Mineru
Nebutra/MinerU-Skill
An AI-Native skill for parsing PDF / Office / image files into Markdown with MinerU — a fast, zero-config document parser for AI agents.
Fix garbled text in PDF/SVG vector graphics caused by font encoding issues, making files editable in AI tools.
Install Vector Text Fixer
$ npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aipoch/medical-research-skills vector-text-fixer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/scientific-skills/Other/vector-text-fixer .claude/skills/vector-text-fixer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "vector-text-fixer" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Other/vector-text-fixer into .claude/skills/vector-text-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vector-text-fixer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Other/vector-text-fixerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aipoch/medical-research-skills vector-text-fixer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/scientific-skills/Other/vector-text-fixer .agents/skills/vector-text-fixer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "vector-text-fixer" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Other/vector-text-fixer into .agents/skills/vector-text-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vector-text-fixer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aipoch/medical-research-skills vector-text-fixer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/scientific-skills/Other/vector-text-fixer .cursor/skills/vector-text-fixer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "vector-text-fixer" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Other/vector-text-fixer into .cursor/skills/vector-text-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vector-text-fixer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/aipoch/medical-research-skills.git --path scientific-skills/Other/vector-text-fixer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aipoch/medical-research-skills vector-text-fixer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/scientific-skills/Other/vector-text-fixer .gemini/skills/vector-text-fixer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "vector-text-fixer" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Other/vector-text-fixer into .gemini/skills/vector-text-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vector-text-fixer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install aipoch/medical-research-skills vector-text-fixerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/scientific-skills/Other/vector-text-fixer .github/skills/vector-text-fixer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "vector-text-fixer" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Other/vector-text-fixer into .github/skills/vector-text-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vector-text-fixer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aipoch/medical-research-skills vector-text-fixer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/scientific-skills/Other/vector-text-fixer .opencode/skills/vector-text-fixer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "vector-text-fixer" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Other/vector-text-fixer into .opencode/skills/vector-text-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vector-text-fixer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
vector-text-fixer- GitHub stars
- 2k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 624 words
- Files
- 4 (incl. scripts)
- Skills in repo
- 567
- Repo updated
- First seen
- Licence
- MIT
At a glance
Fix garbled text in PDF/SVG vector graphics caused by font encoding issues, making files editable in AI tools.
- Works in 5 steps: Confirm input file path (PDF or SVG) or… → Validate that the request involves… → Run scripts/main.py --input --output or… → …
- Tasks that involve Data pipelines and ETL
- SKILL.md covers Quick Check, Audit-Ready Commands, When to Use and Workflow, plus 12 more sections
- Runs Python scripts from its folder; calls python
What it does
Vector Text Fixer is an agent skill from aipoch/medical-research-skills. Fix garbled text in PDF/SVG vector graphics caused by font encoding issues, making files editable in AI tools. Supports batch processing and JSON export for manual correction.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/main.py` and `vector-text-fixer_audit_result_v2.json`).
It sits in Documents & Office, covering Data pipelines and ETL and PDF. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.
When your agent uses it
- Tasks that involve Data pipelines and ETL
- Tasks that involve PDF
Example prompts
- “/vector-text-fixer”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Confirm input file path (PDF or SVG) or batch folder, and desired output path.
- Validate that the request involves PDF/SVG garbled text repair; stop early if not.
- Run scripts/main.py --input --output or --batch .
- Return a structured result separating repaired blocks, skipped blocks, and unresolved items.
- If execution fails or inputs are incomplete, switch to the Fallback Template below.
What it can do on your machine
Read from SKILL.md and the folder at commit 686e09d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Vector Text Fixer loads about 1.7k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 624 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 624 words, ~1,723 tokens.
Download SKILL.mdSave it as
.claude/skills/vector-text-fixer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- vector-text-fixer
- description
- Fix garbled text in PDF/SVG vector graphics caused by font encoding issues, making files editable in AI tools. Supports batch processing and JSON export for manual correction.
- license
- MIT
- author
- AIPOCH
Vector Text Fixer
Fixes garbled text in PDF/SVG vector graphics caused by font embedding problems, encoding errors, or missing font substitution. Outputs repaired files or editable JSON for AI tool import.
Quick Check
python -m py_compile scripts/main.pyAudit-Ready Commands
python -m py_compile scripts/main.py
python scripts/main.py --help
python scripts/main.py --input document.pdf --output fixed.pdf
python scripts/main.py --input diagram.svg --output fixed.svgWhen to Use
- Fix garbled/box characters in PDF files caused by font embedding issues
- Repair SVG text encoding errors before editing in Illustrator or Inkscape
- Batch-process a folder of PDF/SVG files with garbled text
- Export a text map JSON for manual correction in AI editors
Workflow
- Confirm input file path (PDF or SVG) or batch folder, and desired output path.
- Validate that the request involves PDF/SVG garbled text repair; stop early if not.
- Run
scripts/main.py --input <file> --output <file>or--batch <folder>. - Return a structured result separating repaired blocks, skipped blocks, and unresolved items.
- If execution fails or inputs are incomplete, switch to the Fallback Template below.
Fallback Template
If scripts/main.py fails or required fields are missing, respond with:
FALLBACK REPORT
───────────────────────────────────────
Objective : <repair goal>
Inputs Available : <file path or batch folder provided>
Missing Inputs : <list exactly what is missing>
Note: --input requires a valid PDF or SVG file path, not a text string.
For batch mode use --batch <folder_path> instead.
Partial Result : <any blocks repaired safely>
Blocked Steps : <what could not be completed and why>
Next Steps : <minimum info needed to complete>
───────────────────────────────────────Stress-Case Output Checklist
For complex multi-constraint requests, always include these sections explicitly:
- Assumptions: repair level default (standard), encoding auto-detected
- Constraints: encrypted PDFs require password unlock first; scanned PDFs need OCR first
- Risks: severely damaged files may not be fully repairable; rare fonts may not map correctly
- Unresolved Items: blocks with confidence < 0.3 flagged for manual review
Supported Scenarios
PDF Garbled Text:
- Box/question mark issues from font embedding problems
- Garbled text from encoding conversion errors
- Missing font substitution characters
- Multi-language mixed encoding issues
SVG Garbled Text:
- Text entity encoding errors
- Special character escaping issues
- Invalid font reference display abnormalities
- XML encoding declaration errors
CLI Usage
# Fix single PDF
python scripts/main.py --input document.pdf --output fixed.pdf
# Fix single SVG
python scripts/main.py --input diagram.svg --output fixed.svg
# Batch process folder
python scripts/main.py --batch ./input_folder --output ./output_folder
# Interactive repair
python scripts/main.py --input doc.pdf --interactive
# Export editable JSON
python scripts/main.py --input doc.pdf --export-json editable.json
# Specify repair level
python scripts/main.py --input doc.pdf --output fixed.pdf --repair-level aggressiveParameters
| Parameter | Required | Description | Default |
|---|---|---|---|
--input | Yes* | Input PDF or SVG file path | — |
--batch | Yes* | Batch input folder path | — |
--output | Yes | Output file or folder path | — |
--repair-level | No | minimal / standard / aggressive | standard |
--interactive | No | Enable interactive repair mode | False |
--export-json | No | Export editable JSON format | — |
--encoding | No | Source file encoding (default: auto-detect) | auto |
*At least one of --input or --batch is required.
Repair Levels
- Minimal: Only obvious errors (replacement characters, null bytes); maximum original integrity
- Standard: Common encoding issues + smart font replacement; balanced repair rate and accuracy
- Aggressive: Full text re-encoding + OCR-assisted recognition; for severely garbled documents
Output Format (JSON Export)
{
"file_type": "pdf",
"pages": [{
"page_num": 1,
"text_blocks": [{
"id": "tb_001",
"bbox": [100, 200, 300, 220],
"original_text": "?????",
"detected_encoding": "UTF-8",
"confidence": 0.3,
"suggested_fix": "Sample Text"
}]
}],
"repair_summary": {
"total_blocks": 15,
"fixed_blocks": 12,
"skipped_blocks": 3
}
}Show full SKILL.md (258 more words)Show less
Input Validation
This skill accepts: PDF (.pdf) or SVG (.svg) file paths, or a folder path for batch processing, where the files contain garbled or unreadable text caused by font/encoding issues.
If the request does not involve PDF/SVG garbled text repair — for example, asking to convert file formats, edit PDF content directly, perform OCR on scanned images, or process non-vector files — do not proceed. Instead respond:
"
vector-text-fixeris designed to fix garbled text in PDF/SVG vector graphics caused by font encoding issues. Your request appears to be outside this scope. Please provide a valid PDF or SVG file path, or use a more appropriate tool."
Error Handling
- If
--inputreceives a text string instead of a file path, report the error and request a valid file path. - If the file is encrypted, report that password unlock is required before processing.
- If the task goes outside documented scope, stop instead of guessing.
- If
scripts/main.pyfails, use the Fallback Template above. - Do not fabricate repaired text content or execution outcomes.
Output Requirements
Every final response must include:
- Objective — file(s) repaired and repair level used
- Inputs Received — file path, repair level, encoding settings
- Assumptions — defaults applied (repair level, encoding detection)
- Result — output file path, blocks fixed vs skipped
- Risks and Limits — confidence thresholds, manual review blocks
- Next Checks — review low-confidence blocks manually before use
Limitations
- Encrypted PDFs require password unlock before processing
- Severely damaged vector files may not be fully repairable
- Some rare fonts may not map correctly
- Scanned PDFs require OCR recognition first
Dependencies
pdfplumber >= 0.10.0
PyMuPDF >= 1.23.0
cairosvg >= 2.7.0
beautifulsoup4 >= 4.12.0
fonttools >= 4.40.0
chardet >= 5.0.0
Pillow >= 10.0.0© aipoch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (scripts) in scientific-skills/Other/vector-text-fixer of aipoch/medical-research-skills.
