conflict-of-interest-checker

Check for co-authorship and institutional conflicts between authors and suggested reviewers to support peer review integrity. Coauthorship and institutional conflict detection supported.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/conflict-of-interest-checker/SKILL.md

Quality

Content

58%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and largely actionable with real bundle-file references, but it suffers from redundant sections and lacks an explicit executable validation checkpoint for a batch screening workflow. Tightening duplication and adding a concrete verify-step would raise the score.

Suggestions

Add an explicit validation checkpoint (e.g. 'Run `python -m py_compile scripts/main.py` and confirm exit code 0 before reporting results') and a validate->fix->retry loop for the batch reviewer screening.

De-duplicate overlapping sections: merge Quick Check into Audit-Ready Commands and consolidate Output Requirements, Stress-Case Rules, and Response Template, which restate the same deliverable structure.

Fix or remove the buggy `check_institutional_conflict()` path in the bundled script so the 'Claude Direct Path' workaround is not the only correct route.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with organized sections and concrete commands, but it carries redundancy (Quick Check vs Audit-Ready Commands repeat the same py_compile line, Output and Output Requirements and Stress-Case Rules and Response Template overlap) and generic process boilerplate that could be tightened.	3 / 5
Actionability	It provides mostly executable, copy-paste-ready bash commands with concrete flags and a CSV format example, with only minor gaps (e.g. the institutional path is described procedurally rather than as runnable code).	4 / 5
Workflow Clarity	There are clearly sequenced steps and a fallback path, but no executable validation/checkpoint before reporting for a batch reviewer-screening operation, and the documented institutional method is a known bug; the rubric caps destructive/batch workflows lacking validation at 3.	3 / 5
Progressive Disclosure	Content is well-organized into single-purpose sections with one concrete bundle file (scripts/main.py) referenced by path; the overview is compact and references are clearly signaled, with only minor gaps since there is no separate reference/asset layer to navigate.	4 / 5
	Total	14 / 20 Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys a clear, specific purpose and a distinct niche, but lacks an explicit 'Use when...' trigger clause and has thin trigger-term coverage with redundant phrasing. Adding a natural-language trigger phrase and dropping the redundant restatement would lift it toward the top anchors.

Suggestions

Add an explicit trigger clause, e.g. 'Use when screening journal or grant reviewers for conflicts of interest with manuscript authors.'

Broaden trigger terms with natural synonyms like 'recusal', 'reviewer conflicts', 'COI screening', and 'reviewer selection'.

Remove the redundant trailing sentence 'Coauthorship and institutional conflict detection supported.' which adds no new information.

Dimension	Reasoning	Score
Specificity	Names the domain (conflict-of-interest checking for peer review) and two concrete detection actions (co-authorship and institutional conflicts), meeting the 'several specific actions; minor gaps' anchor; coverage is broad but collaboration-conflict detection is omitted, keeping it below 5.	4 / 5
Completeness	It has a clear 'what' but no 'Use when...' trigger clause; per the rubric a missing explicit trigger guidance caps completeness at 3, and the appended restatement does not supply a 'when' condition.	3 / 5
Trigger Term Quality	Includes some natural terms ('co-authorship', 'conflicts', 'reviewers', 'peer review') but lacks common synonyms and trigger phrases users would actually say, and redundantly repeats 'Coauthorship and institutional conflict detection supported' rather than adding fresh natural keywords.	3 / 5
Distinctiveness Conflict Risk	The niche (co-authorship/institutional conflicts between authors and suggested reviewers) is fairly distinct with only minor overlap risk against general peer-review or bibliographic skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/conflict-of-interest-checker/SKILL.md
Commit: f5ef65b

Reviewed: ~14 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.