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

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

65%

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 with concrete commands and a clear report template, but it lacks an explicit sequenced workflow with validation checkpoints for its batch operation and carries repeated path boilerplate plus a broken config.yaml reference.

Suggestions

Add a numbered end-to-end workflow (convert→retrieve source→spawn worker→assemble report) with an explicit validation/verification checkpoint before assembling the final report.

Define the long task-directory path once as a variable/placeholder and reuse it instead of repeating the full literal path six times.

Either add the referenced paper-explain-figures/config.yaml to the bundle or remove the reference so progressive-disclosure navigation is accurate.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with well-organized sections, but the long hidden-directory path '.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-explain-figures/' is repeated verbatim ~6 times and the 协作约定 section adds context not essential to the core task.	2 / 3
Actionability	Provides copy-paste-ready executable commands with concrete flags ('python3 paper-explain-figures/scripts/paper_explain_figures.py --fig … --parallel --max-parallel 3 --runner codex') and a full report-format template, matching the 'fully executable…copy-paste ready' anchor.	3 / 3
Workflow Clarity	The 目标 section lists the three understanding sources and 技术路径 describes the runner, but there is no explicit ordered sequence with validation checkpoints; since this is a batch/parallel operation, the missing verify-step caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are reasonably organized and reference real bundle scripts (scripts/paper_explain_figures.py exists), but the body is largely inline (~140 lines) and references paper-explain-figures/config.yaml which is not present in the bundle, leaving navigation slightly undersignaled.	2 / 3
	Total	9 / 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 is specific and well-scoped with a clear niche and helpful negative triggers, but it leans heavily on implementation jargon and omits an explicit positive 'Use when' trigger, capping completeness and trigger-term quality.

Suggestions

Add an explicit positive trigger clause, e.g. 'Use when the user wants to understand or explain what a paper figure shows.'

Reduce implementation jargon (parallel-vibe, codex exec, 进程级隔离) in favor of natural user-facing phrasing so trigger terms match what users actually say.

Keep the ⚠️ 不适用 negative-scoping but pair it with a positive 'Use when…' so the when-condition is not only implied.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — '解读论文 Figure 的含义并输出…Markdown 报告', '自动尝试从图附近检索生成该图的源代码', '通过 codex exec/claude -p 以进程级隔离解读每张图' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does, but the 'when' is only implied via the ⚠️ 不适用 negative-scoping clause; there is no positive 'Use when…' trigger, so per guideline completeness caps at 2.	2 / 3
Trigger Term Quality	Contains some natural terms ('解读论文 Figure', 'figure 文件绝对路径') but is dominated by technical jargon ('parallel-vibe', 'codex exec', 'claude -p', '进程级隔离') and lacks common user phrasings like '解释这张论文图'.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (paper figure interpretation) and the explicit 不适用 clause ('用户只是想改图尺寸/裁剪/改格式') disambiguates it from image-editing skills, making wrong-skill triggering unlikely.	3 / 3
	Total	10 / 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/paper-explain-figures/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.