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.
76
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skills-codex/deepxiv/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is structurally sound with a clear 'Use when' clause and a distinctive niche around DeepXiv. However, it relies on somewhat jargon-like phrases ('layered paper access', 'DeepXiv-backed literature retrieval') that users wouldn't naturally say, and could benefit from more concrete action verbs and common user-facing trigger terms like 'research papers', 'arxiv', or 'preprints'.
Suggestions
Replace jargon like 'layered paper access' and 'DeepXiv-backed literature retrieval' with natural user terms such as 'find research papers', 'browse arxiv preprints', or 'look up scientific articles'.
Add more concrete actions such as 'retrieve abstracts', 'read specific sections', 'browse by topic', or 'find citations' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (academic papers via DeepXiv) and some actions ('search', 'progressively read', 'section-level reading', 'trending papers'), but the actions are somewhat vague—'layered paper access' and 'literature retrieval' are not concrete operations like 'extract abstracts' or 'summarize findings'. | 2 / 3 |
Completeness | Clearly answers both 'what' (search and progressively read open-access academic papers through DeepXiv) and 'when' (explicit 'Use when' clause covering layered paper access, section-level reading, trending papers, and DeepXiv-backed literature retrieval). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'academic papers', 'trending papers', 'section-level reading', and 'DeepXiv', but misses common user terms like 'research papers', 'arxiv', 'preprints', 'scientific articles', 'paper search', or 'read paper'. 'Layered paper access' is not a phrase users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'DeepXiv' as a specific platform, combined with distinctive features like 'progressive reading' and 'section-level reading', creates a clear niche that is unlikely to conflict with generic search or document skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid actionable guidance with concrete, executable commands for both the adapter and fallback paths, and a clear progressive reading model. Its main weaknesses are the lack of error handling/validation steps in the workflow and moderate verbosity in the adapter-location logic and positioning table. The referenced integration contract and bundle files are absent, weakening the progressive disclosure story.
Suggestions
Add error handling and validation checkpoints: what to do when deepxiv-sdk is not installed, when a paper ID is not found, or when the adapter script is missing — currently Step 3 just silently does nothing if SCRIPT is empty.
Move the adapter-location bash logic to a separate referenced script or utility file to reduce inline verbosity and improve progressive disclosure.
Add a brief example of expected output (e.g., a sample search result table or brief summary format) so Claude knows exactly what to present in Step 4.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some unnecessary elements like the role/positioning comparison table and verbose adapter-location logic. The constants section and some explanatory text could be tightened, though most content is functional. | 2 / 3 |
Actionability | Provides fully executable bash commands for both the adapter script and fallback CLI, with concrete argument patterns and clear override syntax examples. The commands are copy-paste ready with specific flags and formats. | 3 / 3 |
Workflow Clarity | The six-step workflow is clearly sequenced with a well-defined progressive reading escalation (search → brief → head → section). However, there are no validation checkpoints or error-handling feedback loops — no guidance on what to do if commands fail, if the SDK isn't installed, or if results are empty. | 2 / 3 |
Progressive Disclosure | References the integration contract file and mentions other skills (/arxiv, /semantic-scholar), but no bundle files are provided to support these references. The content is somewhat monolithic with the full adapter-location logic and all command variants inline rather than in a separate reference file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
2028ac4
- 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.