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 Power-Agent · Agent Tool · ★ 64
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is PowerSkills safe to install? View the security audit →
PowerSkills PowerSkills is the skill layer on top of PowerMCP. PowerMCP exposes raw software tools. PowerSkills tells an agent which tool to reach for first, what to verify before escalating to advanced studies, and what mitigation playbooks to follow when a study finds a real operating problem. The skills are packaged as two Agent Skills plugins inside a Claude Code marketplace, so you can install them in one step (see Install). How this repo differs from PowerMCP Progressive disclosure of software tools Start with the lowest-risk actions first: open or load the case, inspect the model, solve the base case, and only then move to advanced studies. Avoid jumping directly into contingency analysis, dynamics, matrix extraction, or investment optimization before the base case is credible. Senior engineer mitigation skills Add issue-driven playbooks for voltage violations, thermal overloads, contingency findings, dynamic stability problems, planning infeasibilities, convergence failures, fault-duty problems, frequency response, interconnection impacts, and DER hosting capacity. Move beyond violati
| Stars | 64 |
| Forks | 14 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 65.3228905840001/100 |
| Last Updated | 2026-08-22 |
| Created | 2026-01-26 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with PowerSkills for enhanced workflows:
Explore other popular agent tool tools:
PowerSkills is PowerSkills are some Agent Skills for power system analysis. This repository provides AI agents with specialized knowledge and instructions for performing power system simulations, analysis, and optim. It is categorized as a Agent Tool with 64 GitHub stars.
PowerSkills is primarily written in Python.
You can find installation instructions and usage details in the PowerSkills GitHub repository at github.com/Power-Agent/PowerSkills. The project has 64 stars and 14 forks, indicating an active community.
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: