scientific-thinking-scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback. Use when evaluating academic or scientific work — papers, proposals, methods sections, or evidence quality — against a repeatable rubric.

Quality

79%

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 ./skills/scientific-thinking-scholar-evaluation/SKILL.md

Quality

Content

75%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 actionable: a defined scoring scale, nine concrete dimensions, a clear review sequence with a claims-checking checkpoint, a complete output template, and honest pitfalls. Weaknesses are minor — small redundancy between sections, no worked examples, no explicit feedback loops, and a rubric block that could live in a reference file.

Suggestions

Add one worked example (a filled-in dimension-score row with evidence and revision priority) to make the output template fully concrete.

Trim the redundant overlap between the "When to Use" bullets and the "Evaluation Scope" artifact list, and drop the opening line that repeats the description.

Consider moving the nine-dimension question bank to a one-level-deep reference file (e.g., references/dimensions.md), keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is a lean set of checklists and templates with no padding and no explanation of concepts Claude already knows. Minor trims are possible — the opening line repeats the frontmatter description and the "When to Use" bullets overlap the "Evaluation Scope" artifact list — so it is efficient with minor over-explanation rather than perfectly lean.	4 / 5
Actionability	Concrete, executable instruction-only guidance: a defined 1–5 scale with labels, an N/A rule, nine dimensions of specific probe questions, a complete copy-paste markdown output template, and a pitfalls section. It falls short of fully copy-paste-ready only in lacking a worked example (e.g., one filled-in dimension row or a sample evidence check).	4 / 5
Workflow Clarity	The six-step Review Process is clearly sequenced and includes a verification checkpoint ("Check the strongest claims against cited sources") plus separating blockers from suggestions. No explicit feedback/retry loops or validation gates are present, keeping it below the score-5 anchor, but sequence and checkpoints clearly exceed the score-3 anchor; the skill is non-destructive so no cap applies.	4 / 5
Progressive Disclosure	No bundle files exist and all content is appropriately inline with well-organized, well-signaled sections (scope → rubric → process → template → pitfalls). The ~160-line rubric question bank is a plausible candidate for a one-level-deep reference file, which is a minor organization gap rather than misplaced content.	4 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong description: it clearly states both capability and explicit trigger conditions with concrete artifacts. Its only weaknesses are limited action-verb variety, some missing natural synonyms (peer review, manuscript, thesis), and minor overlap with general writing-feedback skills.

Suggestions

Diversify the action verbs beyond "evaluation" — e.g., "score ... against a rubric", "check citation support", "compare works" — to strengthen the specificity of capabilities.

Add natural trigger synonyms users commonly say, such as "peer review", "manuscript", or "thesis", to the Use-when clause.

Narrow "research-writing feedback" or anchor it to the rubric context to reduce overlap with generic writing-assistance skills.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete evaluation targets ("papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback") with minor gaps, but rests on a single core action verb ("evaluation") rather than multiple distinct concrete actions, so it fits the several-specific-actions anchor rather than the comprehensive score-5 anchor.	4 / 5
Completeness	Explicitly answers both what ("Structured scholarly-work evaluation for papers, proposals, ... citation support, and research-writing feedback") and when ("Use when evaluating academic or scientific work — papers, proposals, methods sections, or evidence quality — against a repeatable rubric") with concrete trigger phrases, matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	Natural phrases users would say are present ("papers", "proposals", "methods sections", "evidence quality"), but common synonyms like "peer review", "manuscript", and "thesis" are missing, matching good-but-not-comprehensive keyword coverage.	4 / 5
Distinctiveness Conflict Risk	The rubric-based scholarly-evaluation niche is clear with distinct triggers, but "research-writing feedback" and generic "evaluation" slightly overlap with general writing-review skills, so overlap risk is minor rather than minimal.	4 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/scientific-thinking-scholar-evaluation/SKILL.md
Commit: c70874f

Reviewed: 1 day 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.