CtrlK
BlogDocsLog inGet started
Tessl Logo

mlava/scholar-sidekick-python

Resolve scholarly identifiers (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS bibcode, WHO IRIS URL) into formatted citations (10,000+ CSL styles) and bibliography exports (BibTeX, RIS, EndNote, CSV…), verify a claimed citation against the record its identifier actually resolves to, and audit a reference list of any length for fabricated and retracted entries — from Python via the `scholar-sidekick` package. Wraps the public REST API; needs Python ≥3.9 but no API key for the free tier. Use when the agent runs Python (a script, a notebook, a data pipeline) and the user wants to cite, export, verify, or audit references by DOI, PMID, PMCID, ISBN, arXiv ID, ISSN, ADS bibcode, or WHO IRIS URL — especially a bibliography longer than 25 entries, which this client chunks and paces automatically.

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 high-quality, actionable Python skill body with executable examples, error guidance, and a verification step. It is slightly long and fully inlined with no progressive file split, leaving minor room for trimming and externalization.

Suggestions

Move the full method/exception/export-format tables and the Pitfalls list into a reference file (e.g. references/API.md) referenced one level deep, keeping SKILL.md as a concise overview plus the core verify/audit/format examples.

Tighten the 'When to Use' and sibling-skills note into a few bullet lines; the routing detail partly duplicates the frontmatter description.

Add an explicit numbered validate→fix→retry checklist for the audit workflow (e.g. run audit → check report.complete → inspect report.errors → re-run failed chunks) to reach the top workflow-clarity anchor.

DimensionReasoningScore

Conciseness

Mostly lean and task-specific (API tables, executable snippets, no basic-concept padding), but the combined 'When to Use', sibling-skills note, and 'Pitfalls' sections add length that could be trimmed slightly. It fits the 'efficient; minor over-explanation' anchor rather than the fully-lean 5.

4 / 5

Actionability

Copy-paste-ready, executable code for verify(), audit_bibliography(), format(), export(), error handling, and context managers, plus tables of methods, verdicts, exceptions, and export formats covering the common cases.

5 / 5

Workflow Clarity

The Procedure is organized by task with clear code and a dedicated Verification section, plus a failed-chunk feedback loop (report.complete / report.errors / stop_on_error). It stops short of a rigid numbered validate→fix→retry checklist, fitting the 'clear sequence with most checkpoints' anchor.

4 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and easy navigation, but no bundle/reference files exist and all content is inlined, so it does not match the 'one-level-deep references, content appropriately split' anchor for a 5.

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.

A strong, third-person description that comprehensively states capabilities, includes an explicit 'Use when' trigger with natural keywords and synonyms, and is clearly distinguished from sibling skills. Voice and trigger guidance are correct; no over-claims or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Resolve scholarly identifiers ... into formatted citations', 'verify a claimed citation', 'audit a reference list ... for fabricated and retracted entries' — with specific identifier types and output formats, giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (resolve/verify/audit) and when ('Use when the agent runs Python ... and the user wants to cite, export, verify, or audit references by ...'), with concrete trigger phrases including the >25-entry heuristic.

5 / 5

Trigger Term Quality

Covers natural user terms and synonyms — 'cite', 'export', 'verify', 'audit references', 'DOI', 'PMID', 'ISBN', 'arXiv ID', 'bibliography', 'Python', 'notebook', 'data pipeline' — matching the comprehensive-synonym anchor.

5 / 5

Distinctiveness Conflict Risk

A clear Python-specific niche for scholarly citation resolution/verification/audit, with explicit sibling-skill routing (api/cli/mcp) that minimizes overlap and 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