Evidence Insight
research-article-weekly
88100Total Score
Core Capability
76 / 100
Functional Suitability
10 / 12
Reliability
9 / 12
Performance & Context
8 / 8
Agent Usability
12 / 16
Human Usability
6 / 8
Security
8 / 12
Maintainability
8 / 12
Agent-Specific
15 / 20
Medical Task
20 / 20 Passed
100Generates a weekly academic literature report based on keywords using PubMed
4/4
96Generates a weekly academic literature report based on keywords using PubMed
4/4
94Generates a weekly academic literature report based on keywords using PubMed
4/4
94Packaged executable path(s): scripts/pubmed_search.py
4/4
94End-to-end case for Scope-focused workflow aligned to: Generates a weekly academic literature report based on keywords using PubMed. Use when the user wants to track recent research progress on a specific topic, automatically retrieving, classifying, and summarizing relevant papers from the last 7 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
PASSResearch Veto✅ PASS — Applicable
| Dimension | Result | Detail |
|---|---|---|
| Scientific Integrity | PASS | The archived evaluation kept the skill tied to retrieved records or indexed source material rather than invented scientific claims. |
| 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 | Code usability passed because the search or lookup workflow still exposed a usable entrypoint and output expectation. |
Core Capability76 / 100 — 8 Categories
Functional Suitability
A modest deduction remained in functional suitability for research-article-weekly in the archived review.
10 / 12
83%
Reliability
A modest deduction remained in reliability for research-article-weekly in the archived review.
9 / 12
75%
Performance & Context
No point loss was recorded for performance context in the legacy audit.
8 / 8
100%
Agent Usability
The archived evaluation left some headroom for research-article-weekly under agent usability.
12 / 16
75%
Human Usability
The archived deduction in human usability traces back to: Minor polish before wide rollout. No major defects found
6 / 8
75%
Security
The legacy audit deducted points for research-article-weekly in security.
8 / 12
67%
Maintainability
The legacy audit deducted points for research-article-weekly in maintainability.
8 / 12
67%
Agent-Specific
The archived evaluation left some headroom for research-article-weekly under agent specific.
15 / 20
75%
Core Capability Total76 / 100
Medical TaskExecution Average: 95.6 / 100 — Assertions: 20/20 Passed
100
Canonical
Generates a weekly academic literature report based on keywords using PubMed
4/4 ✓
96
Variant A
Generates a weekly academic literature report based on keywords using PubMed
4/4 ✓
94
Edge
Generates a weekly academic literature report based on keywords using PubMed
4/4 ✓
94
Variant B
Packaged executable path(s): scripts/pubmed_search.py
4/4 ✓
94
Stress
End-to-end case for Scope-focused workflow aligned to: Generates a weekly academic literature report based on keywords using PubMed. Use when the user wants to track recent research progress on a specific topic, automatically retrieving, classifying, and summarizing relevant papers from the last 7 days
4/4 ✓
100
Canonical✅ Pass
Generates a weekly academic literature report based on keywords using PubMed
The Generates a weekly academic literature report based on keywords... scenario completed within the documented Generates a weekly academic literature report based on keywords using PubMed boundary.
Basic 37/40|Specialized 60/60|Total 100/100
✅A1The research-article-weekly 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: 4 / 4
96
Variant A✅ Pass
Generates a weekly academic literature report based on keywords using PubMed
The Generates a weekly academic literature report based on keywords... scenario completed within the documented Generates a weekly academic literature report based on keywords using PubMed boundary.
Basic 35/40|Specialized 60/60|Total 96/100
✅A1The research-article-weekly 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: 4 / 4
94
Edge✅ Pass
Generates a weekly academic literature report based on keywords using PubMed
Generates a weekly academic literature report based on keywords... remained well-aligned with the documented contract in the preserved audit.
Basic 34/40|Specialized 60/60|Total 94/100
✅A1The research-article-weekly 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: 4 / 4
94
Variant B✅ Pass
Packaged executable path(s): scripts/pubmed_search.py
Packaged executable path(s): scripts/pubmed_search.py remained well-aligned with the documented contract in the preserved audit.
Basic 33/40|Specialized 60/60|Total 94/100
✅A1The research-article-weekly 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: 4 / 4
94
Stress✅ Pass
End-to-end case for Scope-focused workflow aligned to: Generates a weekly academic literature report based on keywords using PubMed. Use when the user wants to track recent research progress on a specific topic, automatically retrieving, classifying, and summarizing relevant papers from the last 7 days
The Generates a weekly academic literature report based on keywords using PubMed scenario completed within the documented Generates a weekly academic literature report based on keywords using PubMed boundary.
Basic 30/40|Specialized 60/60|Total 94/100
✅A1The research-article-weekly 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: 4 / 4
Medical Task Total95.6 / 100
Key Strengths
- Primary routing is Evidence Insight with execution mode B
- Static quality score is 76/100 and dynamic average is 82.6/100
- Assertions and command execution outcomes are recorded per input for human review
- Execution verification summary: Script verification 1/1; adjustment=5. pubmed_search.py: OK