Evidence Insight

biorxiv-database

Search, retrieve metadata, and download PDFs for bioRxiv preprints; use when you need to discover biology preprints by keywords/authors/date ranges and programmatically fetch their details.

88100Total Score

Core Capability

88 / 100

Functional Suitability

11 / 12

Reliability

10 / 12

Performance & Context

8 / 8

Agent Usability

14 / 16

Human Usability

8 / 8

Security

10 / 12

Maintainability

10 / 12

Agent-Specific

17 / 20

Medical Task

20 / 20 Passed

92You need to find recent bioRxiv preprints for a topic (e.g., "CRISPR") within a specific time window (last N days)

4/4

88You want to build a literature monitoring pipeline that periodically searches bioRxiv and collects results

4/4

86Keyword-based search with a configurable lookback window (days)

4/4

86Structured metadata retrieval in JSON-like dictionaries (e.g., Title, Abstract, DOI, Authors)

4/4

86End-to-end case for Keyword-based search with a configurable lookback window (days)

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

Research Veto✅ PASS — Applicable

Dimension	Result	Detail
Scientific Integrity	PASS	Scientific content remained anchored to fetched metadata or source-linked evidence in the legacy review.
Practice Boundaries	PASS	Practice boundaries held because the package remained focused on source handling, lookup, or structured evidence use.
Methodological Ground	PASS	The older review treated the package logic as methodologically aligned with its stated workflow.
Code Usability	PASS	The legacy evaluation did not preserve a usability failure in the packaged retrieval path.

Core Capability88 / 100 — 8 Categories

Functional Suitability

The archived deduction in functional suitability traces back to: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency

11 / 12

92%

Reliability

Related legacy finding for biorxiv-database: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency

10 / 12

83%

Performance & Context

The legacy audit gave full marks to performance context for this package.

8 / 8

100%

Agent Usability

The archived evaluation left some headroom for biorxiv-database under agent usability.

14 / 16

88%

Human Usability

No point loss was recorded for human usability in the legacy audit.

8 / 8

100%

Security

The archived evaluation left some headroom for biorxiv-database under security.

10 / 12

83%

Maintainability

The archived evaluation left some headroom for biorxiv-database under maintainability.

10 / 12

83%

Agent-Specific

The archived deduction in agent specific traces back to: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency

17 / 20

85%

Core Capability Total88 / 100

Medical TaskExecution Average: 87.6 / 100 — Assertions: 20/20 Passed

Canonical

You need to find recent bioRxiv preprints for a topic (e.g., "CRISPR") within a specific time window (last N days)

4/4 ✓

Variant A

You want to build a literature monitoring pipeline that periodically searches bioRxiv and collects results

4/4 ✓

Edge

Keyword-based search with a configurable lookback window (days)

4/4 ✓

Variant B

Structured metadata retrieval in JSON-like dictionaries (e.g., Title, Abstract, DOI, Authors)

4/4 ✓

Stress

End-to-end case for Keyword-based search with a configurable lookback window (days)

4/4 ✓

Canonical✅ Pass

You need to find recent bioRxiv preprints for a topic (e.g., "CRISPR") within a specific time window (last N days)

The archived run for You need to find recent bioRxiv preprints for a topic (e.g.,... remained guidance-driven rather than command-driven.

Basic 36/40|Specialized 56/60|Total 92/100

✅A1The biorxiv-database 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

Variant A✅ Pass

You want to build a literature monitoring pipeline that periodically searches bioRxiv and collects results

You want to build a literature monitoring pipeline that... was evaluated as a bounded documentation path, not as a runnable script workflow.

Basic 34/40|Specialized 54/60|Total 88/100

✅A1The biorxiv-database 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

Edge✅ Pass

Keyword-based search with a configurable lookback window (days)

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

Basic 33/40|Specialized 53/60|Total 86/100

✅A1The biorxiv-database 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

Variant B✅ Pass

Structured metadata retrieval in JSON-like dictionaries (e.g., Title, Abstract, DOI, Authors)

The archived run for Structured metadata retrieval in JSON-like dictionaries (e.g.,... remained guidance-driven rather than command-driven.

Basic 32/40|Specialized 54/60|Total 86/100

✅A1The biorxiv-database 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

Stress✅ Pass

End-to-end case for Keyword-based search with a configurable lookback window (days)

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

Basic 29/40|Specialized 57/60|Total 86/100

✅A1The biorxiv-database 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 Total87.6 / 100

Key Strengths

Primary routing is Evidence Insight with execution mode B
Static quality score is 88/100 and dynamic average is 79.6/100
Assertions and command execution outcomes are recorded per input for human review
Execution verification summary: Script verification 0/1; adjustment=0. biorxiv_search.py: error=Command 'python "E:\aipoach-skill\20260314_V2\Evidence Insight\biorxiv-database\scripts\biorxiv_search.py" --help' timed out after 8 seconds