biorxiv-database

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.

Quality

75%

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 ./backend/cli/skills/databases/biorxiv-database/SKILL.md

Quality

Content

61%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 skill body with concrete CLI and Python examples for every capability, and proper offloading of API detail to a real reference file. Its weaknesses are padding (test output block, generic pandas example), non-executable mixed shell/Python snippets, a missing validation loop for batch PDF downloads, and a test-suite reference to a file absent from the bundle.

Suggestions

Add a validation checkpoint to the batch PDF download workflow — e.g. check `result_count` / per-paper download success and retry failures — to lift workflow clarity above the batch-operation cap of 3.

Fix the non-executable snippets: move the Author Tracking and Custom Date Range examples into pure shell (loop via `for author in Smith Johnson; do python scripts/biorxiv_search.py --author "$author" ...; done`) and unify the import style (`from scripts.biorxiv_search import BioRxivSearcher`) so all examples are copy-paste ready.

Trim the ~30-line expected test-suite output block and the generic pandas 'Programmatic Integration' section to recover tokens, and either ship `tests/test_biorxiv_search.py` in the bundle or remove the Testing section's reference to it.

Dimension	Reasoning	Score
Conciseness	The bulk is efficient, concrete CLI/Python examples, but several sections pad it out: the ~30-line expected test-suite output with emoji, a generic pandas 'Programmatic Integration' example Claude could write unaided, and repetitive near-duplicate CLI invocations across sections. This fits anchor 3 ('mostly efficient, some unnecessary content that could be tightened') better than anchor 2, since no section explains concepts Claude doesn't know.	3 / 5
Actionability	Most commands are copy-paste ready (`python scripts/biorxiv_search.py --keywords "CRISPR" --start-date ... --output results.json`), but some blocks are not executable as written: the Author Tracking snippet embeds `python scripts/biorxiv_search.py --author "{author}"` inside a Python for-loop, 'Custom Date Range Logic' interleaves Python and shell in one block, and imports are inconsistent (`from biorxiv_search import ...` vs `from scripts.biorxiv_search import ...`). Concrete with minor gaps matches anchor 4, short of the fully-executable anchor 5.	4 / 5
Workflow Clarity	The Literature Review Workflow is clearly sequenced (broad search → review results → download selected papers), but the batch PDF download step has no validation or error-recovery loop. Per the rubric's cap, batch operations without validation steps cannot score above 3, and 'Handle errors gracefully' (check `result_count`) is only a prose hint, not a checkpoint in the workflow — so 3 rather than 4.	3 / 5
Progressive Disclosure	Good structure: detailed API material is correctly offloaded to a real, clearly-signaled one-level-deep reference (`references/api_reference.md`), and the real script lives in `scripts/biorxiv_search.py`. However, the Testing section points to `tests/test_biorxiv_search.py`, which does not exist in the bundle — a broken reference and a minor organization gap, holding this at anchor 4 rather than 5.	4 / 5
	Total	14 / 20 Passed

Description

88%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: third-person voice, concrete capability list, and an explicit 'Use this skill when...' clause with specific triggers. Its only weaknesses are a few missing natural synonyms/extensions and a broad 'literature reviews' trigger that overlaps with other literature-search skills.

Suggestions

Add common synonyms and extensions to the trigger list, e.g. "preprints, papers, .pdf files" so users asking to 'find bioRxiv papers' or 'download the preprint PDF' match naturally.

Scope the literature-review trigger to bioRxiv specifically (e.g. "conducting literature reviews of bioRxiv preprints") to reduce conflict risk with general literature-search skills.

Dimension	Reasoning	Score
Specificity	Quotes multiple concrete actions — "searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews" — covering the skill's full capability surface, matching the comprehensive-coverage anchor rather than the 'minor gaps' anchor at 4.	5 / 5
Completeness	Explicitly answers what ("Efficient database search tool for bioRxiv preprint server... retrieving paper metadata, downloading PDFs") and when ("Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories..."), with concrete trigger phrases. This matches anchor 5; anchor 4 would require the 'when' to be less explicit or specific, which it is not.	5 / 5
Trigger Term Quality	Natural terms users would say are present ("bioRxiv", "preprint", "life sciences", "PDFs", "literature reviews", "metadata"), but common variations are missing — no "papers", "scientific articles", or file extensions like ".pdf". Good coverage with a few natural terms missing fits anchor 4; it is above 'some relevant keywords' (3) but short of the synonym/extension completeness of anchor 5.	4 / 5
Distinctiveness Conflict Risk	"bioRxiv preprint server" and "life sciences preprints" carve a clear niche, but the trigger "conducting literature reviews" is broad and could fire for literature searches on PubMed, arXiv, or Google Scholar. Mostly distinct with minor overlap risk against closely related literature-search skills fits anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/biorxiv-database/SKILL.md
Commit: 4082a2e

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.