Data Analysis

meta-criteria-generator

Generates scientifically sound inclusion and exclusion criteria for Meta-Analysis based on a given title or keywords. Use when user wants to design eligibility criteria for a systematic review or meta-analysis.

91100Total Score

Core Capability

83 / 100

Functional Suitability

11 / 12

Reliability

10 / 12

Performance & Context

8 / 8

Agent Usability

13 / 16

Human Usability

7 / 8

Security

9 / 12

Maintainability

9 / 12

Agent-Specific

16 / 20

Medical Task

20 / 20 Passed

100Generates scientifically sound inclusion and exclusion criteria for Meta-Analysis based on a given title or keywords

4/4

96Step 2: Generate Exclusion Criteria

4/4

94Step 2: Generate Exclusion Criteria

4/4

94Step 1: Generate Inclusion Criteria

4/4

94Step 3: Extract and Format

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 integrity held because extraction and analysis outputs stayed tied to provided text, metadata, or runtime evidence rather than invented study findings.
Practice Boundaries	PASS	The archived review kept this package within Generates scientifically sound inclusion and exclusion criteria for Meta-Analysis based on..., not freeform inference detached from source data.
Methodological Ground	PASS	Methodological grounding was preserved through the documented inputs, transformations, and expected artifacts.
Code Usability	PASS	Code usability passed because the package still exposed a reviewable execution surface for its documented workflow.

Core Capability83 / 100 — 8 Categories

Functional Suitability

Functional suitability stayed high, with only minor headroom in how the analysis outcome is framed.

11 / 12

92%

Reliability

Reliability remained good, but the archived review still saw room for steadier behavior under edge conditions.

10 / 12

83%

Performance & Context

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

8 / 8

100%

Agent Usability

The archived review left some headroom in how quickly an agent can lock onto the intended analysis path.

13 / 16

81%

Human Usability

Human usability was softened by the legacy issue 'Minor polish before wide rollout'. No major defects found

7 / 8

88%

Security

A modest security gap remained in the archived evaluation despite otherwise controlled workflow behavior.

9 / 12

75%

Maintainability

The archived review treated the package as maintainable, while still preserving some room for cleanup.

9 / 12

75%

Agent-Specific

Agent-specific quality remained high, with only modest headroom in structured prompting or edge handling.

16 / 20

80%

Core Capability Total83 / 100

Medical TaskExecution Average: 95.6 / 100 — Assertions: 20/20 Passed

100

Canonical

Generates scientifically sound inclusion and exclusion criteria for Meta-Analysis based on a given title or keywords

4/4 ✓

Variant A

Step 2: Generate Exclusion Criteria

4/4 ✓

Edge

Step 2: Generate Exclusion Criteria

4/4 ✓

Variant B

Step 1: Generate Inclusion Criteria

4/4 ✓

Stress

Step 3: Extract and Format

4/4 ✓

100

Canonical✅ Pass

Generates scientifically sound inclusion and exclusion criteria for Meta-Analysis based on a given title or keywords

The archived run for Generates scientifically sound inclusion and exclusion criteria for... confirmed the helper entrypoint and left the workflow in a stable state.

Basic 38/40|Specialized 60/60|Total 100/100

✅A1The meta-criteria-generator 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

Variant A✅ Pass

Step 2: Generate Exclusion Criteria

The archived run for Step 2: Generate Exclusion Criteria confirmed the helper entrypoint and left the workflow in a stable state.

Basic 36/40|Specialized 60/60|Total 96/100

✅A1The meta-criteria-generator 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

Edge✅ Pass

Step 2: Generate Exclusion Criteria

The archived run for Step 2: Generate Exclusion Criteria confirmed the helper entrypoint and left the workflow in a stable state.

Basic 35/40|Specialized 59/60|Total 94/100

✅A1The meta-criteria-generator 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

Variant B✅ Pass

Step 1: Generate Inclusion Criteria

For Step 1: Generate Inclusion Criteria, the preserved evidence is lightweight but positive: the packaged validation command behaved as expected.

Basic 34/40|Specialized 60/60|Total 94/100

✅A1The meta-criteria-generator 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

Stress✅ Pass

Step 3: Extract and Format

The Step 3: Extract and Format path verified the packaged helper command without exposing a deeper execution issue.

Basic 31/40|Specialized 60/60|Total 94/100

✅A1The meta-criteria-generator 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 Data Analysis with execution mode B
Static quality score is 83/100 and dynamic average is 82.6/100
Assertions and command execution outcomes are recorded per input for human review
Execution verification summary: Script verification 2/2; adjustment=5. extract_criteria.py: OK; validate_skill.py: OK