alphaxiv

Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

This is a well-structured, highly actionable skill with a clear tiered workflow and explicit validation/escalation logic. Its main weakness is token efficiency — the role positioning table, integration guidance, and the lengthy wiki ingest block inflate the file beyond what's strictly necessary for Claude to execute the task. The progressive disclosure could be improved by moving the wiki ingest details and cross-skill integration into separate reference files.

Suggestions

Move the 'Integration with Other Skills' section and the detailed wiki ingest bash block into a separate reference file (e.g., INTEGRATION.md) to reduce the main skill's token footprint.

Remove or significantly condense the Role & Positioning table — Claude doesn't need a comparison matrix of sibling skills to execute this one; a single sentence noting when NOT to use this skill suffices.

Dimension	Reasoning	Score
Conciseness	The skill includes useful content but has unnecessary verbosity: the role/positioning table explaining other skills, the detailed integration section at the bottom, and the lengthy research wiki ingest bash block add significant token overhead. The UA explanation and some commentary could be trimmed.	2 / 3
Actionability	The skill provides fully executable curl commands, concrete bash scripts, specific URL templates, clear input format examples, and a copy-paste-ready output template. Every step has concrete, actionable guidance.	3 / 3
Workflow Clarity	The tiered fallback workflow is clearly sequenced (Steps 1-6) with explicit decision points for when to escalate tiers, validation via HTTP status codes, rate-limit retry logic, and a mandatory Step 6 with clear instructions not to skip it. The feedback loop for 429 errors is explicit.	3 / 3
Progressive Disclosure	The skill references external files like `integration-contract.md` and other skills appropriately, but the SKILL.md itself is quite long with inline content (the full wiki ingest script, the integration section) that could be split into separate reference files. No bundle files are provided to support offloading.	2 / 3
	Total	10 / 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.

This is an excellent skill description that clearly communicates its specific purpose (single-paper lookup via AlphaXiv), includes natural trigger terms users would say, provides explicit 'Use when' guidance with multiple trigger scenarios, and distinguishes itself from related skills (broad literature search). The negative boundary ('not for broad literature search') is a particularly effective touch for disambiguation.

Dimension	Reasoning	Score
Specificity	Lists concrete actions: 'single-paper lookup', 'LLM-optimized summaries', 'tiered source fallback'. Also specifies what it does NOT do ('not for broad literature search'), which adds clarity.	3 / 3
Completeness	Clearly answers both 'what' (quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback) and 'when' (explicit 'Use when' clause with multiple trigger scenarios plus a negative boundary condition).	3 / 3
Trigger Term Quality	Includes highly natural trigger terms users would actually say: 'explain this paper', 'summarize paper', 'arXiv URL', 'AlphaXiv URL', 'arXiv ID'. These cover common user phrasings well.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with specific niche (AlphaXiv, arXiv, single-paper summaries) and explicitly differentiates from broad literature search skills. The mention of specific platforms and the negative scope boundary minimize conflict risk.	3 / 3
	Total	12 / 12 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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: ccc7999

Reviewed: about 3 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.