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

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

81%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-engineered, mostly copy-paste-ready skill: tiered fallback logic with explicit error handling and stop conditions is exemplary, and the workflow is easy to follow end to end. Remaining gaps are minor — no executable command for the src-tier archive extraction and slight redundancy in the positioning/integration prose.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean constants, curl commands, and a tight tiered workflow, with only minor over-explanation ("This returns a structured, LLM-optimized report designed for machine consumption", the "Complementary, not competing" rule restating the positioning table), fitting anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	Concrete executable curl commands with UA and timeouts, exact URL patterns, enumerated accepted input formats, and a copy-paste bash block for wiki ingest; the src tier describes archive extraction ("prefer cross-platform approaches (e.g., Python stdlib)") without an actual command, a minor gap that keeps it below the fully-executable anchor 5.	4 / 5
Workflow Clarity	Steps 1-6 are clearly sequenced with explicit escalation checkpoints (HTTP 4xx or empty content advances to the next tier), a stop-early rule, a 429 wait-5s retry-once loop with a fallback suggestion, and a WARN-and-backfill error path in the ingest block — matching the explicit-validation-and-feedback-loops anchor. The skill is not destructive or batch, so no cap applies.	5 / 5
Progressive Disclosure	No bundle files exist; the body is well-sectioned (Constants, Workflow, Key Rules, Integration) with one clearly signaled one-level-deep reference (../shared-references/integration-contract.md, absent from this evaluation copy), but the ~190-line body keeps the full bash ingest block and answer template inline, which fits the good-structure/minor-gaps anchor 4 rather than a cleanly split 5.	4 / 5
	Total	17 / 20 Passed

Description

83%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, concrete, with explicit trigger phrases, accepted input formats, and a negative boundary. The what/when pair is fully explicit; only minor trigger-synonym coverage and slight overlap risk with sibling paper skills keep it from top marks on two dimensions.

Dimension	Reasoning	Score
Specificity	"Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback" names the domain and several concrete actions (lookup, summary generation, tiered fallback), but these describe one lookup task's mechanism rather than a comprehensive list of distinct capabilities, placing it just below anchor 5.	4 / 5
Completeness	Explicitly answers both what ("Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback") and when ("Use when user says 'explain this paper', 'summarize paper', pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural quoted phrases users would say ("explain this paper", "summarize paper") plus URL and bare-arXiv-ID input forms, but misses common variants like "read this paper" or "what is this paper about", so it falls between the good-coverage (4) and comprehensive (5) anchors.	4 / 5
Distinctiveness Conflict Risk	The niche is clear (AlphaXiv/arXiv single-paper lookup) with an explicit negative boundary ("not for broad literature search"), but the generic trigger "summarize paper" without a URL could also fire closely related paper-reading skills, giving minor overlap risk characteristic of anchor 4 rather than 5.	4 / 5
	Total	17 / 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: 2132036

Reviewed: 3 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.