CtrlK
BlogDocsLog inGet started
Tessl Logo

mlava/scholar-sidekick-cli

Resolve scholarly identifiers (DOI including shortDOI aliases, PMID, PMCID, ISBN, arXiv, ISSN, ADS bibcode, WHO IRIS URL) into formatted citations (10,000+ CSL styles) and bibliography exports (BibTeX, RIS, EndNote, CSV…), and check retraction, open-access, and citation-fabrication status — from the terminal via the `scholar` CLI. Wraps the public REST API; needs Node ≥20 but no API key for the free tier. Use when the user wants to look up, cite, export, or verify a reference by DOI, PMID, PMCID, ISBN, arXiv ID, ISSN, ADS bibcode, or WHO IRIS URL from the terminal — including retraction, open-access, and fabricated-citation checks, or a whole-bibliography audit of a .bib/.ris/CSL-JSON file.

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

85%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 content is highly actionable with executable commands, a clear command table, and a strong error-recovery workflow for fabrication detection. Its main weakness is progressive disclosure: it references a REFERENCE.md that is not present in the bundle and inlines substantial reference-style material rather than splitting it into separate files.

Suggestions

Either ship the referenced REFERENCE.md (and any other linked files) in the bundle or remove the broken link, since absent references undercut progressive disclosure.

Move the full command table and per-command option detail into a separate reference file, keeping SKILL.md to a concise quick-start overview with one-level-deep, clearly-signaled links.

Trim the per-command prose where it repeats options already shown in the command table to nudge conciseness toward the lean-5 anchor.

DimensionReasoningScore

Conciseness

The body is dense and token-efficient — a compact command table and terse copy-paste examples with no padding of concepts Claude already knows — but the per-command prose and error-recovery loop, while justified for a fabrication-detection workflow, add minor length that keeps it just below the lean-5 anchor.

4 / 5

Actionability

Provides fully executable, copy-paste-ready `scholar` commands covering format, export, verify, audit, retraction, and oa, plus parsing guidance (`--json | jq`), matching the fully-executable anchor.

5 / 5

Workflow Clarity

The verify error-recovery loop is explicitly sequenced with exit-code checkpoints and a feedback path (re-run with --json, distinguish verdict vs error, report exactly what the tool returned), and audit exposes --fail-on-issues for CI gating — matching the explicit-validation-and-feedback-loops anchor.

5 / 5

Progressive Disclosure

No references/scripts/assets bundle exists, yet the body references REFERENCE.md which is absent, and a large command reference plus per-command prose is inlined that could be split out — structurally organized but references are not real and content that could be separate is inline.

3 / 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.

The description is comprehensive and well-structured: it states concrete capabilities, explicit trigger conditions with natural phrasing and file extensions, and clearly distinguishes itself from sibling skills. It is a strong example of a complete, specific, low-conflict description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — resolving many identifier types into formatted citations (10,000+ CSL styles) and bibliography exports (BibTeX, RIS, EndNote, CSV), plus retraction/open-access/fabrication checks — matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what (resolve identifiers into citations/exports/integrity checks via scholar CLI) and when ('Use when the user wants to look up, cite, export, or verify a reference...'), matching the both-what-and-when anchor.

5 / 5

Trigger Term Quality

Covers natural user phrases (look up, cite, export, verify, audit) alongside identifiers (DOI, PMID, arXiv, ISBN) and file extensions (.bib/.ris/CSL-JSON), matching the comprehensive-synonyms-and-extensions anchor.

5 / 5

Distinctiveness Conflict Risk

Niche is clearly scoped to scholarly identifier → citation/integrity from the terminal via the scholar CLI, with explicit redirects to sibling skills (api/mcp) for other environments; third-person voice; minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

75%

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

Validation12 / 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

relative_links

Relative link issues: 1 missing

Warning

Total

12

/

16

Passed

Reviewed

Table of Contents