CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/semantic-scholar/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-structured and highly actionable for an API-search skill, but token efficiency suffers from a duplicated resolver block and the batch workflow lacks an explicit results-validation checkpoint. Progressive disclosure is good with clearly signaled one-level references.

Suggestions

Factor the repeated git/ARIS canonical-resolver bash block (Step 2 and Step 7) into a single shared snippet or reference to remove the duplication and save tokens.

Add an explicit validation checkpoint after the search call (e.g., check for HTTP 429 / empty results / malformed JSON, then retry or fall back) before presenting results, to satisfy batch-operation workflow clarity.

Collapse the Key Rules filter guidance into the existing Constants/overrides section to avoid restating the same --fields-of-study / --publication-types advice twice.

DimensionReasoningScore

Conciseness

Mostly efficient and concrete, but the git/ARIS resolver bash block is duplicated verbatim in Step 2 and Step 7, and the Key Rules section restates filter guidance already covered in Constants/overrides.

3 / 5

Actionability

Provides copy-paste-ready search, search-bulk, and paper commands with concrete flags and ID patterns; the wiki-ingest loop in Step 7 is pseudocode embedded in a bash fence, a minor gap.

4 / 5

Workflow Clarity

Eight steps are clearly sequenced with conditional routing, but this batch-returning skill has no explicit validate-results checkpoint before presentation; the batch-operation cap applies despite rate-limit and fallback handling.

3 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level references (integration-contract.md §2, wiki-helper-resolution.md); some inlined material (filter-combo table, duplicated resolver) could be referenced rather than repeated.

4 / 5

Total

14

/

20

Passed

Description

95%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: concrete capabilities, explicit what/when structure, and five natural trigger phrases. The only weakness is that specificity stops short of mentioning identifier lookup and bulk-search modes that the body supports.

DimensionReasoningScore

Specificity

Names the domain plus several concrete capabilities — "Search published venue papers", "citation counts, venue metadata, and TLDR" — but omits fetch-by-ID and bulk-sort actions present in the body, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both what ("Search published venue papers ... via Semantic Scholar API") and when ("Use when user says ... or wants published literature beyond arXiv preprints") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Five quoted natural phrases users would actually say ("search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search") give comprehensive synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche as the published-venue counterpart to /arxiv, explicitly contrasted via "Complements /arxiv (preprints)", with distinct triggers minimizing conflict risk.

5 / 5

Total

19

/

20

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.