CtrlK
BlogDocsLog inGet started
Tessl Logo

research-to-diagram

深度调研主题并自动生成知识关系图谱PDF。接收研究主题后自动进行网络调研、信息收集、知识整理,最终生成专业的可视化关系图谱。适用于"研究...并做图"、"深度分析...并可视化"、"生成知识图谱"等场景。

60

Quality

71%

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 ./apps/desktop/static/bundled-skills/research-to-diagram/SKILL.md
SKILL.md
Quality
Evals
Security

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 is well-structured and contains genuinely executable DOT examples, but it is padded with redundant sections, mislabels prose as code fences, omits validation checkpoints in the workflow, and fails to link out to its own bundled script.

Suggestions

In the PDF-generation step, call the bundled scripts/generate_pdf.sh (which validates DOT syntax before rendering) instead of the bare `dot -Tpdf` command, and add an explicit validate-then-render checkpoint to the workflow.

Convert the 人物关系图/概念图谱/技术架构图 template blocks from ```dot fences containing bullet prose into either runnable DOT snippets or plain markdown lists, so code fences only hold executable code.

Trim redundant sections (核心特性, the structure-to-pdf comparison table, dated version history) and move templates/troubleshooting into separate reference files linked from a concise overview to reduce the monolithic body.

DimensionReasoningScore

Conciseness

Mostly useful reference material but padded with redundancy — '核心特性' restates the description, three full worked examples and a comparison table add length, and a dated version history ('v1.0 (2026-01-02)') injects time-sensitive info outside any deprecated/old-patterns section.

2 / 3

Actionability

The main DOT example and the `dot -Tpdf` command are executable, but the three template blocks are fenced as ```dot yet contain bullet prose (not runnable code), and the TodoWrite 'task plan' block is bullet list rather than a real TodoWrite call.

2 / 3

Workflow Clarity

The six-step workflow is clearly sequenced, but the PDF-generation step shows a bare render command with no validation checkpoint, even though a validating script exists in the bundle — missing verification for a generation/batch operation caps this at 2.

2 / 3

Progressive Disclosure

Sections are well-organized, but the body is a monolithic ~280-line document with templates, troubleshooting and examples all inline, and the bundled scripts/generate_pdf.sh is never referenced or signaled from the overview.

2 / 3

Total

8

/

12

Passed

Description

92%

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, concrete description with explicit trigger guidance and natural user phrasings; its only weakness is moderate overlap with general visualization skills, which the body has to explicitly disambiguate.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '网络调研、信息收集、知识整理' and '生成专业的可视化关系图谱' — matching the multi-action anchor rather than a single vague verb.

3 / 3

Completeness

States both what it does (research → knowledge-graph PDF) and when to use it via the explicit trigger clause '适用于...等场景', equivalent to a 'Use when' clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Natural phrasings a user would actually say ('研究...并做图', '深度分析...并可视化', '生成知识图谱') give good coverage of how the request is phrased in practice.

3 / 3

Distinctiveness Conflict Risk

The research-first framing is a distinct niche, but triggers like '生成知识图谱' and '可视化' can overlap with pure diagram/structure skills — the body itself needs a dedicated comparison section to disambiguate from structure-to-pdf, signalling residual overlap risk.

2 / 3

Total

11

/

12

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/nexu
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.