Private Claude Code plugins for the AI Platform Optimization team.
Adding the marketplace registers this repo as a plugin source. Plugins are then installed individually — install whichever ones you need.
# 1. Add marketplace (one-time)
/plugin marketplace add https://github.com/inference-sim/sdlc-plugins
# 2. Install plugins (pick what you need)
/plugin install research-ideas@sdlc-plugins
/plugin install hypothesis-test@sdlc-plugins
To enable automatic plugin updates when new versions are released, go to /plugin > Marketplaces > sdlc-plugins and enable auto-update
# Install individual plugins
/plugin install research-ideas@sdlc-plugins
/plugin install hypothesis-test@sdlc-plugins
# Update all installed plugins to latest versions
/plugin marketplace update sdlc-plugins
# Remove a plugin
/plugin uninstall research-ideas@sdlc-plugins
/plugin uninstall hypothesis-test@sdlc-plugins
Generates research ideas with multi-model AI review (Claude, GPT-4o, Gemini).
/research-ideas
Features:
Just run the command and let it guide you. The plugin will:
Outputs a single research.md with problem, background, all ideas, reviews, and executive summary.
Create a problem.md file in your project directory. Some questions you can consider to help drive the problem statement:
Need help articulating your problem? Use the brainstorming superpower:
/superpowers:brainstorm brainstorm problem statements for the /research-ideas skill
This will help you explore and refine your problem statement before generating research ideas.
Guided hypothesis-driven experimentation with auto-analysis.
/hypothesis-test
Features:
Just run the command and it will:
Outputs per-hypothesis directories under hypotheses/ with HYPOTHESIS.md, run.sh, analyze.py, and FINDINGS.md, plus a hypotheses/README.md catalog.
For private repo access, use SSH keys or set GITHUB_TOKEN:
export GITHUB_TOKEN=$(gh auth token)
See example output here.
See CONTRIBUTING.md for plugin development.
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub inference-sim/sdlc-plugins --plugin shared-skillsGuided hypothesis-driven experimentation with auto-analysis
Researches and generates ideas for your project that have been iteratively reviewed by different models
Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.
Structured protocols for feature exploration and development workflows
Strategic research thinking agents — idea evaluation, project triage, and structured brainstorming inspired by Carlini's research methodology
No description provided.
Autonomous research loops with 10 commands. Generalizes Karpathy's autoresearch loop to any domain with mechanical evaluation, overnight persistence, and zero dependencies.
Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces hypothesis-driven reasoning, evidence-first observation, causality validation, and structured output templates. Use when facing unknowns, repeated failures, or complex investigations requiring rigorous methodology.