CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

The body is an efficient, actionable, well-sequenced overview with executable commands and a clear depth-escalation workflow. It scores a consistent 4 across dimensions, held back by minor redundancy, placeholder commands, an optional validation step, and the absence of an in-bundle reference split.

Suggestions

Make the Step 2 smoke test mandatory and add a fail-and-fallback loop so a resolved-but-broken adapter auto-demotes to the raw CLI.

Tighten the dual command listings by showing the adapter form once and documenting the raw-CLI fallback as a single mapped table.

Provide a concrete argument-parsing snippet (e.g. a small case/regex block) rather than only a bullet list of flags.

DimensionReasoningScore

Conciseness

Mostly lean — no concept-explanation padding, uses tables and code blocks efficiently — but the dual adapter/raw-CLI command listings for seven operations and the four-skill positioning table add some redundancy.

4 / 5

Actionability

Provides concrete, executable commands (pip install, the bash adapter-resolution block, python3 fetcher calls, deepxiv CLI fallbacks with exact flags), but placeholders like QUERY/ARXIV_ID/SECTION_NAME require substitution and argument parsing has no concrete implementation.

4 / 5

Workflow Clarity

A clear six-step sequence (Parse → Locate Adapter → Execute → Present → Escalate Depth → Update Wiki) with a resolve-or-fallback checkpoint in Step 2, but the smoke test is explicitly 'optional' and non-functional adapters are not auto-demoted, leaving a minor validation gap.

4 / 5

Progressive Disclosure

Well-organized into clear sections with a one-level-deep, well-signaled reference to shared-references/integration-contract.md (linked with section anchors), though no internal bundle files exist to split content further and the referenced shared file is not part of this skill's bundle.

4 / 5

Total

16

/

20

Passed

Description

88%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 that clearly states capability and provides an explicit 'Use when' trigger with multiple concrete phrases. It is held back only by minor overlap with sibling literature skills and a few missing natural synonyms.

Suggestions

Add 'arXiv' or 'paper ID' to the trigger phrase list, since users often reference papers by arXiv ID.

Sharpen distinctiveness by contrasting the progressive-reading angle against flat full-text search in the description itself.

DimensionReasoningScore

Specificity

Names the domain plus multiple concrete actions — 'Search and progressively read', 'section-level reading', 'trending papers', 'literature retrieval' — giving comprehensive coverage rather than just 1-2 actions.

5 / 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

Strong natural keywords ('academic papers', 'trending papers', 'section-level reading', 'literature retrieval') with synonyms, but a few common terms a user might say ('arXiv', 'abstract', 'paper summary') are absent.

4 / 5

Distinctiveness Conflict Risk

The named source 'DeepXiv' and 'section-level reading' niche make it mostly distinct, but 'academic papers'/'literature retrieval' overlap with closely related search skills (arxiv, semantic-scholar) the body itself enumerates.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Reviewed

Table of Contents

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.