skillforge-agent is a unified toolkit of 539 production-ready AI agent skills — merged from three specialized repositories into one clean package.
| Category | Count | Source |
|---|---|---|
| Claude | 340 | Claude Code system prompts & agent prompts |
| Scientific | 148 | Research, science, engineering & analysis skills |
| Gemini | 51 | Gemini-exclusive agent skills |
| Total | 539 |
Skills are not preloaded. The index is tiny (~200 KB). Only the skill you ask for is read into memory — at the moment you call load(). No startup cost, no wasted tokens.
import time # Your app starts instantly
load("eda") # Only THIS skill is loaded, only when you need it
pip install skillforge-agentnpm install skillforge-agentfrom skillforge_agent import load, search, list_skills, categories
# Load a skill — reads from disk only at this moment
skill = load("scientific-brainstorming")
print(skill.name) # "scientific-brainstorming"
print(skill.category) # "scientific"
print(skill.prompt) # full skill content
# Use directly as a string
print(str(skill))
# Search skills
results = search("data analysis")
for r in results:
print(r["name"], r["category"])
# List by category
gemini_skills = list_skills(category="gemini")
# See counts
print(categories())
# {"claude": 340, "scientific": 148, "gemini": 51, "total": 539}const { load, search, listSkills, categories } = require('skillforge-agent')
// or: import { load, search, listSkills, categories } from 'skillforge-agent'
// Load a skill
const skill = load('exploratory-data-analysis')
console.log(skill.prompt)
// Search
const results = search('protein', 'scientific', 5)
results.forEach(r => console.log(r.name))
// Stats
console.log(categories())
// { claude: 340, scientific: 148, gemini: 51, total: 539 }# After pip install
skillforge stats
skillforge search "data analysis"
skillforge search "agent" --category gemini
skillforge list --category scientific
skillforge load scientific-brainstorming
# After npm install -g
npx skillforge stats
npx skillforge search "protein"
npx skillforge load exploratory-data-analysisGeneral-purpose agent skills covering accessibility, data analysis, cloud tools, frameworks, APIs, and more.
skill = load("exploratory-data-analysis", category="gemini")
skill = load("accessibility-a11y")Research and science-focused skills: protein structure, molecular dynamics, bioinformatics, brainstorming, and more.
skill = load("scientific-brainstorming")
skill = load("molecular-dynamics")
skill = load("protein-structure-prediction")Claude Code system prompts, agent prompts, tool descriptions, and skill templates.
skill = load("agent-prompt-explore", category="claude")Load a skill by name. Returns a Skill object.
| Field | Type | Description |
|---|---|---|
.name |
str | Skill name |
.category |
str | gemini, scientific, or claude |
.description |
str | One-line description |
.prompt |
str | Full skill content |
Search skills by keyword. Returns a list of metadata dicts.
List all skills. Returns a list of metadata dicts.
Returns skill counts per category.
ai-skillforge/
├── skills/
│ ├── claude/ # 340 Claude Code system prompts
│ ├── gemini/ # 51 unique Gemini agent skills
│ └── scientific/ # 148 scientific research skills
├── index.json # Unified skill registry (lazy-loaded)
├── python/ # Python package source
│ └── skillforge_agent/
│ ├── __init__.py
│ ├── loader.py
│ └── cli.py
├── js/ # Node.js package source
│ ├── src/
│ │ ├── index.js
│ │ └── index.d.ts
│ └── package.json
└── README.md
Pull requests welcome! To add a new skill, create a folder in the appropriate category:
skills/gemini/my-new-skill/SKILL.md
With frontmatter:
---
name: my-new-skill
description: One-line description of what this skill does.
license: MIT license
metadata:
skill-author: YourGitHub
---
# Skill Title
...Then regenerate index.json by running:
python3 scripts/build_index.pyMIT — Made with ❤️ by Lord1Egypt