What is skillforge-agent?
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 |
Zero token waste — skills load on demand
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
Install
Python
pip install skillforge-agent
Node.js
npm install skillforge-agent
Quick Start
Python
from 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}
JavaScript / TypeScript
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 }
CLI
# 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-analysis
Skill Categories
Gemini (51 skills)
General-purpose agent skills covering accessibility, data analysis, cloud tools, frameworks, APIs, and more.
skill = load("exploratory-data-analysis", category="gemini")
skill = load("accessibility-a11y")
Scientific (148 skills)
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 (340 skills)
Claude Code system prompts, agent prompts, tool descriptions, and skill templates.
skill = load("agent-prompt-explore", category="claude")
API Reference
load(name, category=None)
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(query, category=None, limit=10)
Search skills by keyword. Returns a list of metadata dicts.
list_skills(category=None)
List all skills. Returns a list of metadata dicts.
categories()
Returns skill counts per category.
Project Structure
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
│ └── ai_skillforge/
│ ├── __init__.py
│ ├── loader.py
│ └── cli.py
├── js/ # Node.js package source
│ ├── src/
│ │ ├── index.js
│ │ └── index.d.ts
│ └── package.json
└── README.md
Contributing
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.py
License
MIT — Made with ❤️ by Lord1Egypt
Metadata
Release files for skillforge-agent 1.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| skillforge_agent-1.0.1.tar.gz | 13.0 MB | Without provenance | Details for skillforge_agent-1.0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| skillforge_agent-1.0.1-py3-none-any.whl | Python 3 | none | any | Details for skillforge_agent-1.0.1-py3-none-any.whl |
Total release size: 28.2 MB
Release files / skillforge_agent-1.0.1.tar.gz
| Download URL | skillforge_agent-1.0.1.tar.gz |
|---|---|
| Size | 13.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
23b5e006f34247918bef7c0dd8c1448c9cffb66d5ae0dc69c1ecfddda1ffd36d
|
|
BLAKE2b-256 checksum How to use checksums |
bf3259599b84928f2293025634c883c8f968e5e70faab07201d02290beb6256c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.13
|
Release files / skillforge_agent-1.0.1-py3-none-any.whl
| Download URL | skillforge_agent-1.0.1-py3-none-any.whl |
|---|---|
| Size | 15.3 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
82af4ae0d8b2c266eb411c317e6c88fe9692a9a833b81c79c1ebfab79d9a2363
|
|
BLAKE2b-256 checksum How to use checksums |
e29e34868073a8456be2d05dff42b19843a62959f4cb864b04321c34e29bd3c6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.13
|
Security for skillforge-agent 1.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.