Evidence Insight
pubmed-topic-recommend
87100Total 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
15 / 20 Passed
86You have a broad research direction (e.g., "immunotherapy biomarkers") and need 5 concrete, literature-grounded topic options to choose from
3/4
86You need research direction suggestions after a quick PubMed scan, with each suggestion tied to recent papers
3/4
86Uses the official PubMed E-utilities interface for literature retrieval
3/4
86Builds PubMed queries with:
3/4
86End-to-end case for Uses the official PubMed E-utilities interface for literature retrieval
3/4
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
PASSResearch 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 | The legacy review kept this workflow on the evidence-access side of the boundary, not the advice-giving side. |
| Methodological Ground | PASS | The older review treated the package logic as methodologically aligned with its stated workflow. |
| Code Usability | PASS | The packaged retrieval surface remained understandable at the command and parameter level in the archived review. |
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 pubmed-topic-recommend: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency
10 / 12
83%
Performance & Context
Performance context reached full score in the archived evaluation.
8 / 8
100%
Agent Usability
The archived evaluation left some headroom for pubmed-topic-recommend under agent usability.
14 / 16
88%
Human Usability
Human usability reached full score in the archived evaluation.
8 / 8
100%
Security
The legacy audit deducted points for pubmed-topic-recommend in security.
10 / 12
83%
Maintainability
The legacy audit deducted points for pubmed-topic-recommend in maintainability.
10 / 12
83%
Agent-Specific
Related legacy finding for pubmed-topic-recommend: Stabilize executable path and fallback behavior. Some inputs only reached PARTIAL due to execution gaps or weak boundary handling
17 / 20
85%
Core Capability Total88 / 100
Medical TaskExecution Average: 86 / 100 — Assertions: 15/20 Passed
86
Canonical
You have a broad research direction (e.g., "immunotherapy biomarkers") and need 5 concrete, literature-grounded topic options to choose from
3/4 ✓
86
Variant A
You need research direction suggestions after a quick PubMed scan, with each suggestion tied to recent papers
3/4 ✓
86
Edge
Uses the official PubMed E-utilities interface for literature retrieval
3/4 ✓
86
Variant B
Builds PubMed queries with:
3/4 ✓
86
Stress
End-to-end case for Uses the official PubMed E-utilities interface for literature retrieval
3/4 ✓
86
Canonical✅ Pass
You have a broad research direction (e.g., "immunotherapy biomarkers") and need 5 concrete, literature-grounded topic options to choose from
This canonical case was mostly intact, but the archived review centered its concern on: The script execution path completed successfully for the documented case.
Basic 33/40|Specialized 53/60|Total 86/100
✅A1The pubmed-topic-recommend output structure matches the documented deliverable
❌A2The script execution path completed successfully for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 3 / 4
86
Variant A✅ Pass
You need research direction suggestions after a quick PubMed scan, with each suggestion tied to recent papers
The preserved weakness for You need research direction suggestions after a quick PubMed scan, with each suggestion tied to recent papers was concentrated in one point: The script execution path completed successfully for the documented case.
Basic 31/40|Specialized 55/60|Total 86/100
✅A1The pubmed-topic-recommend output structure matches the documented deliverable
❌A2The script execution path completed successfully for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 3 / 4
86
Edge✅ Pass
Uses the official PubMed E-utilities interface for literature retrieval
This edge case was mostly intact, but the archived review centered its concern on: The script execution path completed successfully for the documented case.
Basic 30/40|Specialized 56/60|Total 86/100
✅A1The pubmed-topic-recommend output structure matches the documented deliverable
❌A2The script execution path completed successfully for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 3 / 4
86
Variant B✅ Pass
Builds PubMed queries with:
This variant b case was mostly intact, but the archived review centered its concern on: The script execution path completed successfully for the documented case.
Basic 29/40|Specialized 57/60|Total 86/100
✅A1The pubmed-topic-recommend output structure matches the documented deliverable
❌A2The script execution path completed successfully for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 3 / 4
86
Stress✅ Pass
End-to-end case for Uses the official PubMed E-utilities interface for literature retrieval
The preserved weakness for End-to-end case for Uses the official PubMed E-utilities interface for literature retrieval was concentrated in one point: The script execution path completed successfully for the documented case.
Basic 26/40|Specialized 60/60|Total 86/100
✅A1The pubmed-topic-recommend output structure matches the documented deliverable
❌A2The script execution path completed successfully for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 3 / 4
Medical Task Total86 / 100
Key Strengths
- Primary routing is Evidence Insight with execution mode B
- Static quality score is 88/100 and dynamic average is 73.6/100
- Assertions and command execution outcomes are recorded per input for human review
- Execution verification summary: Script verification 0/1; adjustment=0. run_topic_recommendation.py: rc=1