daily-paper-generator

Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.

Quality

82%

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

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and actionable, with an executable script command and a clear narrowing funnel, but redundant sections, a missing validation feedback loop, and a dangling reference to a non-existent example file limit several dimensions.

Suggestions

Remove the redundant "Core workflow" summary list (or the duplicated "Additional Resources" reference list) — the detailed "## Workflow" and "Quick Reference" table already cover this content, saving tokens.

Add an explicit validation/feedback step for the batch search, e.g., "If fewer than 10 relevant results, widen --months or refine the query and re-run," to introduce an error-recovery loop.

Fix or remove the dangling reference to `example/daily paper example.md` — the file does not exist in the bundle, which breaks navigation and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The "Core workflow" 1–7 list duplicates the detailed "## Workflow" Step 1–7 section, and the reference files appear in both a "Quick Reference" table and an "Additional Resources" list; mostly efficient but not every token earns its place. It is not a 3 because of this clear redundancy.	2 / 3
Actionability	Provides a fully executable search command with concrete flags, a specific Top 10 → Top 3 → Top 1 narrowing rule, an explicit output-naming format, and pointed references to scoring/style files; the core step is copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	The 7-step sequence and required output trace are clearly laid out with screening gates, but there is no validation/error-recovery feedback loop (e.g., re-search when results are too few), which caps batch-operation workflow clarity at 2 per the guidelines. It is not a 3 because explicit feedback-loop checkpoints are missing.	2 / 3
Progressive Disclosure	The real reference files are well-signaled and one level deep, but the body references `example/daily paper example.md` which does not exist in the bundle, and references are listed redundantly across two sections. It is not a 3 because the broken/dangling reference is a navigation defect.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 well-constructed description with explicit trigger guidance, concrete actions, named sources, and a clear niche. It cleanly answers both what the skill does and when Claude should use it, closely matching the good examples.

Dimension	Reasoning	Score
Specificity	Phrases like "generate daily paper digests" and "produces structured Chinese/English summaries" name multiple concrete actions, matching the score-3 anchor that lists several specific actions; it is above 2 because actions are concrete and comprehensive rather than partial.	3 / 3
Completeness	An explicit "Use when the user asks to generate daily paper digests..." trigger answers when, while "supports both arXiv and bioRxiv... produces structured Chinese/English summaries" answers what, satisfying the score-3 requirement for both with an explicit trigger.	3 / 3
Trigger Term Quality	Natural terms a user would say — "daily paper digests", "arXiv", "bioRxiv", "Chinese/English summaries" — are present with good coverage; not a 2 because common source names and the core task phrasing are all included.	3 / 3
Distinctiveness Conflict Risk	The arXiv/bioRxiv daily-digest-with-bilingual-summaries niche is specific with distinct triggers unlikely to overlap with general document or paper skills, matching the clear-niche score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/daily-paper-generator/SKILL.md
Commit: 2f7766f

Reviewed: about 14 hours 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.