- SKILL.md
- requirements.txt
- scripts/main.py
- vector-text-fixer_audit_result_v2.json
Open the folder on GitHubat commit 686e09d
Compare with similar skills
Vector Text Fixer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Vector Text Fixer this skillaipoch/medical-research-skills | 2k | — | ~1.7k | Automated safety check: Pass | MIT | |
| MineruNebutra/MinerU-Skill | 122 | — | ~504 | Automated safety check: Pass | MIT | |
| Multi Source Data Integration ExtractionDrchronx/ai-agent-research-starter-kit | 134 | — | ~671 | Automated safety check: Pass | Custom licence | |
| Documentsmagnus919/agent-skills | 111 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Find Skillsfastclaw-ai/fastclaw | 1.4k | — | ~2.3k | Automated safety check: Warn | Custom licence | |
| Latchshot Page Capturegithub/awesome-copilot | 40k | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Multi Source Data Integration Extraction
Drchronx/ai-agent-research-starter-kit
Automatically merge scattered Excel and CSV files, normalize column names, and extract structured tables from PDF, HTML, TXT, or Markdown documents.
Documents
magnus919/agent-skills
Generate, inspect, validate, and fix PDF, Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) documents: turn structured content into render-ready artifacts, verify structural and output quality…
Find Skills
fastclaw-ai/fastclaw
Run this BEFORE any package install (pip / npm / apt / brew / cargo / gem / go install) you would otherwise execute via the exec tool — including when the user asks for a deliverable that needs…
- Official
Latchshot Page Capture
github/awesome-copilot
A skill your agent uses when a user needs a screenshot, website thumbnail, full-page capture, or PDF of a public HTTP(S) webpage saved as a local artifact through Latchshot, including report, QA…
Education Cloud Course Catalog Migrate
forcedotcom/sf-skills
A skill your agent uses to migrate course catalog data from external sources (CSV, PDF, website) and bulk-create Learning and LearningCourse records in Education Cloud.
More from aipoch/medical-research-skills
All 567 skills in this repoAcademic Poster Generator
aipoch/medical-research-skills
Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster…
Diagnostic Study Quality Assessment Quadas
aipoch/medical-research-skills
Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool.
Exploratory Data Analysis
aipoch/medical-research-skills
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.
Iso Certification
aipoch/medical-research-skills
A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS.
Journal Skills
aipoch/medical-research-skills
Recommends target journals for manuscript submission by analyzing the paper topic/abstract and the journal distribution of similar PubMed literature; use when users ask for journal…
Latex Posters
aipoch/medical-research-skills
Creates academic-poster writing packages for LaTeX using beamerposter, tikzposter, or baposter.
Related
Categories
Questions about Vector Text Fixer
What does Vector Text Fixer do?
Fix garbled text in PDF/SVG vector graphics caused by font encoding issues, making files editable in AI tools. Vector Text Fixer is an agent skill from aipoch/medical-research-skills. Fix garbled text in PDF/SVG vector graphics caused by font encoding issues, making files editable in AI tools.
When should I use Vector Text Fixer?
Vector Text Fixer fits situations like: tasks that involve Data pipelines and ETL; tasks that involve PDF.
How do I install Vector Text Fixer in Claude Code?
Run `npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a claude-code`. Or copy the skill folder (scientific-skills/Other/vector-text-fixer in aipoch/medical-research-skills) into .claude/skills/vector-text-fixer in your project. Claude Code loads it when a task matches its description.
How do I install Vector Text Fixer in Codex?
Run `npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a codex`. Or copy the skill folder (scientific-skills/Other/vector-text-fixer in aipoch/medical-research-skills) into .agents/skills/vector-text-fixer in your project. Codex loads it when a task matches its description.
Can I use Vector Text Fixer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aipoch/medical-research-skills --skill vector-text-fixer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vector-text-fixer, .gemini/skills/vector-text-fixer, .github/skills/vector-text-fixer and .opencode/skills/vector-text-fixer in your project.
What does Vector Text Fixer need to run?
Going by SKILL.md and its folder, Vector Text Fixer needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Vector Text Fixer access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Vector Text Fixer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Vector Text Fixer use?
Vector Text Fixer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Vector Text Fixer use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Vector Text Fixer?
Skills that share tags, products or a category with Vector Text Fixer: Mineru (Nebutra/MinerU-Skill, 122 stars), Multi Source Data Integration Extraction (Drchronx/ai-agent-research-starter-kit, 134 stars), Documents (magnus919/agent-skills, 111 stars) and Find Skills (fastclaw-ai/fastclaw, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Vector Text Fixer?
aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,973 GitHub stars. The repository holds 567 skills in this directory. The repository was last updated on September 17, 2026.
Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.