Tessl • The management layer for AI agent skills

SkillPublic

aris-semantic-scholar

Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /aris-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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%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.

A highly actionable, well-sequenced workflow with unusually complete error handling for rate limits, missing scripts, and null API fields. The main improvements are tightening the duplicated directive documentation and making the inline-Python fallback actually executable.

Suggestions

Deduplicate the directive documentation: the override list in the Constants section (max/type/min-citations/year/fields/sort) repeats Step 1's parsing table — keep one canonical listing and reference it.

Include the actual inline-Python fallback snippet (urllib request against api.semanticscholar.org) instead of only describing it, so the search command works even when semantic_scholar_fetch.py is absent.

Consider moving the script-locator bash block and the presentation templates into a small reference file to slim the main SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely operational (commands, flags, filter combos, error-handling rules) with no explanations of concepts Claude already knows, but the directive list is duplicated between the Constants overrides block and Step 1, and the ~30-line script-locator block could be tightened.	4 / 5
Actionability	Provides concrete executable commands (e.g. `python3 "$SCRIPT" search "QUERY" --max MAX_RESULTS --fields-of-study ...`), an executable locator script, and exact flag mappings, but the inline-Python fallback is only described ("fall back to inline Python using urllib against https://api.semanticscholar.org/...") rather than given as copy-paste code.	4 / 5
Workflow Clarity	Seven clearly sequenced steps with explicit routing (identifier patterns skip search and go directly to Step 3) and thorough error-recovery loops: HTTP 429 wait-and-retry, missing-script fallback, null TLDR falling back to the abstract's first sentence, empty openAccessPdf falling back to the DOI link, and unreachable-API alternatives. Read-only search, so no destructive-operation cap applies.	5 / 5
Progressive Disclosure	Well-organized single-file skill (Role & Positioning, Constants, Workflow, Key Rules) with the external helper-script dependency clearly signaled and a fallback path; presentation templates and the locator logic are inlined, but they are operational rather than reference material, leaving only minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

87%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: third-person voice, concrete what-and-when with explicit trigger phrases, and clear positioning against the sibling arXiv skill. Minor room to broaden the action list (paper-ID/DOI lookup) and add a few more trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the source ("via Semantic Scholar API"), the content type ("published venue papers (IEEE, ACM, Springer, etc.)"), and the distinguishing data ("citation counts, venue metadata, and TLDR"), but the action list is effectively a single search action — the body's fetch-by-ID/DOI capability is not reflected, so coverage has minor gaps.	4 / 5
Completeness	Explicitly answers both what ("Search published venue papers ... via Semantic Scholar API ... with citation counts, venue metadata, and TLDR") and when ("Use when user says ...") with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Includes natural quoted phrases users would say — "search semantic scholar", "find IEEE papers", "find journal papers", "citation search" — plus the "published literature beyond arXiv preprints" use case, but misses common variations like "conference papers", "ACM papers", or "scholar search".	4 / 5
Distinctiveness Conflict Risk	"Complements /aris-arxiv (preprints)" explicitly carves the venue-published niche, and triggers like "find IEEE papers" and "search semantic scholar" are highly distinctive; the only mild overlap ("published literature beyond arXiv preprints") is explicitly framed as complementary, so conflict risk is minimal.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-semantic-scholar/SKILL.md
Revision: 3456bb4

Reviewed: 5 days ago

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.

aris-semantic-scholar

Table of Contents

Is this your skill?