liza-mas

liza-mas/liza

Skill Claude CodeCodex

Context-efficient delegation to subagents (read-only default, READ-WRITE opt-in).

liza-mas/liza

Skill Claude CodeCodex

Surface alternatives — different ways to address the same need.

liza-mas/liza

Skill Claude CodeCodex

Capture project-specific operational lessons from mistakes, discoveries, and hard-won insights.

liza-mas/liza

Skill Claude CodeCodex

Analyze §BRANDNAMETITLE§ agents logs.

liza-mas/liza

Skill Claude CodeCodex

Operate a running §BRANDNAMETITLE§ multi-agent run from outside the agent pool: keep the orchestrator healthy, review checkpoints, recover stalls, wire agent environments, plan the next run, and escalate to the human only at genuine forks. Use when operating/babysitting a §BRANDNAMETITLE§ run (interactive…

liza-mas/liza

Skill Claude CodeCodex

REVIEWFILE = specs/architecture/architecture-review.md.

liza-mas/liza

Skill Claude CodeCodex

Backfill missing specifications, reconcile spec/code drift, maintain changelog.

liza-mas/liza

Skill Claude CodeCodex

Specification Review Protocol.

liza-mas/liza

Skill Claude CodeCodex

Systemic Coherence and Risk Analysis.

liza-mas/liza

Skill Claude CodeCodex

Tests are the immune system — they reject bugs, not document them.

liza-mas/liza

Skill Claude CodeCodex

Transform requirements into user stories for coding tasks.

liza-mas/liza

Skill Claude CodeCodex

Find bugs by writing tests that should pass but don't. Invoke manually on user-chosen scope (commits, files, or coverage threshold). Outputs red tests with structured rationale. Use when user asks to "stress-test", "find bugs in", "attack", or "break" code.