sn-search-academic

用于学术调研、论文精读、相关工作梳理、百科知识查询和引用链追溯。

Quality

83%

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

85%

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

The body is highly actionable with excellent workflow sequencing and well-structured one-level references. The main weakness is conciseness, due to large inline JSON examples and a full ArXiv category table that inflate the token budget.

Suggestions

Move the full ArXiv category table (lines ~342-375) into a references file and keep only a few representative examples inline to reduce token cost.

Trim or collapse the large JSON output-format blocks into compact field-list summaries, keeping one canonical example per script.

Consider moving the per-source item field lists into the corresponding reference file rather than inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and reference-driven with little concept padding, but the body is long (~375 lines) with large inline JSON output blocks and a full ArXiv category table that could be tightened or moved to a reference.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout (e.g. 'python3 scripts/search.py "..." --limit 5'), real parameter tables, and concrete output JSON shapes.	3 / 3
Workflow Clarity	Multiple clearly sequenced numbered workflows (全文阅读, 引用追溯, 主工作流) with explicit step ordering and error-handling guidance via the output 'success'/'error' fields.	3 / 3
Progressive Disclosure	Clear overview naming three unified entry points, with one-level-deep, clearly-signaled references (references/search.md, paper.md, refTree.md — all verified to exist) for provider fallback details.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 distinct, but lacks an explicit 'Use when' trigger clause, which caps its completeness at 2. Overall a strong description that would benefit from one sentence of explicit usage triggers.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks for literature review, deep-reading a paper, mapping related work, looking up encyclopedia entries, or tracing citation chains.'

Optionally mention the supported sources (arXiv, Semantic Scholar, PubMed, Wikipedia, Google Scholar) in the description to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple distinct concrete actions — '学术调研、论文精读、相关工作梳理、百科知识查询和引用链追溯' — covering the skill's full scope, matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance; the when is only implied, capping completeness per the rubric guideline.	2 / 3
Trigger Term Quality	Uses natural terms users actually say during academic work — '学术调研', '论文精读', '相关工作梳理', '引用链追溯' — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear academic-search niche with distinct triggers (citation tracing, related-work mapping) unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: OpenSenseNova/SenseNova-Skills
Path: skills/sn-search-academic/SKILL.md
Commit: 179fea1

Reviewed: 2 days 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.