reference-integrity-checker

Checks whether manuscript references are accurately matched to claims, appropriately scoped, and not overextended, misquoted, or second-hand cited.

Quality

63%

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 ./awesome-med-research-skills/Academic Writing/reference-integrity-checker/SKILL.md

Quality

Content

60%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 with concrete, actionable guidance, a clear sequenced workflow, and a properly organized one-level-deep reference bundle. Its main weakness is conciseness: the same concepts are restated across several sections, inflating the file.

Suggestions

Collapse redundant sections — fold 'Core Function' into 'Task', merge 'Hard Rules' with 'What This Skill Should Not Do', and drop 'Quality Standard' or fold it into the Task — to cut repetition.

Move the 'Important Distinctions' list into a reference file and link to it from the Execution steps instead of restating both inline.

Add one short worked example (a mismatched or overextended claim with the corrected citation) to lift actionability from good to fully concrete.

Dimension	Reasoning	Score
Conciseness	The body restates the same ideas across multiple sections (Core Function ≈ Task, Hard Rules ≈ What This Skill Should Not Do ≈ Scope 'not for', Quality Standard ≈ Task, Important Distinctions ≈ Execution steps), producing noticeable verbosity and several padded sections; it is above a 1 only because some domain distinctions are genuinely non-obvious.	2 / 5
Actionability	Provides concrete, specific guidance — exact matching dimensions (population, intervention/exposure, evidence level, direction, strength), a fixed output structure with named headers, and a severity taxonomy — which is mostly executable for an instruction-only skill with only minor gaps (no worked example).	4 / 5
Workflow Clarity	A clear 9-step Execution sequence with an explicit Step-1 clarification/input-validation gate and a mandatory output structure; the destructive/batch cap does not apply since this is a review task, but there is no explicit retry loop after requesting more material, keeping it just below 5.	4 / 5
Progressive Disclosure	Seven real, one-level-deep reference files are clearly signaled in the Reference Module Integration section with per-file usage guidance, giving good structure and easy navigation; it is not a 5 because the SKILL.md body itself inlines and repeats content that could live in those reference files.	4 / 5
	Total	14 / 20 Passed

Description

66%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 is specific, third-person, and clearly scoped to manuscript reference integrity, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger-term coverage is good though not exhaustive.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing manuscript citations for mismatch, overextension, second-hand citing, or quote drift before submission.'

Include more natural user phrasings such as 'citations actually support these claims' and 'quote drift' to broaden trigger-term coverage.

Mention common synonyms/file-context terms (e.g. 'reference list', 'response-to-reviewer drafts') to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete checks (matched to claims, appropriately scoped, not overextended, misquoted, second-hand cited), landing between the 'several specific actions' (4) and 'comprehensive coverage' (5) anchors but short of the maximally comprehensive example.	4 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause, and the rubric guideline caps completeness at 3 in that case; it is not a 4 because 'when' is only weakly implied by the domain rather than explicit.	3 / 5
Trigger Term Quality	Includes relevant natural terms (references, claims, citations, second-hand cited, misquoted, overextended), but omits common user phrasings such as 'quote drift' or 'do my citations actually support my claims', so it sits at good-but-not-comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (manuscript reference integrity vs. bibliography formatting) with distinct triggers, with only minor overlap risk against a generic citation-review skill, so it is mostly distinct rather than fully clear-cut.	4 / 5
	Total	15 / 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: awesome-med-research-skills/Academic Writing/reference-integrity-checker/SKILL.md
Commit: f5ef65b

Reviewed: ~8 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.