by ashutoshsinghpr7 · Codex Skill · ★ 209
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.
| Stars | 209 |
| Forks | 24 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 59.3377000770124/100 |
| Open Issues | 5 |
| Last Updated | 2026-09-15 |
| Created | 2026-08-29 |
| Platforms | python |
| Est. Tokens | ~13k |
These tools work well together with wikiskill for enhanced workflows:
Looking for a wikiskill alternative? If you're comparing wikiskill with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear
Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate age
Debug your AI agents
Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.
Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into
Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.
Explore other popular codex skill tools:
wikiskill is WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a docum. It is categorized as a Codex Skill with 209 GitHub stars.
wikiskill is primarily written in Python. It covers topics such as agent-skills, agents, ai-agents.
You can find installation instructions and usage details in the wikiskill GitHub repository at github.com/ashutoshsinghpr7/wikiskill. The project has 209 stars and 24 forks, indicating an active community.
wikiskill is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to wikiskill on Agent Skills Hub include open-skills, openlegion, vllora. 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: