Software Development Skills

Validate claims through tool execution, avoid superlatives and unsubstantiated metrics. Use when reviewing codebases, analyzing systems, reporting test results, or making any factual claims about code or capabilities.

Guide for using awman to run AI coding agents in isolated containers with multi-step workflows and a REST API. Use when configuring parallel agent sessions, authoring awman workflows, driving the awman api server, managing worktrees, migrating from amux, or troubleshooting awman container runs.

Guide for using Bees, a lightweight SQLite-backed local issue tracker. Use when managing issues, tracking dependencies, exporting for AI context, or running local-first project management.

Package Claude Code as an OCI image using mise and deploy it as a kubernetes-sigs/agent-sandbox SandboxTemplate workload. Use when building a mise-driven Dockerfile for Claude Code, configuring the ~/.claude named volume for session persistence, injecting ANTHROPICAPIKEY per SandboxClaim, applying per-pod egress allowlists for api.anthropic.com, or running Claude Code headlessly inside a Kata or gVisor isolated pod.

Evaluate and benchmark Agent Skills quality using static analysis and evaluation methodology. Use when discussing skill quality, benchmarking skills, measuring activation rates, or reviewing skill effectiveness.

Guide for using the Dagu Web UI. Use when monitoring workflow executions, managing DAGs through the browser, or troubleshooting workflow issues.

Engineering restraint — stop at the first rung that already solves the problem before writing new code. Use when planning, authoring tests, implementing, or reviewing any code change; loads as a standing principle alongside TDD and twelve-factor.

Runex workflow engine: submit workflows via REST API, author TOML bundles, inspect step logs, and debug runs. Use when interacting with Runex API endpoints, creating or modifying workflow bundles, submitting workflow runs, reading step output, or configuring workflow path resolution.

Extracts implementation-agnostic feature specs from working prototypes with SDLC guardrails. Use when handing off a prototype to an engineering team, reverse-engineering prototype code into user stories and acceptance criteria, assessing licensing, security, or supportability risks, or reading bees epics to produce coding specs for a production implementation.

Guide for WebAssembly development with Wasmtime runtime. Use when compiling Rust or Zig to wasm, embedding Wasmtime in Rust or Elixir hosts, working with WASI, or using the Component Model.