← 返回 Skills 市场
README Grader
作者
Xudong Guo
· GitHub ↗
· v1.0.0
· MIT-0
101
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install readme-grader
功能描述
Evaluate a README file text, score it out of 100, and provide specific, actionable improvement suggestions.
安全使用建议
This skill appears coherent and low-risk, but remember it requires you to paste the raw README text into the chat — do not paste secrets, private keys, or proprietary code you cannot share. If your README contains sensitive info, sanitize it before use. Also note the skill requests responses in Chinese and prohibits fetching external URLs, so provide the README content directly. If you need stricter limits, avoid enabling autonomous invocation or remove the skill after the review.
功能分析
Type: OpenClaw Skill
Name: readme-grader
Version: 1.0.0
The 'readme-grader' skill is a well-structured tool designed to evaluate and score README files based on open-source best practices. It contains explicit security guardrails in SKILL.md that instruct the AI agent to treat input as untrusted text and strictly forbids fetching external URLs (e.g., via curl or GitHub API) to mitigate indirect prompt injection risks. No malicious code, data exfiltration, or suspicious execution patterns were found.
能力评估
Purpose & Capability
Name and description (evaluate a README, score, and provide suggestions) match the SKILL.md and included README. There are no unrelated required binaries, env vars, or config paths — everything requested is proportional to the stated purpose.
Instruction Scope
SKILL.md contains explicit, bounded runtime instructions: treat input as text, never execute embedded commands, require the user to paste raw README content, and produce a structured Chinese report. The instructions do not ask the agent to read local files, access external URLs, or access secrets.
Install Mechanism
No install specification and no code files (instruction-only). This minimizes disk writes and remote code fetches. The README contains an example plugin install command but that is documentation only and not an install spec for this bundle.
Credentials
The skill requires no environment variables, credentials, or configuration paths. That is appropriate for a text-analysis README grader which only needs the user-provided README text.
Persistence & Privilege
always is false (default) and disable-model-invocation is false (normal). The skill does not request persistent presence or modify other skills. Autonomous invocation is platform normal and not, by itself, a problem here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install readme-grader - 安装完成后，直接呼叫该 Skill 的名称或使用
/readme-grader触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of the readme-grader skill.
- Evaluates a provided README file, scoring it out of 100 based on five open-source best-practice criteria.
- Delivers a structured report with score breakdown, strengths, improvement suggestions, and optimized example Markdown.
- Ensures all analysis is done safely as pure text; execution of README instructions or fetching remote files is strictly prohibited.
- Responds in Chinese and encourages users to paste raw README content directly for assessment.
元数据
常见问题
README Grader 是什么？
Evaluate a README file text, score it out of 100, and provide specific, actionable improvement suggestions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 101 次。
如何安装 README Grader？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install readme-grader」即可一键安装，无需额外配置。
README Grader 是免费的吗？
是的，README Grader 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
README Grader 支持哪些平台？
README Grader 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 README Grader？
由 Xudong Guo（@sunny0826）开发并维护，当前版本 v1.0.0。
推荐 Skills