Skill Claude CodeCodex
Headless browser automation using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, web scraping, or browser automation that can run in the background. Keywords - playwright, headless, browser, test, screenshot, scrape, parallel.
Command Claude Code
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
Command Claude Code
Simplify code for clarity and maintainability — reduce complexity without changing behavior.
Command Claude Code
Design and write a new agent persona (agents/), workflow skill (skills/), or pi harness (.pi/harnesses/).
Command Claude Code
Scan agent-fleet install targets for broken symlinks, stale persona references, and overrides-file problems, then offer repairs.
Command Claude Code
Orchestrate a config-defined team of subagents — route planner/builder (and more) as a runtime roster, handling NEEDSRESEARCH and PLANFILE handoffs.
Command Claude Code
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
Command Claude Code
Load foundational context for the agent-fleet repository.
Command Claude Code
Conduct a five-axis code review — correctness, readability, architecture, security, performance.
Command Claude Code
Guided setup — install agent-fleet artifacts into a workspace for a chosen coding agent.
Command Claude Code
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
Command Claude Code
Start spec-driven development — write a structured specification before writing code.
Command Claude Code
Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.
Command Claude Code
Run a web performance audit via the web-performance-auditor persona.
Command
Implement the next task incrementally - build, test, verify, commit.
Command
Simplify code for clarity and maintainability without changing behavior.
Command
Capture this session's lessons into the project's rules and docs — compound engineering pass.
Command
Design and write a new agent persona, workflow skill, or pi harness.
Command
Orchestrate a config-defined team of subagents — route planner/builder (and more) as a runtime roster, handling NEEDSRESEARCH and PLANFILE handoffs.
Command
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
Command
Load foundational context for the agent-fleet repository.
Command
Conduct a five-axis code review - correctness, readability, architecture, security, performance.
Command
Run the pre-launch checklist and prepare for production deployment.
Command
Start spec-driven development by writing a structured specification before code.