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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands and a clear 8-step workflow, but loses points for duplicated resolution logic, a non-executable wiki-ingest loop, and missing validation checkpoints on the batch operation. Splitting detailed resolution/filter reference material into a bundle file would improve organization.

Suggestions

Make the Step 7 wiki-ingest loop executable shell (the `for each paper in results:` pseudo-code will not run) or move it to a helper script, and add an explicit validate/skip checkpoint before ingest.

Factor the repeated canonical-chain resolution logic (S2_FETCHER and WIKI_SCRIPT) into a single shared snippet or reference file instead of inlining it in both Step 2 and Step 7.

Move the filter-combo table and detailed API flag reference into a references/ file so the main SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept-explanation padding, but the S2_FETCHER resolution block and the wiki-script resolution block repeat the same canonical-chain pattern inline, and prose like "this is the unique value of this skill" could be trimmed.	2 / 3
Actionability	Provides fully executable bash commands (e.g. `python3 "$S2_FETCHER" search "QUERY" --max MAX_RESULTS --fields-of-study ...`), concrete flag tables, specific paper-ID formats, and copy-paste-ready output templates.	3 / 3
Workflow Clarity	Eight steps are clearly sequenced, but the batch wiki-ingest in Step 7 uses non-executable pseudo-shell and lacks an explicit validate-before-proceeding checkpoint, capping clarity at 2 for batch operations.	2 / 3
Progressive Disclosure	References to ../shared-references files are one-level-deep and clearly signaled, but no bundle reference files exist in the skill, and substantial filter-combo and resolution detail is inline rather than split into a separate reference file.	2 / 3
	Total	9 / 12 Passed

Description

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.

The description is specific, trigger-rich, and clearly distinguishes the skill from /arxiv while answering both what and when. It uses third-person/imperative voice and avoids vague fluff. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "Search published venue papers", "citation counts, venue metadata, and TLDR" — matching the anchor for listing multiple specific actions rather than a single vague domain mention.	3 / 3
Completeness	Explicitly states what it does ("Search published venue papers... via Semantic Scholar API") and when to use it ("Use when user says..."), answering both what and when with explicit triggers.	3 / 3
Trigger Term Quality	Provides natural phrases users would say — "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search" — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Framed as the "published venue counterpart to /arxiv" complementing preprints, giving it a clear niche with distinct triggers unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 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
Commit: fe5963c

Reviewed: about 17 hours 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.