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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

75%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, actionable skill body with a clear tiered workflow and explicit gating. Slight gains available by trimming explanatory prose, adding an exact archive-extraction command, and making tier-success validation explicit.

Suggestions

Trim explanatory prose that Claude already knows (e.g., the bot-detection rationale and the 'saves significant tokens' note) to improve conciseness.

In Step 4, give a concrete command or short script for downloading and extracting the .tar.gz LaTeX source instead of a high-level 'download, extract, and list' instruction.

Add an explicit verification/decision checkpoint between tiers (e.g., a concrete check that the overview actually answered the question) to strengthen workflow_clarity.

Dimension	Reasoning	Score
Conciseness	Largely efficient with executable curl blocks and a useful positioning table, but includes some explain-y prose (e.g., the bot-detection rationale and the 'saves significant tokens' integration note) that could be trimmed.	4 / 5
Actionability	Provides concrete, copy-paste curl commands, a presentation template, and a runnable wiki-ingest bash block; minor gap is Step 4's source-archive handling ('download, extract, list .tex files') which stays high-level rather than giving an exact command.	4 / 5
Workflow Clarity	Clear 6-step sequenced workflow with explicit tiered fallback and a MUST gate for Step 6, plus a 429 rate-limit retry; validation checkpoints are mostly implicit (success = 'answers the question') rather than explicit verify commands, keeping it below 5.	4 / 5
Progressive Disclosure	Well-organized into labeled sections with one clearly signaled one-level reference (integration-contract.md); no bundle files exist, so structure carries the score, though some inline integration/follow-up content could arguably live elsewhere.	4 / 5
	Total	16 / 20 Passed

Description

95%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, specific description that clearly states capabilities, triggers, and boundaries, distinguishing it from sibling research skills. Only minor room to enumerate the concrete actions more fully.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ('single-paper lookup', 'LLM-optimized summaries', 'tiered source fallback'); not a 5 because the actions are summarized rather than enumerated in full.	4 / 5
Completeness	Explicitly answers both 'what' (quick single-paper lookup with tiered fallback) and 'when' (Use when user says..., pastes URL, provides bare ID), with a concrete negative boundary ('not for broad literature search').	5 / 5
Trigger Term Quality	Includes natural user phrases ('explain this paper', 'summarize paper') plus URL and bare arXiv ID triggers, covering synonyms and the common invocation forms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (AlphaXiv single-paper LLM summaries) with an explicit 'not for' clause that separates it from /arxiv, /deepxiv, and /research-lit, minimizing conflict risk.	5 / 5
	Total	19 / 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
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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/alphaxiv/SKILL.md
Commit: f4f20f9

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.