paper-refbib-stub

Convert normalized multi-search-engine results to minimal BibTeX, preserving real DOI, author, publication year, arXiv ID, source URL, and provenance metadata when available. Unknown years are omitted and duplicate DOI records collapse to one entry.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./src/opensquilla/skills/bundled/paper-refbib-stub/SKILL.md

Quality

Content

78%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 tight, well-organized contract description for a single-purpose converter skill that assumes competence and avoids padding, but it is descriptive rather than executable and lacks an explicit output-validation step.

Suggestions

Add a short executable example showing the expected stdin JSON shape and resulting BibTeX output to lift actionability.

Note an explicit validation/verification step (e.g., that emitted BibTeX parses cleanly or that citation keys are unique) to strengthen workflow clarity for this batch-record transform.

Dimension	Reasoning	Score
Conciseness	Three lean paragraphs with no padding and no explanation of concepts Claude already knows; every sentence conveys a specific behavior (field handling, dedup, sanitization), assuming Claude's competence.	5 / 5
Actionability	Concrete behavioral specs (which fields are consumed, how corporate authors are braced, how DOIs are deduped) but the body is descriptive prose about the script rather than executable code or direct step-by-step instructions.	3 / 5
Workflow Clarity	The single action is unambiguous — 'Reads a multi-search-engine JSON document on stdin and emits a BibTeX file of @misc{} entries keyed ref1, ref2' — with a clear input/output contract, though no explicit output-validation checkpoint is described.	4 / 5
Progressive Disclosure	Under 50 lines, no need for external reference files (references/ and assets/ are empty; the bundle script is the implementation), and the body is well-organized into focused intro/field-handling/sanitization paragraphs.	5 / 5
	Total	17 / 20 Passed

Description

75%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 specific, well-scoped description that clearly states what the skill does and is highly distinct, but it lacks an explicit 'when to use' trigger clause and misses a few natural synonyms (references/citations/bibliography).

Suggestions

Add an explicit 'Use when...' clause naming trigger situations (e.g., 'Use when generating a references.bib from search-engine output or when the user asks for BibTeX/citation entries').

Include broader natural terms like 'references', 'citations', or 'bibliography' alongside 'BibTeX' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete behaviors — 'Convert normalized multi-search-engine results to minimal BibTeX, preserving real DOI, author, publication year, arXiv ID, source URL, and provenance metadata', 'Unknown years are omitted', 'duplicate DOI records collapse' — with comprehensive coverage of the conversion contract.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural domain terms a user would say ('BibTeX', 'DOI', 'arXiv ID', 'publication year') but omits common synonyms like 'references', 'citations', or 'bibliography' that a user might naturally invoke.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (multi-search-engine results → BibTeX with DOI/arXiv handling and dedup) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/paper-refbib-stub/SKILL.md
Commit: 94ac35e

Reviewed: 4 days 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.