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

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/sn-search-academic/SKILL.md

Quality

Content

75%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 highly actionable and well-structured with executable commands, parameter tables, output schemas, and clearly sequenced multi-step workflows, supported by one-level-deep reference files. Its main weakness is mild redundancy in the concurrency guidance and some inline reference material that could be externalized for tighter token efficiency.

Suggestions

Merge the '执行约定' and '并发与限流约定' concurrency guidance into a single section to remove overlap and save tokens.

Move the ArXiv category cheat-sheet into a dedicated reference file (e.g. references/arxiv_categories.md) and link to it from the body.

Weave an explicit output-validation checkpoint ('check top-level `success`; on failure read `error`/`errors`/`attempts` before retrying') into each numbered workflow step rather than only documenting it in the output-format section.

Dimension	Reasoning	Score
Conciseness	The body is dense and task-focused with no padding about concepts Claude already knows, but it carries noticeable redundancy (the no-parallel guidance appears in both '执行约定' and a dedicated '并发与限流约定' section) and a ~35-line ArXiv category table that could live in a reference file, so it could be tightened.	3 / 5
Actionability	Fully executable guidance throughout: copy-paste-ready CLI invocations for all three entry scripts, parameter tables with defaults, concrete examples for common cases (arXiv/PMC, references/citations), and field-level output JSON schemas.	5 / 5
Workflow Clarity	Multiple workflows ('全文阅读工作流', '引用追溯工作流' with backward/forward/chain variants, '主工作流') are clearly numbered and sequenced with an explicit stopping condition, and output checking via top-level `success`/`error`/`attempts` is documented; checkpoints are present but somewhat implicit rather than woven into each workflow step.	4 / 5
Progressive Disclosure	SKILL.md acts as an overview with clearly signaled, one-level-deep references to the verified-real references/search.md, references/paper.md, references/refTree.md, keeping provider internals in scripts; the main organization gap is inline reference material (the ArXiv category table, full output schemas) that is reasonable but could be split out.	4 / 5
	Total	16 / 20 Passed

Description

66%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.

The description clearly conveys a well-scoped academic-search niche with several concrete capabilities and natural trigger terms, but it omits any explicit 'Use when...' guidance, which limits its completeness and leaves the trigger condition implied rather than stated.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to survey academic literature, read or summarize papers, map related work, look up encyclopedia entries, or trace citation chains.'

Add common synonyms users say such as '文献检索' / 'literature search' to broaden trigger-term coverage.

Rephrase capabilities as concrete actions on concrete objects (e.g. 'Search arXiv/Semantic Scholar/PubMed, list and read paper sections, query references and citations') to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the academic-search domain and lists several concrete capabilities — '学术调研', '论文精读', '相关工作梳理', '百科知识查询', '引用链追溯' — but they are phrased as abstract activity nouns rather than concrete operations on concrete objects, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	It clearly states what the skill does (academic research, paper reading, related-work organization, encyclopedia query, citation tracing) but provides no 'Use when...' trigger clause, so per the rubric guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('学术调研', '论文', '相关工作', '百科', '引用链'), giving good keyword coverage, but misses common synonyms such as '文献' / '文献检索' and explicit search phrasings.	4 / 5
Distinctiveness Conflict Risk	The academic-research + paper-reading + citation-tracing niche is mostly distinct with clear triggers and only minor overlap risk with general web-search or generic research skills.	4 / 5
	Total	15 / 20 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: 61b60bb

Reviewed: 8 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.