paper-explain-figures

解读论文 Figure 的含义并输出一份“教会人类如何读图”的高可读性 Markdown 报告；支持输入 1 个或多个 figure 文件绝对路径与人工解读，自动尝试从图附近检索生成该图的源代码，并采用类似 parallel-vibe 的方式通过 `codex exec`/`claude -p` 以进程级隔离解读每张图（并发上限默认 3，可在 config.yaml 调整）。⚠️ 不适用：用户只是想改图尺寸/裁剪/改格式；或要求直接修改图片/源代码（本 skill 对图片与源代码全程只读，严禁修改）。

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/paper-explain-figures/SKILL.md

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 actionable and reasonably structured with executable commands and a real bundle script, but it is padded with placeholders and lacks concrete batch-validation steps. Replacing placeholder templates with real content and tightening the constraints block would raise quality.

Suggestions

Replace placeholder report-template fields ('...', '文件位置： xxx') with real examples so the output section is fully actionable.

Add a concrete validation/feedback step for the batch multi-figure flow (e.g. verify each figure's report section was generated before finalizing) instead of the vague 校验 placeholder.

Move the inlined common-constraints block and the report template into separate reference files (e.g. constraints.md, report-template.md) and link to them, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete command blocks, but includes padded sections (repeated 输入 section, placeholder templates like '> 文件位置： xxx', and the full common-constraints block) that could be trimmed.	3 / 5
Actionability	Provides concrete, copy-pasteable `python3 .../paper_explain_figures.py --fig ...` commands with parameter examples; the core report template is placeholder-only, leaving a minor gap.	4 / 5
Workflow Clarity	Steps are sequenced (输入/执行步骤/输出) but the report template is placeholder-only and validation (校验) is vague; being a batch multi-figure operation, missing concrete validation caps this at 3.	3 / 5
Progressive Disclosure	Has section structure and a real referenced bundle script (scripts/paper_explain_figures.py) plus config.yaml, but the inlined report template and the large common-constraints block are not clearly signaled as separate navigable references.	3 / 5
	Total	13 / 20 Passed

Description

58%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 conveys a clear, specific capability and disambiguates scope via a non-applicable clause, but it lacks a positive explicit 'Use when' trigger and leans on jargon over natural user phrasing. Strengthening trigger language would lift completeness and trigger-term quality.

Suggestions

Add an explicit positive 'Use when...' clause naming natural trigger phrases (e.g. 'Use when you want to understand or explain a paper figure, plot, or chart') instead of only stating what is not applicable.

Replace jargon like 'parallel-vibe' and '进程级隔离' with plain keywords users would actually say, and include common file extensions (.png, .pdf, .jpg).

Tighten the long sentence into a concise capability statement followed by the trigger clause to improve conciseness.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('解读论文 Figure', '输出...Markdown 报告', '从图附近检索...源代码', '通过 codex exec/claude -p...解读每张图') with minor coverage gaps around output format handling.	4 / 5
Completeness	Has a clear 'what' but only states 'when' via a negative '⚠️ 不适用' clause with no positive 'Use when...' trigger guidance, which caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant terms ('论文 Figure', 'figure 文件绝对路径', '源代码') appear but are diluted by technical jargon ('parallel-vibe', '进程级隔离') and missing common synonyms/file extensions users naturally say.	3 / 5
Distinctiveness Conflict Risk	Targets a specific niche (paper-figure interpretation via codex/claude with read-only constraints) that is mostly distinct with only minor overlap risk against adjacent figure skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: huangwb8/ChineseResearchLaTeX
Path: skills/paper-explain-figures/SKILL.md
Commit: dd19421

Reviewed: 4 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.