Agent skills for Claude Desktop

Global TypeScript-first engineering router.

Expert in TypeScript codebase patterns for backend and frontend.

Architecture-first workflow for non-trivial or high-risk software changes.

Local multi-agent design or implementation competition.

Clean Architecture. Enforce the Dependency Rule. Use when adding a file, import, module, package, layer, dependency, framework, database…

Clean Code. Enforce Martin's naming, function, comment, error, test, and smell rules on every change. Use when writing, editing…

Compact the current conversation into a handoff document for another agent to pick up.

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.

Automate Beeminder tasks via Rube MCP (Composio).

Enforce 2026 folder structure standards - feature-based organization, max nesting depth, unidirectional imports.

Bug condition/postcondition formalization as testable Behavior Contracts.

Behavior-Driven Development as a collaboration and specification practice, with pytest-bdd and behave as the bundled automation references.

Behavior tree design and implementation skill for game AI.

Help users apply behavioral science to product design.

Go behind a program to discover what it ACTUALLY uses — its real dependencies, libraries, syscalls, files, network endpoints, env/config…

../../../engineering/behuman/skills/behuman/SKILL.md

Use when the user wants more human-like AI responses — less robotic, less listy, more authentic.

Design a performance benchmark for an API — test scenarios, metrics, and tooling.

Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr…

Use for JS/TS performance-sensitive changes, benchmark additions, benchmark regressions, benchmark result JSON, or any claim that code is…

Agent skill for benchmark-suite - invoke with $agent-benchmark-suite