deepxiv

Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/deepxiv/SKILL.md

Quality

Content

73%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 highly actionable skill body with executable commands and fallbacks for every operation and a clear escalation progression. The main weaknesses are workflow validation gaps around batch ingest/error recovery and some verbosity in the repeated adapter-resolution shell blocks.

Suggestions

Add an explicit validate/retry checkpoint in Step 6's wiki ingest loop (e.g., check the helper's exit code per ingest and report failures before backfill), since batch ingestion is a batch operation that currently caps workflow_clarity.

Factor the duplicated ARIS_REPO / adapter-resolution shell preamble (Step 2 and Step 6) into a single shared snippet or a referenced helper script to reduce inline verbosity and drift between the two copies.

Clarify the auto-demotion behavior: the Step 2 comment admits a resolved-but-non-functional adapter is not demoted — add an explicit smoke-test branch that falls back to the raw CLI on adapter failure so the workflow has a real error-recovery loop.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient — concrete commands, a positioning table, and override examples with little concept-over-explanation — but the adapter-resolution shell block (Step 2 / Step 6) is long and somewhat padded with redundant comments and fallback-chain detail that could be trimmed; above midpoint but not fully lean.	4 / 5
Actionability	Provides copy-paste-ready, executable commands for every operation (search, brief, head, section, trending, web search, Semantic Scholar) with both primary-adapter and raw-CLI fallbacks, plus explicit install and override syntax; concrete examples cover the common cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced (parse args, locate adapter, execute, present, escalate depth, update wiki), but batch/destructive-adjacent operations (ingesting multiple papers, the wiki-sync loop) lack explicit validate-then-retry checkpoints and error recovery loops, and the caveat that a resolved-but-broken adapter is not auto-demoted is a validation gap.	3 / 5
Progressive Disclosure	Good overall structure with a positioning table, constants, override cheatsheet, and step-by-step workflow; external details are pushed to one-level-deep shared-references (integration-contract.md, wiki-helper-resolution.md) with clear links. No local references/scripts/assets bundle exists, so some bulk (the duplicated adapter-resolution block) lives inline where a separate helper could carry it, keeping this at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

81%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, well-formed description that clearly states what the skill does and when to invoke it with concrete, natural trigger phrases. It could push distinctiveness higher by naming its progressive-reading niche even more sharply relative to its /arxiv and /alphaxiv siblings.

Dimension	Reasoning	Score
Specificity	Names the domain ('open-access academic papers through DeepXiv') and several concrete actions ('Search', 'progressively read', 'layered paper access', 'section-level reading', 'trending papers'), which is several specific actions with only minor gaps in coverage; not a comprehensive 5-level enumeration of all operations but clearly above the 3-level two-action anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('Search and progressively read open-access academic papers through DeepXiv') and 'when' ('Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ('trending papers', 'section-level reading', 'literature retrieval', 'academic papers') with good coverage, though it misses a few common synonyms/extensions (e.g. 'arXiv', 'abstract', 'summaries'); not as exhaustive as the 5-anchor list.	4 / 5
Distinctiveness Conflict Risk	The DeepXiv-specific naming and 'progressively read / section-level reading' niche distinguish it from generic paper skills, but there is some overlap risk with sibling skills like /arxiv, /semantic-scholar, and /alphaxiv (acknowledged in the body), so it is mostly distinct rather than minimal-conflict.	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: 4 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/deepxiv/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.