CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-select-journal

当用户明确要求“推荐投稿期刊”“帮我的论文选 SCI 杂志”“这篇 manuscript 适合投哪些 journal”“期刊匹配/选刊/投稿建议”时必须使用。适用于用户提供全文、摘要、Markdown、LaTeX、PDF、Word 或混合材料的场景;本 skill 会基于 manuscript 与用户偏好,先用内置 `2023IF.xlsx` 做最小硬过滤生成候选池,再由宿主模型自主规划 Set1/Set2/Set3,并联网核验 scope / 质量 / 近 3 个月 PubMed 论文,最后输出 1 份按推荐度排序的 Markdown 选刊报告。⚠️ 不适用:用户只是想润色论文、只想翻译摘要、或只问某个单一期刊的官网信息而不需要系统选刊。

65

Quality

79%

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/paper-select-journal/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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, actionable multi-step workflow with concrete commands and real reference files, undermined by repeated workspace-constraint boilerplate and by repeated references to a templates/ directory that is absent from the bundle.

Suggestions

Add the missing templates/ directory with manuscript_profile.template.json, scope_review.template.json, set3_similarity_review.template.json, and final_recommendations.template.json, or remove the template references and inline the required fields.

Consolidate the .bensz-api workspace-path convention into a single stated location instead of restating it in '输入与工作区', '输出管理', and '公共硬约束'.

Provide one fully-resolved example command (with a concrete <skill_root> and timestamp) so the executable guidance is copy-paste ready without placeholder substitution.

DimensionReasoningScore

Conciseness

Mostly task-specific and efficient, but the workspace-path convention is restated across '输入与工作区', '输出管理', and '公共硬约束', and the boilerplate common-constraints block adds tokens that do not advance the skill's unique procedure.

3 / 5

Actionability

Provides concrete, copy-paste-ready commands for all four scripts (init_workspace.py, shortlist_journals.py, fetch_pubmed_recent.py, render_report.py) with named output artifacts; minor gap is the unresolved <skill_root> and {yyyymmdd-hhmm} placeholders that require substitution.

4 / 5

Workflow Clarity

Clear sequenced pipeline (profile → Set1 → Set2 scope核验 → 4a PubMed → 4b similarity → final JSON → render) with verification gates between sets and predatory-journal/Set3 elimination checkpoints; lacks an explicit validate→fix→retry feedback loop, but validation is present so the batch cap does not apply.

4 / 5

Progressive Disclosure

References to real bundle files (references/*.md, scripts/*.py, assets/journal_catalog/2023IF.xlsx) are clearly signaled, but the body repeatedly cites templates/*.template.json (manuscript_profile, scope_review, set3_similarity_review, final_recommendations) whose templates/ directory does not exist in the bundle, breaking navigation.

3 / 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, information-dense description with explicit trigger phrases, a clear what/when structure, and a well-defined non-applicability boundary. Its only weakness is mild abstraction in the 'host model plans Set1-3' phrasing and overall verbosity.

DimensionReasoningScore

Specificity

Lists several concrete actions ('最小硬过滤生成候选池', '联网核验 scope / 质量 / 近 3 个月 PubMed 论文', '输出 1 份按推荐度排序的 Markdown 选刊报告'), but '宿主模型自主规划 Set1/Set2/Set3' is somewhat abstract, leaving minor gaps versus a fully enumerated action list.

4 / 5

Completeness

Explicitly answers both 'what' (hard-filter candidate pool, plan Set1-3, verify scope/quality/PubMed, output Markdown report) and 'when' ('当用户明确要求…时必须使用'), plus a concrete 不适用 clause.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say ('推荐投稿期刊', '帮我的论文选 SCI 杂志', '这篇 manuscript 适合投哪些 journal', '期刊匹配/选刊/投稿建议'), covering synonyms and mixed-language variants.

5 / 5

Distinctiveness Conflict Risk

Clear niche (systematic journal selection for manuscript submission) with distinct triggers and an explicit 不适用 boundary that minimizes overlap with polishing/translation/single-journal lookup skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
huangwb8/ChineseResearchLaTeX
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.