By oaustegard
Orchestrate multi-agent AI workflows: convene expert panels, delegate sub-tasks to parallel API instances, invoke Gemini models for multimodal analysis, distill reasoning from advanced models into cheaper ones, and explore problem spaces with structured decomposition methods.
Invokes Google Gemini models for structured outputs, image generation, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, structured JSON output, Google API integration, or cost-effective parallel processing.
Execute programs on a compiled transformer stack machine where every instruction fetch and memory read is a parabolic attention head. Demonstrates that transformer attention + FF layers can implement a working computer. Use when user mentions "llm-as-computer", "lac", "stack machine", "compiled transformer", "percepta", "parabolic attention", "execute program", or asks to run/trace programs on the transformer executor.
Convenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six Sigma, root cause analysis, strategic decisions, process improvement, or asks for philosophers/ancients (Socratic, Aristotelian, Stoic method experts).
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.
Install and drive Google's Antigravity CLI (`agy`) as a non-interactive sub-agent. Use when orchestrating agy, running Antigravity agents from a script or sandbox, delegating a task to Google's agent harness, or wanting a Gemini-backed peer agent alongside Claude.
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.
A collection of Claude skills distributed as a Claude Code plugin marketplace. Skills are primarily designed for the Claude.ai PaaS skill compute environment; mileage will vary if used as Claude Code Agent Skills.
Add this repository as a plugin marketplace in Claude Code:
/plugin marketplace add oaustegard/claude-skills
Then browse and install individual plugins:
/plugin install skill-name@oaustegard-claude-skills
Update all marketplace plugins to latest:
/plugin marketplace update
Install skills directly to your project with a single command:
curl -fsSL https://raw.githubusercontent.com/oaustegard/claude-skills/main/templates/installation/install-skills.sh | bash
Or download and customize which skills to install:
curl -O https://raw.githubusercontent.com/oaustegard/claude-skills/main/templates/installation/install-skills.sh
nano install-skills.sh # Edit SKILLS array
chmod +x install-skills.sh && ./install-skills.sh
CI/CD Integration:
mkdir -p .github/workflows
curl -o .github/workflows/install-skills.yml \
https://raw.githubusercontent.com/oaustegard/claude-skills/main/templates/installation/install-skills.yml
For complete documentation, see templates/installation/README.md
Note: If your skill contribution is just a marketing ploy I'll simply delete it.
SKILL.md at the rootyour-skill.zip
└── your-skill/
├── SKILL.md
└── resources/ (optional)
.uploads/ directoryReleases are triggered by updating metadata.version in SKILL.md frontmatter on main branch.
Use semantic versioning:
0.1.0 - Initial release0.1.1 - Patch (bug fixes)0.2.0 - Minor (new features, backward compatible)1.0.0 - Major (breaking changes)npx claudepluginhub oaustegard/claude-skills --plugin ai-and-reasoningCodebase exploration, navigation, mapping, and static analysis tools for understanding unfamiliar codebases.
Ultimate Claude Code skill creator. Design, scaffold, build, review, evolve, and publish production-grade AI agent skills following the Agent Skills open standard and 3-layer architecture.
Open collection of AI agent skills — reusable, framework-agnostic SKILL.md packages
Anthropic's open-source skill for authoring new Agent Skills. For finance devs and power users building their own skills.
Create, edit, evaluate, and package Claude Code agent skills — full draft→test→review→improve lifecycle.
Collection of agent skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.