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 byenzyme · Claude Skill · ★ 86
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is enzyme safe to install? View the security audit →
🧬 Enzyme Enzyme introduces a compile step for your Markdown wiki that: Uses temporally grounded context sampling that captures the contextual use of tags and wikilinks, or natural accumulation in folders (i.e. pseudo-Zettelkasten) With this context, generate questions (called catalysts) and embed them as semantic routes to the whole knowledge base Keeps refreshing, but separates new doc ingestion (local, fast) from catalyst evolution (cheap, periodic) When your agent passes queries through the catalysts, it gets a more personalized way to get caught up on the knowledge base. New: Enzyme relies on a program that Jev generates through a deterministic scan: profile relationships { seek "what matters between people" notice ["meaningful exchanges", "shared interests", "unfi
| Stars | 86 |
| Forks | 3 |
| Language | TypeScript |
| Category | Claude Skill |
| Quality Score | 67.4350275899648/100 |
| Last Updated | 2026-09-30 |
| Created | 2025-01-22 |
| Platforms | claude-code, node |
| Est. Tokens | ~16k |
These tools work well together with enzyme for enhanced workflows:
Looking for a enzyme alternative? If you're comparing enzyme with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A compile step for knowledge bases. Gives your agent a concept graph of your content — under 20s to index, 8ms
Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search,
An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vaul
Persistent memory for AI coding agents
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP
Explore other popular claude skill tools:
enzyme is Local-first compile step for knowledge bases. Save 350x cost, 1000x speed vs. frontier models. It is categorized as a Claude Skill with 86 GitHub stars.
enzyme is primarily written in TypeScript. It covers topics such as claude-code, knowledge-management, local-first.
You can find installation instructions and usage details in the enzyme GitHub repository at github.com/byenzyme/enzyme. The project has 86 stars and 3 forks, indicating an active community.
The top alternatives to enzyme on Agent Skills Hub include enzyme, ChatCrystal, agent-second-brain. 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: