with one click
pdf-processor
Perform basic local PDF operations (merge, split, extract pages/text/tables, create) when users request offline PDF processing without external services.
Menu
Perform basic local PDF operations (merge, split, extract pages/text/tables, create) when users request offline PDF processing without external services.
| name | pdf-processor |
| description | Perform basic local PDF operations (merge, split, extract pages/text/tables, create) when users request offline PDF processing without external services. |
| license | MIT |
| author | AIPOCH |
1-3,5) into a new PDF..txt file without using any cloud API.Install Python dependencies:
pip install -r scripts/requirements.txt
More examples may be available in
references/examples.md.
python scripts/pdf_tool.py \
--operation merge \
--inputs "a.pdf" "b.pdf" \
--output "out.pdf"
python scripts/pdf_tool.py \
--operation split \
--inputs "input.pdf" \
--output "out_dir"
python scripts/pdf_tool.py \
--operation extract-pages \
--inputs "input.pdf" \
--pages "1-3,5" \
--output "extracted.pdf"
.txt filepython scripts/pdf_tool.py \
--operation extract-text \
--inputs "input.pdf" \
--output "output.txt"
python scripts/pdf_tool.py \
--operation extract-tables \
--inputs "input.pdf" \
--output "tables_out_dir"
python scripts/pdf_tool.py \
--operation create \
--inputs "input.txt" \
--output "created.pdf"
scripts/pdf_tool.py) that reads from provided input paths and writes only to the specified output path.merge: Concatenates PDFs in the order provided via --inputs.split: Writes one PDF per page (output is typically a directory path).extract-pages: Uses --pages to select pages and writes a new PDF.extract-text: Extracts selectable text; pages with no extractable text may yield empty lines.extract-tables: Attempts table detection/extraction; pages without tables may produce empty CSV outputs.create: Produces a simple PDF from a text input.--pages "1-3,5" where page numbering starts at 1.--pages are ignored.pdf_processor_result.md unless the skill documentation defines a better convention.Run this minimal verification path before full execution when possible:
python scripts/pdf_tool.py --help
Expected output format:
Result file: pdf_processor_result.md
Validation summary: PASS/FAIL with brief notes
Assumptions: explicit list if any
A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills. Use this skill whenever a user wants to evaluate, audit, review, score, or quality-check an agent skill before publishing, updating, or deploying. Covers two hard veto gates (structural redlines + research integrity redlines), static quality scoring across 25 criteria (ISO 25010 + OpenSSF + Agent), dynamic test input generation, multi-mode execution testing, multi-layer output evaluation with five specialized category rubrics (Evidence Insight / Protocol Design / Data Analysis / Academic Writing / Other), a Research Veto that applies to all four research categories, human eval viewer generation, actionable P0/P1/P2 optimization recommendations, and automatic skill improvement that outputs a polished, production-ready SKILL.md. Also use whenever a user says "audit my skill", "evaluate my skill", "improve my skill", or wants a corrected version after evaluation.
Run GSEA on a ranked gene list and produce the enrichment table, running-score table, and enrichment plots.
Identifies real, evidence-audited, topic-specific research gaps in medical research by first retrieving and verifying literature from trusted sources, then mapping the current evidence landscape, rejecting pseudo-gaps, and converting only medium/high-confidence gaps into study-ready research opportunities. Always require real literature retrieval before formal gap claims. Never fabricate references, metadata, or findings.
Converts an audited medical research gap into a complete, structured, gap-traceable study design. Always use this skill whenever a user already has one or more candidate research gaps and wants to transform them into an executable biomedical research plan rather than re-run broad topic ideation. Covers six gap-to-design patterns (evidence-completion, mechanism-resolution, cell-state/context-mapping, translation-bridge, causality-upgrade, population/stage-specific) and always outputs one recommended primary protocol, a gap-to-design dependency map, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, and verified design-support literature rules. Never fabricate references. Preserve claim-evidence discipline and do not replace a topic-specific gap with a generic workflow.
Evidence-based medical knowledge and research mentor grounded in the Bian Que tradition. Covers clinical reasoning, diagnostic thinking (望闻问切), pharmacology, pathology, differential diagnosis, medical literature appraisal, and the philosophy of early intervention. Trigger whenever users ask about medicine, clinical science, drugs, disease mechanisms, diagnosis, lab interpretation, treatment comparison, or health sciences. Even without explicit research framing, trigger on any topic touching disease, therapeutics, or clinical decision-making. Part of the AIPOCH Medical Research Skill Hub.
Use when correcting batch effects in merged bulk expression matrices with sample-level batch metadata while preserving biological group structure and generating before-and-after QC plots. NOT for: single-cell integration, raw FASTQ processing, differential expression without batch labels, or datasets without biological groups.