← Back to Skills Marketplace
norci

Prose Optimize

by norci · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ Security Clean
215
Downloads
0
Stars
2
Active Installs
3
Versions
Install in OpenClaw
/install prose-optimize
Description
优化 OpenProse 文件,减少不必要的 LLM API 调用。触发:修改或编写 .prose 文件时。
Usage Guidance
This is an instruction-only helper that sensibly recommends using python3 and grep to replace some LLM steps in .prose workflows. Before using it, review any local scripts (e.g., ./src/*.py or collect_sessions.py) the skill suggests running — the skill assumes those scripts exist and will be executed by the agent. Also confirm your agent/runtime policy for running shell commands: while the skill itself doesn't request credentials or network access, running arbitrary scripts can execute arbitrary code, so only use with trusted scripts and in environments where executing them is acceptable.
Capability Analysis
Type: OpenClaw Skill Name: prose-optimize Version: 1.0.2 The 'prose-optimize' skill is a documentation-heavy bundle providing guidelines and examples for optimizing .prose workflow files to reduce LLM token usage. It suggests replacing redundant LLM calls with Python scripts and merging agent tasks, using standard tools like grep and python3 for auditing and execution without any signs of malicious intent or data exfiltration.
Capability Assessment
Purpose & Capability
Name/description (optimize .prose to reduce LLM calls) match the required tools (python3, grep) and the examples: the skill's recommendations are about replacing LLM steps with Python scripts, piping, and grepping prose files, which legitimately require those binaries.
Instruction Scope
SKILL.md is focused on auditing and refactoring .prose workflows. It references running grep and python scripts, merging agent calls, and using Prose VM conditionals. It does not instruct reading unrelated system files, exfiltrating data, or contacting external endpoints.
Install Mechanism
No install spec and no code files — the skill is instruction-only. That minimizes on-disk risk; runtime suggestions rely on already-installed python3/grep.
Credentials
No environment variables, credentials, or config paths are requested. The lack of secrets is proportional to the described purpose.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent system changes or cross-skill configuration.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install prose-optimize
  3. After installation, invoke the skill by name or use /prose-optimize
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Fixed: Added missing binaries field in metadata. Changed from 'binaries' to 'requires.bins' to match ClawHub spec.
v1.0.1
- Added "binaries" field to metadata, listing required binaries ("python3", "grep") - No changes to core documentation or functionality
v1.0.0
Initial release via EvoSkill
Metadata
Slug prose-optimize
Version 1.0.2
License MIT-0
All-time Installs 2
Active Installs 2
Total Versions 3
Frequently Asked Questions

What is Prose Optimize?

优化 OpenProse 文件,减少不必要的 LLM API 调用。触发:修改或编写 .prose 文件时。 It is an AI Agent Skill for Claude Code / OpenClaw, with 215 downloads so far.

How do I install Prose Optimize?

Run "/install prose-optimize" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Prose Optimize free?

Yes, Prose Optimize is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Prose Optimize support?

Prose Optimize is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Prose Optimize?

It is built and maintained by norci (@norci); the current version is v1.0.2.

💬 Comments