research-plan

科研分析策略规划助手。根据用户的科研分析需求，通过调研顶尖期刊/会议论文的分析方法，制定个性化、可落地的最优分析策略。适用于需要制定实验设计、数据分析流程、技术路线的场景；兼容旧名 make-research-plan 的 prompt 触发。

Quality

58%

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/research-plan/SKILL.md

Quality

Content

50%

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

The body presents a well-sequenced, structured multi-stage research workflow with concrete output schemas and a genuine bundle, but it is verbose, describes operations rather than giving executable commands, omits validation feedback loops for batch steps, and underuses two of its reference files.

Suggestions

Wire the implemented scripts into the workflow as explicit commands (e.g., 'Run `python scripts/initialize.py <dir>`' in 阶段0, '`python scripts/validate.py metadata/theme.json theme`' after step 1.1) so steps are executable rather than descriptive.

Add a validate→fix→retry checkpoint for the batch steps (e.g., after scoring/downloading, validate papers_scored.json with validate.py and re-run failed downloads before proceeding).

Link the orphaned references from the body (e.g., point step 1.2 to literature-search-guide.md and step 2.1 to methodology-extraction-patterns.md as markdown links) and move the large inline JSON schemas into output-templates.md to tighten the overview.

Dimension	Reasoning	Score
Conciseness	The workflow is mostly efficient with clear per-step input/output, but large inline JSON schemas, a marketing '核心价值' section, and a somewhat obvious '故障排除' Q&A add tokens that could be trimmed or moved to references.	2 / 3
Actionability	Concrete artifacts are specified (directory layout, JSON schemas, PDF naming '{第一作者姓氏}_{年份}_{期刊简写}.pdf'), but operations are described ('使用 PDF 读取工具提取', 'AI 语义分析') rather than executed, and the implemented scripts are never wired into steps as runnable commands.	2 / 3
Workflow Clarity	Phases 0-3 with numbered steps and per-step 输入/操作/输出 give a clear sequence, and step 3.3 adds a user-review checkpoint, but the batch operations (search, PDF download, scoring) lack an explicit validate→fix→retry feedback loop, capping clarity at 2.	2 / 3
Progressive Disclosure	Real reference files exist and two are linked ('output-templates.md', 'implementation-notes.md'), but references are signaled as prose paths rather than markdown links, large content stays inline, and 'literature-search-guide.md' and 'methodology-extraction-patterns.md' are never referenced from the body.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 answers both what and when with an explicit trigger clause and uses appropriate third-person voice, but it leans on marketing adjectives ('最优', '可落地') and its trigger terms are somewhat formal and broad, limiting specificity and distinctiveness.

Suggestions

Drop over-claims like '最优' and '可落地' from the description and replace with concrete operations (e.g., '检索 PubMed/arXiv, 评分筛选, 生成 plan.md 与 references.bib').

Add more natural user-facing trigger phrasings (e.g., 'Use when the user asks how to design an experiment, pick statistical methods, or draft a technical roadmap').

Sharpen the niche by naming what is out of scope (e.g., 'does not run the analysis or write the paper') to reduce overlap with generic analysis skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('调研...论文的分析方法', '制定...分析策略', '实验设计', '数据分析流程', '技术路线'), but they stay fairly abstract and are padded with over-claims like '最优' and '可落地' rather than concrete operations.	2 / 3
Completeness	Clearly states what it does ('科研分析策略规划助手...制定...分析策略') and gives an explicit when clause ('适用于需要制定实验设计、数据分析流程、技术路线的场景'), satisfying both what and when.	3 / 3
Trigger Term Quality	Contains relevant terms a researcher might say ('实验设计', '数据分析流程', '技术路线', 'make-research-plan'), but the phrasing is formal/academic and lacks common natural variations, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The literature-based analysis-strategy niche is identifiable, but the trigger terms ('实验设计', '数据分析流程', '技术路线') are broad enough to overlap with generic analysis or planning skills.	2 / 3
	Total	9 / 12 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: huangwb8/ChineseResearchLaTeX
Path: skills/research-plan/SKILL.md
Commit: 01044a6

Reviewed: 3 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.