11 form (--cols 48):
- Header: boundaries
0, 2, 4, 9, 14, 21, 28, 34, 40, 48 - Table: boundaries
0, 2, 4, 11, 16, 19, 23, 28, 32, 36, 42, 48 - Union:
0, 2, 4, 9, 11, 14, 16, 19, 21, 23, 28, 32, 34, 36, 40, 42, 48 - Result: 16 base columns with proportions
2, 2, 5, 2, 3, 2, 3, 2, 2, 5, 4, 2, 2, 4, 2, 6
3. Record the proportions
{
"columns": 16,
"page": "A4-landscape",
"columnWidths": {
"1": "2x", "2": "2x", "3": "5x", "4": "2x", "5": "3x",
"6": "2x", "7": "3x", "8": "2x", "9": "2x", "10": "5x",
"11": "4x", "12": "2x", "13": "2x", "14": "4x", "15": "2x", "16": "6x"
}
}
Typical workflow (reverse-engineering MXL)
# 1. Take a screenshot of the form
# 2. Overlay a grid with a step of ~50px
python3 tools/img-grid/grid.py form-screenshot.png --cell-size 50 -o form-grid.png
# 3. Study the form, experiment with the number of divisions
python3 tools/img-grid/grid.py form-screenshot.png --cols 48 -o form-grid-48.png
# 4. Pass it to the agent for analysis: name the column boundaries by number
Target agents
- developer-code — when working with an MXL form from a screenshot
- explorer / debugger — when reverse-engineering unknown printed forms
Related Skills
steelmorgan/vanessa-diagnostics
tools
VerifiedTrustedCommunity
Diagnostics for Vanessa Automation runs. Use when a feature scenario failed, artifacts were not created, or you need to classify a failure after launch.
65SKILL.mdUpdated May 26, 2026
steelmorgan/vanessa-authoring
tools
VerifiedTrustedCommunity
Creating and refining Vanessa Automation feature scenarios based on real project requirements. Use when you need to write or update a scenario test, not just run it.
65SKILL.mdUpdated May 26, 2026
steelmorgan/framework_eng/skills/tool-usage/v8-session-manager
tools
VerifiedTrustedCommunity
--- name: v8-session-manager description: Use when working with the 1С session manager (v8-session-manager) - launch, configuration, connecting 1С clients, reading session_list, calling proxied MCP-tools from 1С extensions, diagnostics. Triggers: mention of `v8-session-manager`, `session_list`, 1С extension MCP showcase, error “no active sessions” / “session_id required”, connecting a client to the manager via `mcpMode=ws`. provides_capabilities: # Built-in manager tools — always available whi
65SKILL.mdUpdated May 26, 2026
steelmorgan/v8-runner
tools
VerifiedTrustedCommunity
Use when Codex needs to manage v8-runner on local 1C projects through the CLI: configure v8project.yaml, initialize infobases or EDT workspaces, build sources from Designer or EDT, run syntax checks and tests, dump infobase changes, convert source formats, load or export artifacts, launch 1C clients, or choose safe 1C automation command sequences.
65SKILL.mdUpdated May 26, 2026