semantic-scholar
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines its scope, provides abundant natural trigger terms, and explicitly distinguishes itself from a related skill (/arxiv). It uses proper third-person voice, answers both 'what' and 'when' comprehensively, and includes enough specificity for accurate skill selection among many options.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: searching published venue papers, providing citation counts, venue metadata, and TLDR summaries. Also specifies the API used (Semantic Scholar) and the publishers covered (IEEE, ACM, Springer). | 3 / 3 |
Completeness | Clearly answers both 'what' (search published venue papers via Semantic Scholar API with citation counts, venue metadata, TLDR) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also clarifies its relationship to a complementary /arxiv skill. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'search semantic scholar', 'find IEEE papers', 'find journal papers', 'venue papers', 'citation search', 'published literature beyond arXiv preprints'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by explicitly differentiating itself from the /arxiv skill (preprints vs. published venue papers), naming the specific API (Semantic Scholar), and targeting a clear niche of published literature with citation metadata. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, highly actionable skill with excellent workflow clarity and concrete executable commands throughout. Its main weakness is length — at ~200 lines with everything inline, it could benefit from splitting reference material (filter combos, output templates) into separate files. The conciseness could also be improved by trimming the positioning table and some explanatory notes that Claude would already understand.
Suggestions
Move the recommended filter combos table and detailed output format templates into a separate reference file (e.g., REFERENCE.md) to reduce inline length and improve progressive disclosure.
Trim the Role & Positioning table — a single sentence like 'Complements /arxiv (preprints) with published venue papers, citation counts, and TLDR' would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and well-structured, but includes some unnecessary content like the role/positioning table comparing to /arxiv, and the extensive recommended filter combos table. Some sections could be tightened, though most content earns its place given the complexity of the API interactions. | 2 / 3 |
Actionability | Provides fully executable bash commands and concrete examples for every step — search, bulk search, paper fetch, and wiki ingestion. Paper ID formats, flag mappings, and fallback behaviors are all explicitly specified with copy-paste ready commands. | 3 / 3 |
Workflow Clarity | Clear 8-step sequential workflow with explicit validation/de-duplication (Step 4), conditional branching (ID detection skips to Step 3, bulk vs standard search), error handling (HTTP 429 retry, missing script fallback), and a well-defined output format. The wiki integration step includes proper conditional logic. | 3 / 3 |
Progressive Disclosure | The skill is quite long (~200 lines) with all content inline. The recommended filter combos, detailed output format templates, and wiki integration details could be split into separate reference files. There is one external reference to integration-contract.md, but the bulk of content that could be separated remains inline. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 |
Total | 9 / 11 Passed | |
- Commit
700fbe2
- 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.