code-harness-skills

Check and process messages from autonomous agents. Use when starting a session, after agent handoffs, or when checking for completion notifications. This skill describes the pattern of inter-agent messaging -- adapt the implementation to your project's tooling.

Set up Claude Code cloud/mobile environments for development. Use when starting a new cloud session, when tools are missing, or when user says "setup cloud", "setup environment", or mentions mobile Claude Code.

Monitor and refactor large files into smaller, AI-friendly modules. Use when user asks to check file sizes, split large files, or organize the codebase. Ensures tests pass before and after refactoring.

Create design documents in the correct format and location. Use when user asks to create a design doc, plan a feature, or document a design. Handles both planned/ and implemented/ docs with proper structure.

Monitor and triage GitHub issues against design docs and implementation status. Use when user asks to "check issues", "triage issues", "sync issues", "what issues are open", or wants to ensure issues are up-to-date with development progress.

Run Claude Code in headless/programmatic mode for automation, CI/CD, and agent workflows. Use when user asks about headless mode, programmatic execution, scripting Claude, or automating Claude workflows.

Review code for performance issues and run benchmarks. Use when user asks to analyze performance, run benchmarks, or review code for optimization opportunities.

Create new releases with version bumps, changelog updates, git tags, and CI/CD verification. Use when user says "ready to release", "create release", mentions version numbers, or wants to publish a new version.

Create new Anthropic Agent Skills, test them with eval-driven iteration, and optimize descriptions for triggering accuracy. Use when user asks to create a new skill, improve an existing skill, test skill quality, optimize skill descriptions, add skill functionality, or wants to build a custom workflow. Also use when analyzing why a skill under-triggers or produces poor results.

Execute approved sprint plans with test-driven development, continuous linting, progress tracking, and pause points. Supports parallel milestone execution via Task sub-agents. Use when user says "execute sprint", "start sprint", or wants to implement an approved sprint plan.

Analyze design docs, calculate velocity from recent work, and create realistic sprint plans with day-by-day breakdowns. Use when user asks to "plan sprint", "create sprint plan", or wants to estimate development timeline.

Analyze test coverage, identify gaps, detect dead code, and improve test quality. Use when user asks to check coverage, review tests, find untested code, or improve test robustness.