AI Engineering

Penguin SDK is a TypeScript SDK for building self-contained AI apps with agents, sessions, and streaming thinking/tool messages. It includes a complete RAG recipe that ingests documents into a knowledge base and answers with citations behind a web UI.

Skill Porting installs skills from Claude Code plugin marketplaces, Codex plugins, skills.sh registry names, GitHub repos, or local folders into Penguin's agent_state/skills directory after reviewing all files and normalizing SKILL.md frontmatter. Use it to add a third-party skill safely.

VLLM Serving deploys and serves open-weight LLMs on local GPUs with vLLM behind an OpenAI-compatible endpoint, ready for chat and agent workloads. Use it when you need high-throughput GPU inference with tool calling for agent harnesses like PenguinHarness.

Agent Creation turns a user requirement into a working agent configuration by writing AGENTS.md, setting identity metadata, and installing only needed skills. Use it to create or configure an Agent State under the agents directory.

Agent Evaluation runs one specified test agent on one benchmark case exactly once, privately scores the execution, and returns one protocol result. Use it when a run_subagent caller needs a single isolated agent evaluation without managing loops or scoreboards.

Skill Porting teaches an agent to import skills from Claude Code plugin marketplaces, Codex plugins, npx skills, GitHub repos, and local folders, then normalize their frontmatter and verify the install. Use it when you need to safely bring external skills into penguin-harness without blindly running installers.

User Research Cookiy plans, runs, and synthesizes qualitative interviews and quantitative surveys. Use it for research plans, discussion guides, interview analysis, participant recruitment, or Cookiy-backed studies.

Paper2Code converts an arXiv paper into a minimal, citation-anchored Python implementation. Trigger when a user provides an arXiv URL or paper ID and wants an implementation, with all ambiguities flagged honestly.

CC Safety Net configures custom blocking rules across user, project, or shareable GitHub scopes. Use it to add, edit, disable, migrate, or explain safety net rulebooks, then sync and verify that the rules apply.

Decompose With Gates splits hard or multi-part work into independently checkable pieces with explicit verification gates and risk-weighted ordering. Use it when planning corridor-sized tasks, writing lane briefs for subagents, or whenever a task is too large to verify as a whole.

Happier Implement guides AI agents through implementing, changing, fixing, refactoring, migrating, or applying accepted review findings in repositories with owner discovery, scope-preserving economy, TDD, and evidence-backed closeout. Use it for source changes whether or not backed by an approved plan.

Happier Implement Plan executes an approved Happier implementation plan as its orchestrator and integrator. Use it when the user explicitly asks to implement, execute, resume, continue, or complete an approved plan.