一键导入
skill-factory
// A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
// A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
Access and search Telegram message history using AI. Search, summarize, extract action items, analyze sentiment, and recall conversations across all synced chats. Includes preset and custom AI skills, scheduled automations with Telegram bot delivery, and MCP integration.
ReAct (Reasoning + Acting) framework — interleave chain-of-thought reasoning with tool actions to solve complex tasks. Eliminates hallucination by grounding every reasoning step in real observations. Use when the agent needs multi-step reasoning with external tool use: question answering, fact verification, web navigation, interactive decision making, or any task where pure reasoning hallucinates and pure acting fails to plan.
Agent-to-agent feedback protocol for HermesHub. Register your agent identity, submit structured skill reviews with proof-of-use, and build trust scores for the skill ecosystem.
Comprehensive security hardening for Hermes Agent. Detects prompt injection, unicode smuggling, hidden directives, supply-chain skill poisoning, credential exposure, and memory manipulation. Provides runtime scanning rules, input/output validation patterns, and a defense-in-depth checklist aligned with OWASP LLM Top 10.
Undetectable, adaptive, high-performance Python web data extraction. Automatically survives website structure changes, bypasses anti-bot systems (Cloudflare, WAFs), and outperforms BeautifulSoup/Scrapy. Includes stealth browser fetching, CSS/XPath selectors, CLI, interactive shell, and MCP AI server integration.
Open-source orchestration for zero-human companies. Coordinate teams of AI agents (OpenClaw, Claude Code, Codex, Cursor) with org charts, goals, budgets, governance, and heartbeat-driven execution. Manage business goals from a dashboard — not pull requests.
| name | Skill Factory |
| version | 1.0.0 |
| author | Romanescu11 |
| repository | https://github.com/Romanescu11/hermes-skill-factory |
| license | MIT |
| category | meta |
| description | A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them. |
| tags | ["meta","automation","skills","learning","productivity","workflow-capture"] |
A meta-skill plugin for Hermes Agent that silently observes user workflows, detects repeatable patterns (e.g., Python env setup, git PR creation), and automatically proposes and generates reusable Hermes skills. Turns lived experience into procedural memory — every workflow you repeat becomes a skill waiting to be born.
Skill Factory operates in three stages:
┌──────────────────────────────────────────────────────────┐
│ Your Session │
│ "write a test → run it → fix the failure → commit" │
└────────────────────────┬─────────────────────────────────┘
│ observed silently
▼
┌──────────────────────────────────────────────────────────┐
│ SKILL.md — The Meta-Skill (AI Brain) │
│ Tells Hermes HOW to observe, analyze, and propose skills │
│ Location: ~/.hermes/skills/meta/skill-factory/SKILL.md │
└────────────────────────┬─────────────────────────────────┘
│ proposes + generates
▼
┌──────────────────────────────────────────────────────────┐
│ plugin.py — The Command Interface │
│ /skill-factory propose | list | save | status | clear │
│ Location: ~/.hermes/plugins/skill_factory.py │
└────────────────────────┬─────────────────────────────────┘
│ writes files to disk
▼
┌──────────────────────────────────────────────────────────┐
│ Generated Skill Package │
│ ~/.hermes/skills/<category>/<name>/SKILL.md │
│ ~/.hermes/plugins/<name>.py │
└──────────────────────────────────────────────────────────┘
While active, the skill maintains a log of session activity without surfacing it to the user.
What it tracks:
What it ignores:
Skill creation is proposed when any of the following occur:
| Trigger | Example |
|---|---|
| User explicitly requests | "save this as a skill", "remember this workflow" |
| Slash command | /skill-factory propose |
| Repeated pattern (2x+) | Same workflow appeared twice in the session |
| Session winding down | User says "done", "thanks", or wraps up |
| User frustration hint | "I always have to do this manually..." |
When triggered, Skill Factory presents a structured proposal with the detected workflow, then generates a complete skill package:
| Command | Description |
|---|---|
/skill-factory propose | Analyze current session and propose the top detected skill |
/skill-factory list | Show all skills generated in this session |
/skill-factory status | Show what patterns are currently being tracked |
/skill-factory queue | Show all detected patterns queued for proposal |
/skill-factory save <name> | Name and save the last proposed skill |
/skill-factory clear | Clear the current session tracking log |
git clone https://github.com/Romanescu11/hermes-skill-factory.git
cd hermes-skill-factory
bash install.sh
Or manually copy to your Hermes directories:
cp skills/skill-factory/SKILL.md ~/.hermes/skills/meta/skill-factory/SKILL.md
cp plugins/skill_factory.py ~/.hermes/plugins/skill_factory.py
hermes skills reload
hermes skills enable skill-factory
Generated SKILL.md files must:
Generated plugin.py files must: