Name: google-scholar-search
Rating: 72 (1 reviews)
Author: pantheon-org

google-scholar-search

Search Google Scholar for academic papers and author profiles. Use when discovering papers to triage — by keyword, author, or year range. Returns titles, authors, abstracts, and links. Triggers: search papers, find papers, google scholar, search scholar, find author, author profile, literature search, paper discovery, search academic literature.

Quality

89%

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

The canonical home for this skill is google-scholar-search in pantheon-org/tekhne

Quality

Content

88%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 well-structured, highly actionable body: executable commands for every subcommand, a sequenced workflow with real validation and error-recovery loops, and appropriate offloading of setup detail to a one-level-deep reference. The two minor flaws are duplicated gotcha guidance between Mindset and Anti-Patterns, and a dangling reference to a nonexistent requirements.txt.

Suggestions

Consolidate the duplicated gotchas: state the silent-CAPTCHA, MCP-first, and retry-once guidance once (either Mindset or Anti-Patterns) and cross-reference from the other section instead of repeating them.

Fix the References section: either add the missing requirements.txt to the bundle or remove the "Dependencies: requirements.txt" entry (setup-and-troubleshooting.md already covers dependency installation).

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanation of concepts Claude already knows, but three gotchas are stated twice — Mindset points 2–3 (silent CAPTCHA, MCP-first) reappear nearly verbatim as Anti-Patterns, and step 5's retry guidance duplicates "NEVER loop on blocked responses". That duplication keeps it below the every-token-earns-its-place anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover every subcommand and common case: basic search, advanced author/year filtering, author profiles, JSON export, a one-liner to preview saved results, and the retry command with "sleep 60". All flags and example values are concrete.	5 / 5
Workflow Clarity	Six clearly sequenced steps with explicit validation checkpoints and feedback loops: "Always verify by checking the raw response length before reporting 'no results'", 429/short-body detection, retry-once-after-60s with MCP fallback, and a confirm-with-user gate before triage. The batch-candidate use case has validation, so no cap applies.	5 / 5
Progressive Disclosure	Setup is appropriately pushed to a real, one-level-deep reference (references/setup-and-troubleshooting.md) that is clearly signaled in both the workflow and a References section, and the script source is linked. The gap keeping it from 5: the References section lists requirements.txt, which does not exist in the bundle.	4 / 5
	Total	18 / 20 Passed

Description

91%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, an explicit "Use when" clause with concrete triggers, and a rich synonym list of natural trigger terms. The only weaknesses are minor — JSON export for batch workflows is unmentioned, and a few generic trigger terms leave slight overlap risk with sibling academic-search skills.

Dimension	Reasoning	Score
Specificity	"Search Google Scholar for academic papers and author profiles... by keyword, author, or year range. Returns titles, authors, abstracts, and links" lists several concrete actions (keyword/author/year search, author profiles, structured outputs). It stops short of 5 because JSON export for batch review — a headline use case in the body — is not mentioned.	4 / 5
Completeness	"Search Google Scholar for academic papers and author profiles" explicitly states what the skill does, and "Use when discovering papers to triage — by keyword, author, or year range" explicitly states when to use it with concrete trigger phrases — both halves are clearly answered.	5 / 5
Trigger Term Quality	"Triggers: search papers, find papers, google scholar, search scholar, find author, author profile, literature search, paper discovery, search academic literature" covers natural synonyms and phrasings a user would actually say, matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Distinctive triggers like "google scholar", "author profile", and "paper discovery" carve a clear niche, but generic terms such as "search papers" and "literature search" could overlap a closely related academic-search skill (e.g., a semantic-scholar skill), so minor overlap risk remains.	4 / 5
	Total	18 / 20 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
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: pantheon-org/tekhne
Path: crates/skill-auditor/tests/golden-corpus/fixtures/grade-b-google-scholar-search/SKILL.md
Commit: a1083f4

Reviewed: 2 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.