Proof-driven QA skill that autonomously proves features and bugfixes work with visual evidence — screenshots, logs, and a self-contained HTML proof report
A Claude Code plugin marketplace by Foundra.
| Plugin | Description |
|---|---|
| rust | Pragmatic Rust coding guidelines — API design, error handling, safety, performance, and idiomatic patterns |
| nls | Language-neutral natural language spec guidance for spec-driven-development projects |
| litmus | Proof-driven QA — autonomously proves features/bugfixes work with screenshots, logs, and HTML proof reports |
Add the marketplace, then install plugins:
/plugin marketplace add foundra-build/foundra-ai-tools
/plugin install rust@foundra
/plugin install nls@foundra
/plugin install litmus@foundra
MIT
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimClaude Code plugin for setting up and using devproxy — local HTTPS dev subdomains for Docker Compose projects
Pragmatic Rust coding guidelines based on Microsoft's Rust Guidelines — covers API design, error handling, safety, performance, and idiomatic patterns
npx claudepluginhub foundra-build/foundra-ai-tools --plugin litmusQA skills for functional-testing domain.
10 coordinated QA agents for Claude Code: chains diff analysis, AC compliance, test scenarios, browser validation, bug reports, and automation code generation.
Agents specialized in quality assurance, testing strategies, and test architecture. Focuses on ensuring code quality and reliability.
Testing workflow skill for high-value test discovery, strategy selection, focused implementation, realistic workload generation, strict review, and suite health diagnostics.
AI code review catches structural issues — null derefs, leaks, races — about 65% of real defects. The other 35% are intent violations: bugs only catchable when you know what the code is supposed to do. Quality Playbook derives behavioral requirements from your codebase AND your docs (specs, issues, chat history), then drives a six-phase review against them. Finds the bugs that look right but aren't.
Self-serve QA for your PR — browser-based verification of ticket requirements before you push.