← 返回 Skills 市场
skill-condenser
作者
Vaskin Kissoyan
· GitHub ↗
· v1.1.0
1693
总下载
3
收藏
10
当前安装
1
版本数
在 OpenClaw 中安装
/install skill-condenser
功能描述
Compress verbose SKILL.md files using Chain-of-Density with skill-aware formatting. Use when a skill exceeds 200 lines or needs terse refactoring.
安全使用建议
This skill appears coherent, but take simple precautions before running it: (1) Run it on a working copy or branch so you can review diffs and revert if necessary. (2) Confirm what 'cod-iteration' means in your agent — does it run locally or call an external API? If external, consider data sensitivity. (3) Check SKILL.md frontmatter for any secrets or tokens (the skill preserves frontmatter exactly). (4) Require a manual review step before applying changes to upstream repositories, and test on a small example first.
功能分析
Type: OpenClaw Skill
Name: skill-condenser
Version: 1.1.0
The skill-condenser bundle is designed to compress verbose SKILL.md files using a Chain-of-Density approach. The `SKILL.md` file contains detailed instructions for an AI agent on how to perform this text condensation, including specific formatting rules and content prioritization. All instructions are directly related to the stated purpose of text processing and do not exhibit any signs of malicious intent, such as data exfiltration, unauthorized execution, persistence, or prompt injection aimed at subverting the agent's core functions or accessing sensitive data. The instructions are functional guidance for the AI model to achieve the desired output format.
能力评估
Purpose & Capability
Name/description match the SKILL.md instructions: the skill reads a SKILL.md, runs iterative 'cod-iteration' passes to compress content, and outputs a condensed SKILL.md. There are no requested binaries, env vars, or config paths that would be unrelated to this purpose.
Instruction Scope
Instructions explicitly tell the agent to read and rewrite SKILL.md content (including moving detailed sections to references/). That's expected for a condenser, but the SKILL.md is somewhat vague about where the source file comes from and how writes are authorized. It also references an undefined step/tool 'cod-iteration' (presumably a model/internal routine). The skill does not instruct sending data to external endpoints, but you should confirm how 'cod-iteration' is implemented so you know whether content is kept locally or sent externally. Frontmatter preservation is required; frontmatter can occasionally contain sensitive metadata, so the agent's handling of it should be confirmed.
Install Mechanism
No install spec and no code files — instruction-only. This is low risk because nothing is written to disk by an installer. The runtime behavior depends on the agent's own capabilities (no external downloads or package installs are requested).
Credentials
The skill requests no environment variables or credentials, which is proportional. A minor caution: frontmatter or example SKILL.md files could embed tokens or URLs; the instructions preserve frontmatter exactly rather than redacting it, so verify that frontmatter does not contain secrets before running automated condensation that may write those fields back or expose them in logs.
Persistence & Privilege
always is false and there is no claim of modifying other skills' configurations or system-wide agent settings. The instructions do describe modifying repository files (moving sections to references/ and updating SKILL.md), which is within scope for a documentation refactorer; just ensure you consent to those repository writes.
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 skill-condenser - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-condenser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
v1.1.0
From Foundry: Compress verbose SKILL.md files using Chain-of-Density with skill-aware formatti
元数据
常见问题
skill-condenser 是什么？
Compress verbose SKILL.md files using Chain-of-Density with skill-aware formatting. Use when a skill exceeds 200 lines or needs terse refactoring. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1693 次。
如何安装 skill-condenser？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-condenser」即可一键安装，无需额外配置。
skill-condenser 是免费的吗？
是的，skill-condenser 完全免费（开源免费），可自由下载、安装和使用。
skill-condenser 支持哪些平台？
skill-condenser 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 skill-condenser？
由 Vaskin Kissoyan（@killerapp）开发并维护，当前版本 v1.1.0。
推荐 Skills