Academic Writing
meta-manuscript-generator
88100Total Score
Core Capability
83 / 100
Functional Suitability
10 / 12
Reliability
10 / 12
Performance & Context
8 / 8
Agent Usability
13 / 16
Human Usability
7 / 8
Security
9 / 12
Maintainability
10 / 12
Agent-Specific
16 / 20
Medical Task
20 / 20 Passed
95Generates a first draft of a clinical meta-analysis paper. Input the research report (including Methods and Results sections), language, and title to automatically generate a complete paper draft including Abstract, Introduction, Discussion, and other sections, with automatic PubMed retrieval of relevant references. Suitable for assisting in the writing of systematic reviews and meta-analyses
4/4
91Generates a first draft of a clinical meta-analysis paper. Input the research report (including Methods and Results sections), language, and title to automatically generate a complete paper draft including Abstract, Introduction, Discussion, and other sections, with automatic PubMed retrieval of relevant references. Suitable for assisting in the writing of systematic reviews and meta-analyses
4/4
89Stage 2: Reference Retrieval
4/4
89Packaged executable path(s): scripts/insert_references.py plus 1 additional script(s)
4/4
89Stage 2: Reference Retrieval
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 legacy review did not flag invented scientific claims in the package's writing-oriented output. |
| Practice Boundaries | PASS | The evaluated outputs stayed inside the Generates a first draft of a clinical meta-analysis paper. Input the research report... workflow rather than drifting into unsupported scientific interpretation. |
| Methodological Ground | PASS | No methodological-grounding issue was recorded for meta-manuscript-generator in the archived evaluation. |
| Code Usability | N/A | The core deliverable is textual rather than executable, which makes code usability not applicable in this case. |
Core Capability83 / 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
10 / 12
83%
Reliability
Related legacy finding for meta-manuscript-generator: 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 package guides agents reasonably well, while still leaving a little room for crisper trigger wording.
13 / 16
81%
Human Usability
Human usability remained good overall, with minor room to make the output package easier to scan or hand off.
7 / 8
88%
Security
Security scored well, though the archived review still left some room to state source-faithful boundaries more explicitly.
9 / 12
75%
Maintainability
The workflow is low-risk to maintain, though a little more structural cleanup would likely close the remaining gap.
10 / 12
83%
Agent-Specific
Agent specific was softened by the legacy issue '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
Generates a first draft of a clinical meta-analysis paper. Input the research report (including Methods and Results sections), language, and title to automatically generate a complete paper draft including Abstract, Introduction, Discussion, and other sections, with automatic PubMed retrieval of relevant references. Suitable for assisting in the writing of systematic reviews and meta-analyses
4/4 ✓
91
Variant A
Generates a first draft of a clinical meta-analysis paper. Input the research report (including Methods and Results sections), language, and title to automatically generate a complete paper draft including Abstract, Introduction, Discussion, and other sections, with automatic PubMed retrieval of relevant references. Suitable for assisting in the writing of systematic reviews and meta-analyses
4/4 ✓
89
Edge
Stage 2: Reference Retrieval
4/4 ✓
89
Variant B
Packaged executable path(s): scripts/insert_references.py plus 1 additional script(s)
4/4 ✓
89
Stress
Stage 2: Reference Retrieval
4/4 ✓
95
Canonical✅ Pass
Generates a first draft of a clinical meta-analysis paper. Input the research report (including Methods and Results sections), language, and title to automatically generate a complete paper draft including Abstract, Introduction, Discussion, and other sections, with automatic PubMed retrieval of relevant references. Suitable for assisting in the writing of systematic reviews and meta-analyses
The archived run for Generates a first draft of a clinical meta-analysis paper. Input... stayed on the narrative-deliverable path rather than a code path.
Basic 36/40|Specialized 59/60|Total 95/100
✅A1The meta-manuscript-generator 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
Generates a first draft of a clinical meta-analysis paper. Input the research report (including Methods and Results sections), language, and title to automatically generate a complete paper draft including Abstract, Introduction, Discussion, and other sections, with automatic PubMed retrieval of relevant references. Suitable for assisting in the writing of systematic reviews and meta-analyses
Generates a first draft of a clinical meta-analysis paper. Input... remained a writing-first workflow and was evaluated without depending on a runnable helper script.
Basic 34/40|Specialized 57/60|Total 91/100
✅A1The meta-manuscript-generator 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
Stage 2: Reference Retrieval
The archived run for Stage 2: Reference Retrieval stayed on the narrative-deliverable path rather than a code path.
Basic 33/40|Specialized 56/60|Total 89/100
✅A1The meta-manuscript-generator 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
Packaged executable path(s): scripts/insert_references.py plus 1 additional script(s)
The archived run for Packaged executable path(s): scripts/insert_references.py plus 1... stayed on the narrative-deliverable path rather than a code path.
Basic 32/40|Specialized 57/60|Total 89/100
✅A1The meta-manuscript-generator 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
Stage 2: Reference Retrieval
This stress case was handled as a bounded writing workflow, not as an executable pipeline.
Basic 29/40|Specialized 60/60|Total 89/100
✅A1The meta-manuscript-generator 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 Academic Writing with execution mode B
- Static quality score is 83/100 and dynamic average is 79.6/100
- Assertions and command execution outcomes are recorded per input for human review
- Execution verification summary: Script verification 1/2; adjustment=3. insert_references.py: OK; search_references.py: error=Command 'python "E:\aipoach-skill\20260314\Academic Writing\meta-manuscript-generator\scripts\search_references.py" --help' timed out after 8 seconds