← Back to Skills Marketplace
112
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install prompt-diet
Description
Analyze and optimize OpenClaw system prompt token usage by compressing workspace files (AGENTS.md, SOUL.md, USER.md, TOOLS.md, IDENTITY.md, HEARTBEAT.md, MEM...
Usage Guidance
This skill appears coherent and safe for its stated purpose, but you should: (1) confirm the workspace path before running (it defaults to /home/aif/.openclaw/workspace/ or a local .openclaw/workspace), (2) review recommendations and approve any 🟡 items before edits, (3) ensure sensitive tool auth or secret references in TOOLS.md or MEMORY.md are not accidentally included in automatic changes (the rules say to skip them but double-check), and (4) keep the backups the skill creates until you verify behavior. Optionally install the tiktoken package for more accurate token counts (pip install tiktoken).
Capability Analysis
Type: OpenClaw Skill
Name: prompt-diet
Version: 1.0.0
The 'prompt-diet' skill is a utility designed to optimize token usage in OpenClaw workspace files by identifying and removing redundant content. The bundle includes a Python script (scripts/token_count.py) for estimating token counts and detailed guidelines (references/compression-rules.md) for safe text reduction. The instructions in SKILL.md emphasize a 'safety-first' approach, requiring explicit user approval before any modifications and mandating the creation of backups. No evidence of data exfiltration, unauthorized execution, or malicious prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match actual behavior: it measures token usage and recommends/edits workspace .md files. No unrelated binaries, env vars, or network access are requested.
Instruction Scope
SKILL.md limits operations to workspace markdown files, requires explicit user approval before applying 🟡 review edits, and outlines safe/skip rules. It does read and may modify files in the workspace (expected for this task); it does not instruct exfiltration or access to unrelated system areas.
Install Mechanism
Instruction-only skill with a small included Python script. No install spec, no external downloads, and optional dependency on tiktoken (falls back to chars/4 approximation).
Credentials
No required environment variables, credentials, or config paths are declared. The operations (reading/writing workspace files) are proportional to the stated goal.
Persistence & Privilege
always is false and the skill does not auto-register periodic jobs. It edits only workspace files (with backups) and does not claim to modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install prompt-diet - After installation, invoke the skill by name or use
/prompt-diet - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: audit/recommend/apply workflow for OpenClaw system prompt token optimization. Includes token_count.py script with tiktoken/fallback support, 3-tier safety classification, per-file compression rules, and MEMORY.md special handling.
Metadata
Frequently Asked Questions
What is Prompt Diet?
Analyze and optimize OpenClaw system prompt token usage by compressing workspace files (AGENTS.md, SOUL.md, USER.md, TOOLS.md, IDENTITY.md, HEARTBEAT.md, MEM... It is an AI Agent Skill for Claude Code / OpenClaw, with 112 downloads so far.
How do I install Prompt Diet?
Run "/install prompt-diet" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Prompt Diet free?
Yes, Prompt Diet is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Prompt Diet support?
Prompt Diet is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Prompt Diet?
It is built and maintained by dgkim311 (@dgkim311); the current version is v1.0.0.
More Skills