antigravity-awesome-skills
Antigravity Awesome Skills is an installable GitHub library/installer CLI that places reusable SKILL.md agent playbooks into directories for various AI coding assistants (e.g., Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and others). It also provides curated bundles and ordered workflows/playbooks plus installer metadata for plugin marketplace-style distributions where supported.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
This package primarily distributes static markdown playbooks and installer metadata; it does not describe an authenticated network API. Security risks are more about (1) installing unreviewed third-party/community skills, (2) content that may include unsafe instructions for certain environments, and (3) supply-chain risk from installation/updates. No concrete details are provided about secret handling, TLS, or dependency/SBOM hygiene in the supplied content.
⚡ Reliability
Best When
You want an install-once library of reusable, tool-compatible agent instructions and curated starting bundles/workflows across popular coding assistants.
Avoid When
You need a runtime API with fine-grained programmatic control, or you require strict guarantees that every installed skill has been security-hardened for your environment.
Use Cases
- • Quickly installing a large catalog of reusable agent playbooks (SKILL.md) into the expected folders for multiple AI coding assistants
- • Using curated bundles (role/domain-based) to bootstrap consistent planning/coding/testing/security workflows
- • Running multi-step workflows by combining multiple skills in an ordered way
- • Improving agent prompting/operating instructions for common software engineering tasks (debugging, testing, security review, infra/product workflows)
- • Marketplace-style installation for Claude Code/Codex where the repo publishes plugin metadata
Not For
- • A dedicated hosted API service for runtime agent calls (it is primarily a content/library + installer)
- • Real-time authentication/authorization-protected operations (it mostly distributes static markdown playbooks)
- • Use cases requiring strong, standardized machine-to-machine contracts like REST/OpenAPI for skill execution
- • Compliance-heavy environments needing guaranteed content provenance/review for third-party/community skills
Interface
Authentication
The README content indicates installer and file-placement behavior rather than an authenticated network API. No OAuth/scopes mechanism is described for tool execution.
Pricing
No pricing model described in the provided content; it appears to be a repository/library distributed via npm/npx and GitHub.
Agent Metadata
Known Gotchas
- ⚠ Skill availability depends on the specific assistant/tool and the correct install path (e.g., directories under ~/.gemini/..., .cursor/, .claude/, etc.).
- ⚠ Marketplace/plugin distributions are described as “plugin-safe filtered,” so some skills may be excluded until hardened.
- ⚠ Because the repository contains many community/curated playbooks, quality/security varies by skill; agents should still perform validation for sensitive tasks.
- ⚠ For OpenCode path updates, the installed location may differ; incorrect paths can lead to “skill not found” behavior.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for antigravity-awesome-skills.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-29.