No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Apeironics · Agent Tool · ★ 69
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is prompt-refine-skill safe to install? View the security audit →
English | 中文 Prompt Refine A model-aware Agent Skill that silently refines your prompt for the model currently answering. You just ask. The active model reshapes the request for itself, preserves your language, and answers without showing the rewrite. Project Introduction | Q
| Stars | 69 |
| Forks | 7 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 60.5194612974043/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-23 |
| Created | 2026-06-05 |
| Platforms | python |
| Est. Tokens | ~13k |
These tools work well together with prompt-refine-skill for enhanced workflows:
Looking for a prompt-refine-skill alternative? If you're comparing prompt-refine-skill with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Agent Skill that silently refines prompts for the currently running model
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
The Ultimate Claude Code Toolkit: 180 skills, 10 agents, 29 commands, 7 hooks, and 81 marketplace repos (11,00
200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.
A collection of AI agent skills for Clawdbot, Claude Code, Codex
World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociatio
Explore other popular agent tool tools:
prompt-refine-skill is Agent Skill that silently refines prompts for the currently running model. It is categorized as a Agent Tool with 69 GitHub stars.
prompt-refine-skill is primarily written in Python. It covers topics such as agent-skill, agent-skills, ai-tools.
You can find installation instructions and usage details in the prompt-refine-skill GitHub repository at github.com/Apeironics/prompt-refine-skill. The project has 69 stars and 7 forks, indicating an active community.
prompt-refine-skill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to prompt-refine-skill on Agent Skills Hub include prompt-refine-skill, claudepro-directory, .claude. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: