CtrlK
BlogDocsLog inGet started
Tessl Logo

mlava/scholar-sidekick-mcp

Use the connected scholar-sidekick-mcp MCP server when the user mentions a scholarly identifier (DOI including shortDOI aliases, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcode, WHO IRIS URL) and wants structured metadata, a formatted citation, a bibliography export file, a retraction check, an open-access check, verification that a claimed citation is real (not fabricated), or a whole-bibliography audit (batch fabrication + retraction check). Requires the MCP server connected — it works anonymously, no API key required; for a zero-install path use the scholar-sidekick-api skill instead.

72

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

82%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.

A well-structured, highly actionable instruction-only skill body that names exact tools, parameters, and accepted values with clear sequencing and a preflight validation step. It is dense in places and could trim redundancy and consider splitting the tool catalog.

Suggestions

In Step 0, state the 'do not run tool names in a terminal / do not self-install the server' rule once instead of repeating it in both the intro paragraph and the bold note.

Consider moving the per-tool catalog in Step 1 (resolveIdentifier/verifyCitation/auditBibliography etc.) into a references file linked from SKILL.md, keeping only the decision table inline to lighten the overview.

Tighten the verifyCitation rationale (the 'Topaz et al., Lancet 2026' sentence) to a one-line justification so the fabrication-pattern note stays concise.

DimensionReasoningScore

Conciseness

Mostly efficient and information-dense about tool specifics without explaining concepts Claude already knows, but Step 0 repeats the 'do not run tool names in a terminal' guidance twice and a few passages (e.g. the verifyCitation fabrication rationale) could be trimmed — matching the 'minor over-explanation' score-4 anchor rather than the lean score-5 anchor.

4 / 5

Actionability

Gives fully concrete, executable guidance: exact tool names, parameter names (text, id, style, format, title, doi...), accepted values (vancouver/ama/apa/ieee/cse; bib/ris/csl/endnote-xml...), and batch rules (max 25 per call, single id for retraction/OA) — the instruction-only equivalent of copy-paste-ready guidance.

5 / 5

Workflow Clarity

Steps 0–5 are clearly sequenced with an explicit Step 0 validation/stop checkpoint ('If these tools are not in your available toolset ... say so plainly and stop') and batch-failure handling for auditBibliography, but there is no validate→fix→retry feedback loop, which sits just below the score-5 anchor.

4 / 5

Progressive Disclosure

No bundle files exist and the single-file body is well organized into clear, navigable sections (When to Use, How to Use, Guidelines, When NOT to Use) with no nested references; the dense Step 1 tool catalog keeps it at good-but-could-split rather than the cleanly-partitioned score-5 anchor.

4 / 5

Total

17

/

20

Passed

Description

100%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.

An exemplary description that concretely states capabilities, trigger conditions, and the identifier surface, while clearly distinguishing itself from the related api skill. It is dense but not padded.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'structured metadata, a formatted citation, a bibliography export file, a retraction check, an open-access check, verification that a claimed citation is real (not fabricated), or a whole-bibliography audit' — covering the domain comprehensively, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (resolve identifiers into metadata/citation/export/retraction/OA/verification/audit) and 'when' ('when the user mentions a scholarly identifier ... and wants ...'), with concrete trigger phrases — the score-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including identifier synonyms (DOI, shortDOI, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcode, WHO IRIS URL) and user phrases ('retraction check', 'open-access check', 'is this real/not fabricated', 'audit my bibliography').

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (scholarly-identifier resolution via the connected scholar-sidekick-mcp MCP server) with distinct triggers, and explicitly disambiguates from the zero-install scholar-sidekick-api skill, minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Reviewed

Table of Contents