CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

56

Quality

63%

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/research-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 a well-structured, actionable multi-phase workflow with concrete schemas, sources, and naming conventions, but it is padded with generic advice/boilerplate, lacks explicit per-phase validation feedback loops for its batch operations, and leaves half the reference bundle undiscoverable from SKILL.md.

Suggestions

Link literature-search-guide.md (from 阶段 1) and methodology-extraction-patterns.md (from 阶段 2) inline so all bundle references are navigable from SKILL.md.

Add explicit validation checkpoints after each batch phase (e.g., 'run scripts/validate.py on papers_scored.json before proceeding to 阶段 2') with a validate→fix→retry loop to lift workflow_clarity above the batch cap.

Trim the 核心价值 buzzword list, the generic 对于用户/对于AI执行 advice, and relocate the 公共硬约束 boilerplate to a shared reference to tighten conciseness.

DimensionReasoningScore

Conciseness

The operational core (phases, JSON schemas, paths) is dense and useful, but fluffy 核心价值 buzzwords, generic 对于用户/对于AI执行 advice, and a boilerplate 公共硬约束 block pad the body noticeably.

3 / 5

Actionability

Concrete actionable guidance throughout — specific data sources (PubMed, IEEE Xplore, arXiv, Semantic Scholar, Unpaywall), thresholds (score ≥7, 15-30篇), naming conventions, and copy-pasteable JSON schemas; minor gaps are the absence of inline script invocation commands.

4 / 5

Workflow Clarity

A clear phased sequence (阶段 0-3 with 目标/方法/输出) exists, but batch operations (15-30 PDF downloads, batch extraction) lack explicit per-phase validate→fix→retry checkpoints, and the final 校验 section is generic — the batch-operation cap at 3 applies.

3 / 5

Progressive Disclosure

References are one level deep and clearly signaled for output-templates.md and implementation-notes.md, but literature-search-guide.md and methodology-extraction-patterns.md are orphaned (never linked from the body), and scripts are only surfaced indirectly via the notes table.

3 / 5

Total

13

/

20

Passed

Description

70%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 communicates a specific niche and explicit use-scenarios with natural trigger terms, achieving solid 'what + when' coverage. It could be tightened by replacing abstract action verbs with concrete operations and adopting a direct 'Use when the user mentions…' trigger clause.

Suggestions

Replace abstract verbs ('制定策略') with concrete operations (e.g., '检索文献、提取方法学、综合分析框架、生成可执行计划文档').

Add an explicit '当用户提到实验设计、数据分析流程、技术路线时使用' trigger clause to lift completeness toward anchor 5.

Drop or compress the make-research-plan compatibility note from the description; it is trigger-irrelevant metadata that dilutes distinctiveness.

DimensionReasoningScore

Specificity

Names the domain and 1-2 concrete actions ('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') plus concrete scenarios, but the actions remain abstract rather than enumerating specific operations.

3 / 5

Completeness

Clearly answers 'what' (research-analysis strategy planning via literature investigation) and 'when' via '适用于需要制定实验设计、数据分析流程、技术路线的场景', but the trigger phrasing is scenario-based rather than the explicit 'Use when the user mentions X' anchor-5 form.

4 / 5

Trigger Term Quality

Good natural terms a researcher would say ('实验设计', '数据分析流程', '技术路线', '科研分析策略') with the make-research-plan alias; a few common synonyms are missing and no file-extension triggers apply to this non-file-format skill.

4 / 5

Distinctiveness Conflict Risk

Clear niche (research-analysis strategy planning grounded in literature) with distinct triggers; only minor overlap risk with generic literature-review or systematic-review skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

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.