← 返回 Skills 市场
LLMCOM Prompt Compression
作者
Shalinda Jayasinghe
· GitHub ↗
· v1.0.3
· MIT-0
104
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install llmcom
功能描述
Compress prompts for Claude Code and Cursor CLI. Reduces tokens by removing filler words and abbreviating terms. Self-contained, no external dependencies req...
使用说明 (SKILL.md)
LLMCOM Prompt Compression
Self-contained prompt compression tool. No installation required - just read this skill and apply the compression rules.
Compression Rules
-
Remove filler words: the, a, an, is, are, with, of, to, in, on, at, and, for, that, this
-
Abbreviate terms:
- refactor -> refac
- review -> rev
- function -> func
- security -> sec
- performance -> perf
- module -> mod
- component -> comp
- authentication -> auth
- implementation -> impl
-
Output format for Claude Code: agent[task]|scope|focus|action|context|constraints
Example
Input: "Refactor the authentication module to improve type security"
Output: agent[refac]|mod|sec|review|@src|strict
Stats: 11 -> 6 tokens (45% reduction)
How to Use
Apply these rules manually when writing prompts for Claude Code CLI or Cursor agent.
- Identify task type: refactor, review, fix, test, audit
- Remove filler words
- Abbreviate key terms
- Format as pipe-separated values
Quick Reference
| Task | Format |
|---|---|
| Refactor | agent[refac] |
| Security audit | agent[audit] |
| Bug fix | agent[fix] |
| Test coverage | agent[test] |
Integration
Use before sending prompts to:
- Claude Code CLI (gent command)
- Cursor agent
- Any LLM API to reduce token costs\r
安全使用建议
This is a low-risk, instruction-only skill that describes manual text-compression rules and requires no installs or secrets. Before using: (1) test outputs—aggressive removal of filler words (e.g., removing 'is', 'in', 'to') can change meaning or break LLM parsing; (2) verify the abbreviated tokens and pipe format are accepted by your target agent/CLI (Claude Code, Cursor) so you don't lose intent; (3) remember the skill is agent-invocable by default, so an agent could apply these rules automatically if allowed—ensure that automated rewriting is acceptable for your workflow. If you need automated, repeatable behavior consider implementing a tested code-based transformer rather than manual rule application.
功能分析
Type: OpenClaw Skill
Name: llmcom
Version: 1.0.3
The skill bundle contains only documentation (SKILL.md) providing rules for manual prompt compression to reduce token usage. It lacks any executable code, network requests, or instructions that could lead to data exfiltration or unauthorized access.
能力评估
Purpose & Capability
Name/description claim to compress prompts for Claude Code and Cursor CLI. SKILL.md contains only rules for removing filler words, abbreviations, and formatting examples consistent with that purpose; no unrelated capabilities are requested.
Instruction Scope
Runtime instructions are limited to text transformation rules and example formats. There are no commands to read files, access environment variables, call external endpoints, or collect system data.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing is downloaded or written to disk.
Credentials
The skill declares no environment variables, credentials, or config paths and the instructions do not reference any secrets; requested access is proportionate (none).
Persistence & Privilege
always is false and there is no indication the skill modifies agent config or demands permanent presence. The default ability for the agent to invoke the skill is normal and not problematic 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 llmcom - 安装完成后，直接呼叫该 Skill 的名称或使用
/llmcom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
v1.0.3
Self-contained skill. Removed all external code and git clone references. Compression rules now documented directly in SKILL.md.
v1.0.2
- Removed the file llmcom-cli.js from the project.
- CLI usage and documentation remain in SKILL.md, but actual CLI functionality has been deleted.
v1.0.1
Simplified documentation to match CLI features
v1.0.0
Initial release of LLMCOM Prompt Generator skill.
Features:
- Claude Code / Cursor CLI domain support with optimized compression
- 6 domains: Claude Code, Image Gen, Code Gen, LLM Dev, Research, Support
- 3-layer compression (Syntactic, Semantic, Abbreviation)
- 40-80% token reduction with 85%+ semantic preservation
- CLI wrapper for quick compression from command line
Claude Code Domain:
- Keywords: refactor, review, fix, test, audit, security
- Template: agent[task]|scope|focus|action|context|constraints
- Examples: agent[refac]|module|types|review|@src/auth|strict
Files: SKILL.md, llmcom-cli.js, llmcom.bat
元数据
常见问题
LLMCOM Prompt Compression 是什么？
Compress prompts for Claude Code and Cursor CLI. Reduces tokens by removing filler words and abbreviating terms. Self-contained, no external dependencies req... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 104 次。
如何安装 LLMCOM Prompt Compression？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install llmcom」即可一键安装，无需额外配置。
LLMCOM Prompt Compression 是免费的吗？
是的，LLMCOM Prompt Compression 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
LLMCOM Prompt Compression 支持哪些平台？
LLMCOM Prompt Compression 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 LLMCOM Prompt Compression？
由 Shalinda Jayasinghe（@shalinda-j）开发并维护，当前版本 v1.0.3。
推荐 Skills