Skill of Skills
📄 skillActivePromisingmedium

mnfst/manifest

by mnfst

Connect Your Agents And Harnesses With Any Provider 🦚

Supported Platforms

🤖 Claude Code

Stars

6.9k

Skill Type

⚙️ Infrastructure Operations

Quality Score

89/200

License

MIT

Forks

431

Last Updated

Jun 11, 2026

Discovered

Apr 20, 2026

Validation

Passed

github.com/mnfst/manifest

Quality Breakdown

89/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
○Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Docker installation script (docker/install.sh) present - automated system-level installation capability
  • CLAUDE.md file present indicating persistent configuration for AI coding tools
  • Docker compose and Dockerfile present enabling containerized execution with potential access isolation bypass
  • CI/CD workflows (.github/workflows/) with release automation could execute arbitrary code during builds
  • NestJS backend with analytics and auth modules suggests multi-agent capable architecture for orchestrating AI operations
  • No evidence of system shell/bash/exec capability requests in visible files, lowering risk from critical