consistency-checker-across-manuscript

Checks consistency across title, abstract, methods, results, figures, tables, and supplements to identify internal contradictions and version drift in biomedical manuscripts.

Quality

66%

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/consistency-checker-across-manuscript/SKILL.md

Quality

Content

67%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 a well-structured, actionable instruction skill with a clear multi-step workflow and properly organized one-level reference files. Its main weakness is redundancy: the same distinctions and rules are repeated across many sections, inflating token usage without adding guidance value.

Suggestions

Consolidate the repeated distinctions and hard rules into a single canonical section, relying on the reference files (e.g., hard-rules.md, component-alignment-rules.md) rather than restating them in Task, Important Distinctions, Core Function, Hard Rules, and What This Skill Should Not Do.

Remove or merge the 'Core Function' list with the 'Execution' steps, since both enumerate the same workflow at nearly identical granularity.

Treat 'What This Skill Should Not Do' and 'Quality Standard' as trim candidates, folding their non-duplicated points into the Scope Boundary or Hard Rules sections.

Dimension	Reasoning	Score
Conciseness	Individual sections avoid concept padding, but the same guidance (true-inconsistency-vs-variation, severity tiers, don't invent inconsistencies, ask for materials) is restated 4-6 times across Task, Important Distinctions, Core Function, Execution, Hard Rules, and What This Skill Should Not Do, adding avoidable token cost.	3 / 5
Actionability	Provides concrete comparison checks ('results match the figures/tables cited'), named inconsistency patterns, a mandated 8-section output structure with explicit A-H headers, and severity tiers — highly actionable for an instruction-only skill with only minor gaps.	4 / 5
Workflow Clarity	An 8-step Execution sequence with an explicit clarify-before-check gate and an Input Validation checkpoint is clearly laid out; it falls short of 5 only because there is no explicit error-recovery feedback loop, which is acceptable for a read-only review skill.	4 / 5
Progressive Disclosure	The body points to 8 real, clearly signaled one-level-deep reference files each with a usage cue, and serves as an overview; minor gaps arise because some guidance (e.g., Hard Rules, Important Distinctions) is duplicated inline rather than living solely in the references.	4 / 5
	Total	15 / 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, well-targeted, and names concrete components and actions for a distinct niche, but it omits an explicit 'Use when...' trigger clause, leaving the 'when to invoke' guidance only implied. Adding a concrete trigger clause would lift completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when checking whether a biomedical manuscript is internally consistent across title, abstract, methods, results, figures, and tables, or when reviewing for version drift after revision').

Add common user synonyms such as 'manuscript alignment' and 'contradictions across sections' to broaden trigger-term coverage.

Tighten the action list so it reads as enumerated concrete actions rather than a single compound sentence.

Dimension	Reasoning	Score
Specificity	Names the domain and several specific components (title, abstract, methods, results, figures, tables, supplements) plus concrete actions ('Checks consistency', 'identify internal contradictions and version drift'), with minor gaps in action enumeration.	4 / 5
Completeness	A clear 'what' is present but there is no explicit 'Use when...' trigger clause, so 'when' is only weakly implied, capping completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	Good coverage of natural user terms ('consistency', 'internal contradictions', 'version drift', 'biomedical manuscripts', component names), though a few common synonyms like 'alignment' or 'contradictions across sections' are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a distinct niche (biomedical manuscript cross-component consistency and version drift) with only minor overlap risk against closely related proofreading/editing skills.	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/consistency-checker-across-manuscript/SKILL.md
Commit: f5ef65b

Reviewed: ~9 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.