Check for co-authorship conflicts between authors and suggested reviewers
68
52%
Does it follow best practices?
Impact
99%
1.94xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/conflict-of-interest-checker/SKILL.mdScript invocation with correct flags
Correct script path
0%
83%
--authors flag used
0%
100%
--reviewers flag used
0%
100%
Comma-separated names
0%
100%
All three authors included
50%
100%
All five reviewers included
50%
100%
No extra packages installed
100%
100%
Script not reimplemented
0%
100%
Recommendations captured
100%
100%
Report output present
100%
100%
Without context: $0.3953 · 1m 59s · 25 turns · 124 in / 6,319 out tokens
With context: $0.2585 · 50s · 16 turns · 1,995 in / 2,481 out tokens
CSV format and --publications flag
CSV column: author
100%
100%
CSV column: reviewer
0%
100%
CSV column: paper_id
100%
100%
--publications flag used
0%
100%
Correct script invocation
0%
100%
Script not reimplemented
0%
100%
Ferreira-Tanaka conflict captured
50%
100%
Zhang-Popescu conflict captured
50%
100%
Conflicts flagged in output
75%
100%
No extra packages installed
100%
100%
Without context: $0.4831 · 1m 55s · 26 turns · 28 in / 7,319 out tokens
With context: $0.5930 · 2m 18s · 24 turns · 2,003 in / 8,421 out tokens
Output interpretation and recommendations
Correct CSV columns
0%
100%
--publications flag used
0%
100%
Correct script path
0%
87%
Three separate runs
100%
100%
O'Brien flagged (Paper 1)
100%
100%
Nakamura flagged (Paper 2)
100%
100%
Recuse recommendation documented
100%
100%
Shared papers cited
100%
100%
Comma-separated names format
100%
100%
No extra packages
100%
100%
Compliance use case acknowledged
100%
100%
Without context: $0.5878 · 2m 24s · 28 turns · 37 in / 9,243 out tokens
With context: $0.6184 · 2m 10s · 27 turns · 2,005 in / 8,248 out tokens
4a48721
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.