← 返回 Skills 市场
142
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install tianshu-abstract-fit
功能描述
检查中英文摘要大致字数，并按句子顺序粗略填入「背景—方法—结果—结论」四栏草稿（启发式分段，需人工改写）。 Use when: 写毕业论文/课程报告摘要；用户说「摘要结构」「摘要超字数」「四段摘要」。 NOT for: 自动投稿或一键生成终稿摘要。
安全使用建议
This skill appears safe and does local text processing only. It requires Node.js to run and will read any file path you pass to --file, so avoid pointing it at unrelated or sensitive files. The output is heuristic and intended as a draft — review and edit before use. If your agent runs skills in a remote/cloud environment, remember the text you pass may be processed off your machine, so avoid submitting highly sensitive unpublished material there.
功能分析
Type: OpenClaw Skill
Name: tianshu-abstract-fit
Version: 1.0.0
The skill is a simple utility for counting characters and heuristically splitting academic abstracts into four sections (Background, Method, Results, Conclusion). The core logic in scripts/abstract_fit.js is transparent, uses no external dependencies, and performs no network or unauthorized file operations beyond reading the input file provided by the user.
能力评估
Purpose & Capability
Name/description promise (count length and split into 背景/方法/结果/结论 slots) matches the included JS script and SKILL.md. The script only needs a text string or a file path and performs simple string/sentence processing. The only implicit runtime requirement is Node.js, which is reasonable for a Node script.
Instruction Scope
SKILL.md instructs running the local Node script with --file or --text and documents the outputs. The instructions do not ask the agent to read arbitrary system files, environment variables, or send data to external endpoints; the script reads only the file path you supply (via path.resolve) or the provided text.
Install Mechanism
No install spec; this is instruction-only with a small included script. No packages are downloaded and no archives are extracted. Risk is limited to running local JS code; Node runtime is required.
Credentials
The skill declares no environment variables, credentials, or config paths. The code does not access process.env or external services, so requested privileges are proportional to the stated task.
Persistence & Privilege
always is false and the skill does not modify other skills or system configurations. It simply reads input and writes output to stdout; it does not persist state or require elevated privileges.
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 tianshu-abstract-fit - 安装完成后，直接呼叫该 Skill 的名称或使用
/tianshu-abstract-fit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: 摘要结构槽位
元数据
常见问题
Tianshu Abstract Fit 是什么？
检查中英文摘要大致字数，并按句子顺序粗略填入「背景—方法—结果—结论」四栏草稿（启发式分段，需人工改写）。 Use when: 写毕业论文/课程报告摘要；用户说「摘要结构」「摘要超字数」「四段摘要」。 NOT for: 自动投稿或一键生成终稿摘要。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 142 次。
如何安装 Tianshu Abstract Fit？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tianshu-abstract-fit」即可一键安装，无需额外配置。
Tianshu Abstract Fit 是免费的吗？
是的，Tianshu Abstract Fit 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Tianshu Abstract Fit 支持哪些平台？
Tianshu Abstract Fit 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 Tianshu Abstract Fit？
由 tianshu（@wangshengli0421）开发并维护，当前版本 v1.0.0。
推荐 Skills