Automated summary
Generates complete PDF test fixtures combining ReportLab tables and AI-generated images to test extractors.
Strengths
- Combines ReportLab tables with AI-generated images for realistic test fixtures
- includes presets targeting known extractor bugs
- modular design via orchestration of specialized sibling skills
- supports both quick-start presets and custom JSON specs.
Limitations
- Requires sibling skills (fixture-table, fixture-image) to be available
- primarily designed for extractor bug reproduction, not general-purpose PDF creation
- legacy JSON spec format may be phased out.
When you need to create PDF test fixtures that combine tables and images to exercise or debug PDF extractors (like Marker, Camelot, or VLM-based tools).
When you need simple PDF generation without specific extractor testing requirements, or when you cannot install the required Python dependencies.
Security analysis
SafeThe skill only orchestrates local PDF generation using ReportLab and pre-cached images. No network calls, exfiltration, or destructive commands are present. The scripts are executed with uv run on known local files, and there is no indication of downloading or executing untrusted payloads.
No concerns found
How this analysis is madeExamples
Create a PDF test fixture that reproduces known extractor bugs with empty sections and malformed titles using the extractor-bugs preset.Generate a simple PDF with a table and some text to test basic extraction.Create a PDF fixture with a standard style containing a requirements section with a table and an architecture diagram image.name: pdf-fixture description: > Generate complete PDF test fixtures combining proper ReportLab tables and AI-generated images. Orchestrates fixture-table and fixture-image skills. Creates PDFs designed to test/expose extractor bugs. allowed-tools: Bash, Read, Write triggers:
- create test PDF
- generate PDF fixture
- make sample PDF
- PDF for testing
- create PDF with tables
- extractor test fixture
- bug reproduction pdf metadata: short-description: Complete PDF fixtures for extractor testing (tables + images)
PDF Fixture Generator
Generate complete PDF test fixtures that combine:
- Proper ReportLab tables via
fixture-table(detectable by Marker/Camelot) - AI-generated images via
fixture-image(diagrams, decorative elements) - Text content with various formatting challenges
Why This Exists
Creating test PDFs that properly exercise extractors requires:
- Tables built with ReportLab (not raw drawing commands)
- Images that test VLM classification (decorative vs data)
- Edge cases: empty sections, malformed titles, nested structures
This skill orchestrates sibling skills for modular, reusable fixtures.
Quick Start (New)
cd .pi/skills/pdf-fixture
# Generate the extractor bug reproduction fixture
uv run generate.py extractor-bugs --output test.pdf
# Generate a simple fixture
uv run generate.py simple --output simple_test.pdf
# List available presets
uv run generate.py list-presets
# Verify table detection
uv run generate.py verify test.pdf
Presets
| Preset | Description | Tests |
|--------|-------------|-------|
| extractor-bugs | Reproduces known extractor issues | Empty sections, false tables, malformed titles |
| simple | Basic PDF with table and text | Basic extraction |
Sibling Skills Used
| Skill | Purpose |
|-------|---------|
| fixture-table | Creates ReportLab tables (Marker-detectable) |
| fixture-image | AI-generated images with caching |
Cached images from fixture-image/cached_images/:
decorative.png- Cover illustrationflowchart.png- Process diagramnetwork_arch.png- Architecture diagram
Legacy Usage (Still Supported)
# Via wrapper (uses extractor project)
./run.sh --example --name test_fixture
./run.sh --spec content_spec.json --name my_fixture
JSON Spec Format (Legacy)
{
"style": "standard",
"sections": [
{
"title": "1. Requirements",
"level": 1,
"content": [
{"type": "text", "text": "This document describes requirements."},
{"type": "table", "columns": ["ID", "Name"], "rows": [["1", "Alice"]]},
{"type": "figure", "description": "Architecture diagram"}
]
}
]
}
Output
extractor_bugs_fixture.pdf- Cached incached_fixtures/- Custom output via
--outputflag
Dependencies
dependencies = [
"pymupdf>=1.23.0",
"reportlab>=4.0.0",
"typer>=0.9.0",
"pillow>=10.0.0",
]
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/pdf-fixture-generator-mma3jrl0/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/pdf-fixture-generator-mma3jrl0' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/pdf-fixture-generator-mma3jrl0/download' --output '.skill-downloads/pdf-fixture-generator-mma3jrl0/SKILL.md.part' && mv '.skill-downloads/pdf-fixture-generator-mma3jrl0/SKILL.md.part' '.skill-downloads/pdf-fixture-generator-mma3jrl0/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Bash, Read, Write
Original excerpt: Dependencies
dependencies = [
"pymupdf>=1.23.0",
"reportlab>=4.0.0",
"typer>=0.9.0",
"pillow>=10.0.0",
]
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/pdf-fixture-generator-mma3jrl0/SKILL.md' && test -s '.skill-downloads/pdf-fixture-generator-mma3jrl0/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/pdf-fixture' && cp -R '.skill-downloads/pdf-fixture-generator-mma3jrl0' '.claude/skills/pdf-fixture'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/pdf-fixture-generator-mma3jrl0'openskills read 'pdf-fixture-generator-mma3jrl0'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/pdf-fixture-generator-mma3jrl0/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.