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

—

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.

A highly actionable, well-sequenced workflow with concrete executable commands and clear error-recovery checkpoints. Its main weaknesses are conciseness (tangential wiki-ingest and integration material) and progressive disclosure (substantial inline content that could be externalized).

Suggestions

Extract the Step 6 research-wiki ingest bash block and the "Integration with Other Skills" section into a reference file (e.g., references/integration.md), keeping SKILL.md to a one-line pointer, to improve both conciseness and progressive disclosure.

Tighten the WIKI_SCRIPT resolution fallback chain in Step 6 — the three nested `[ -f ] ||` checks add verbosity; a single documented resolution or a short helper script would reduce tokens without losing the safety net.

The description could list one or two more distinct concrete actions (e.g., "extract equations/proofs from LaTeX source") to lift specificity from 2 to 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no explaining of curl or LaTeX), but the Step 6 wiki-ingest bash block with multi-fallback script resolution and the "Integration with Other Skills" section add tangential length that could be tightened, keeping it at level 2 rather than the every-token-earns-its-place bar of 3.	2 / 3
Actionability	It provides fully executable curl commands with exact flags and URLs, concrete argument-parsing formats, a copy-paste bash block, and a specific result template, matching the anchor-3 copy-paste-ready example.	3 / 3
Workflow Clarity	Steps 1–6 are clearly sequenced with explicit validation checkpoints (stop if the overview answers, HTTP 4xx cascades to the next tier, 429 retry once), and the operation is read-only so the destructive/batch cap does not apply; not 2 because checkpoints and feedback loops are explicit rather than implicit.	3 / 3
Progressive Disclosure	Sections are well organized and the integration-contract.md reference is one level deep and clearly signaled, but the large inline Step 6 wiki-ingest block and the integration section are inline content that could be split into a reference file, matching the anchor-2 "content that should be separate is inline" rather than the clean split of level 3.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 that clearly states both purpose and explicit triggers, with a useful negative boundary for distinctiveness. Its only weakness is specificity, where the action list is essentially one capability with a fallback rather than multiple distinct actions.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete capabilities ("single-paper lookup", "LLM-optimized summaries", "tiered source fallback"), but these describe one primary action with a fallback rather than the multiple distinct actions of the anchor-3 example, so it sits at level 2 not 3.	2 / 3
Completeness	It explicitly answers both what ("Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback") and when ("Use when user says...") plus a negative trigger, matching the anchor-3 both-what-and-when pattern.	3 / 3
Trigger Term Quality	It includes natural phrases users would actually say ("explain this paper", "summarize paper", pasting an arXiv/AlphaXiv URL, bare arXiv ID), giving good coverage that matches the anchor-3 example; not 2 because common variations are present rather than missing.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (AlphaXiv single-paper summaries) with distinct triggers and an explicit negative boundary ("not for broad literature search"), making conflict with sibling paper skills unlikely; level 2 would lack that boundary.	3 / 3
	Total	11 / 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 — 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
Commit: 82076e5

Reviewed: 5 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.