Other

markitdown

88100Total Score
Core Capability
83 / 100
Functional Suitability
10 / 12
Reliability
9 / 12
Performance & Context
8 / 8
Agent Usability
13 / 16
Human Usability
8 / 8
Security
9 / 12
Maintainability
10 / 12
Agent-Specific
16 / 20
Medical Task
20 / 20 Passed
95Converting research papers or reports (PDF/DOCX/EPUB/HTML) into Markdown for LLM summarization, Q&A, or RAG indexing
4/4
91Extracting tables and structured content from spreadsheets (XLSX/CSV) into Markdown for analysis or documentation
4/4
89Converts many formats to structured Markdown (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, YouTube URLs, etc.)
4/4
89Produces token-efficient output suitable for LLM pipelines (summarization, chunking, embedding)
4/4
89End-to-end case for Converts many formats to structured Markdown (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, YouTube URLs, etc.)
4/4

Veto GatesRequired pass for any deployment consideration

Skill Veto✓ All 4 gates passed
✓
Operational Stability
System remains stable across varied inputs and edge cases
PASS
✓
Structural Consistency
Output structure conforms to expected skill contract format
PASS
✓
Result Determinism
Equivalent inputs produce semantically equivalent outputs
PASS
✓
System Security
No prompt injection, data leakage, or unsafe tool use detected
PASS

Core Capability83 / 100 — 8 Categories

Functional Suitability
Related legacy finding for markitdown: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency
10 / 12
83%
Reliability
The archived deduction in reliability traces back to: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency
9 / 12
75%
Performance & Context
Performance context reached full score in the archived evaluation.
8 / 8
100%
Agent Usability
The archived evaluation left some headroom for markitdown under agent usability.
13 / 16
81%
Human Usability
The legacy audit gave full marks to human usability for this package.
8 / 8
100%
Security
A modest deduction remained in security for markitdown in the archived review.
9 / 12
75%
Maintainability
A modest deduction remained in maintainability for markitdown in the archived review.
10 / 12
83%
Agent-Specific
Related legacy finding for markitdown: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency
16 / 20
80%
Core Capability Total83 / 100

Medical TaskExecution Average: 90.6 / 100 — Assertions: 20/20 Passed

95
Canonical
Converting research papers or reports (PDF/DOCX/EPUB/HTML) into Markdown for LLM summarization, Q&A, or RAG indexing
4/4 ✓
91
Variant A
Extracting tables and structured content from spreadsheets (XLSX/CSV) into Markdown for analysis or documentation
4/4 ✓
89
Edge
Converts many formats to structured Markdown (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, YouTube URLs, etc.)
4/4 ✓
89
Variant B
Produces token-efficient output suitable for LLM pipelines (summarization, chunking, embedding)
4/4 ✓
89
Stress
End-to-end case for Converts many formats to structured Markdown (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, YouTube URLs, etc.)
4/4 ✓
95
Canonical✅ Pass
Converting research papers or reports (PDF/DOCX/EPUB/HTML) into Markdown for LLM summarization, Q&A, or RAG indexing

Converting research papers or reports (PDF/DOCX/EPUB/HTML) into... was evaluated as a bounded documentation path, not as a runnable script workflow.

Basic 36/40|Specialized 59/60|Total 95/100
✅A1The markitdown output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
91
Variant A✅ Pass
Extracting tables and structured content from spreadsheets (XLSX/CSV) into Markdown for analysis or documentation

This variant a case stayed inside the documented workflow and remained instruction-led.

Basic 34/40|Specialized 57/60|Total 91/100
✅A1The markitdown output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
89
Edge✅ Pass
Converts many formats to structured Markdown (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, YouTube URLs, etc.)

The archived run for Converts many formats to structured Markdown (PDF, DOCX, PPTX,... remained guidance-driven rather than command-driven.

Basic 33/40|Specialized 56/60|Total 89/100
✅A1The markitdown output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
89
Variant B✅ Pass
Produces token-efficient output suitable for LLM pipelines (summarization, chunking, embedding)

This variant b case stayed inside the documented workflow and remained instruction-led.

Basic 32/40|Specialized 57/60|Total 89/100
✅A1The markitdown output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
89
Stress✅ Pass
End-to-end case for Converts many formats to structured Markdown (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, YouTube URLs, etc.)

This stress case stayed inside the documented workflow and remained instruction-led.

Basic 29/40|Specialized 60/60|Total 89/100
✅A1The markitdown output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
Medical Task Total90.6 / 100

Key Strengths

  • Primary routing is Other with execution mode B
  • Static quality score is 83/100 and dynamic average is 77.6/100
  • Assertions and command execution outcomes are recorded per input for human review
  • Execution verification summary: Script verification 3/3; adjustment=5. batch_convert.py: OK; convert_literature.py: OK; convert_with_ai.py: OK