antigravity-awesome-skills and skillport

One project offers a vast collection of pre-built agentic skills for specific AI platforms, while the other provides a management system to bring and serve agent skills to any AI agent, making them **complementary tools** in an agentic workflow.

skillport
63
Established
Maintenance 25/25
Adoption 10/25
Maturity 11/25
Community 24/25
Maintenance 10/25
Adoption 17/25
Maturity 22/25
Community 14/25
Stars: 23,847
Forks: 4,099
Downloads:
Commits (30d): 533
Language: Python
License: MIT
Stars: 338
Forks: 24
Downloads: 1,489
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No risk flags

About antigravity-awesome-skills

sickn33/antigravity-awesome-skills

The Ultimate Collection of 1000+ Agentic Skills for Claude Code/Antigravity/Cursor. Battle-tested, high-performance skills for AI agents including official skills from Anthropic and Vercel.

Provides an installable skill library distributed via CLI (`npx antigravity-awesome-skills`) that places reusable markdown playbooks into tool-specific directories for Claude Code, Cursor, Gemini CLI, and others. Organizes 1,331+ skills into curated bundles and multi-step workflows, separating operating instructions (skills) from external capabilities (MCP tools) to support planning, security, infrastructure, and product workflows. Integrates with major AI IDEs and agents through both direct installation paths and marketplace plugins, enabling natural invocation syntax like `@brainstorming` within agent conversations.

About skillport

gotalab/skillport

Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.

Provides spec-compliant skill validation and full lifecycle management (install, update, remove) from GitHub or local sources, with programmatic metadata control. Implements a search-first architecture via MCP and CLI modes—metadata loads upfront while full skill instructions load on-demand—reducing context overhead when managing 50+ skills. Targets MCP-compatible clients (Cursor, Copilot, Windsurf, Cline) and agents with shell access, supporting category/tag filtering and per-client skill exposure through environment configuration.

Scores updated daily from GitHub, PyPI, and npm data. How scores work