liza

Generate and curate Claude-oriented bash-policy project rules. Use to run bash-policy export/report, review .bash-policy-candidates.yaml from Claude settings, update .bash-policy.yaml, normalize command-shape identities, or validate bash-policy configuration.

Assess whether an input document is ready for a specific §BRAND_NAME_TITLE§ MAS entry point. Use when a user asks whether a goal, functional spec, detailed spec, technical spec, PRD, story bundle, architecture plan, or other source document is solid enough to run through §BRAND_BINARY_NAME§ with `--entry-point general-objective`, `functional-spec`, `detailed-spec`, or `technical-spec`; when deciding which entry point fits a document; or before `§BRAND_BINARY_NAME§ init --spec`.

Coordinate Pairing-mode doer/reviewer sessions through a Markdown blackboard. Use when the user invokes /adversarial-pairing with role and blackboard-path arguments or asks multiple pairing agents to coordinate plan review, implementation, staged code review, and follow-up review rounds without §BRAND_NAME_TITLE§ multi-agent mode.

Define component boundaries, interfaces, and structural decisions for a change

Summarize artifacts produced by §BRAND_BINARY_NAME§ agents for human checkpoint review

Pre-commit Clean Code refactoring

Quantitative and qualitative code quality assessment with prioritized refactoring recommendations

Code Review Protocol

Analyze §BRAND_NAME_TITLE§ `§BRAND_PROJECT_DIRNAME§/agent-prompts/` and `§BRAND_PROJECT_DIRNAME§/agent-outputs/` from a context-engineering perspective: prompt payload shape, context budget use, cacheability, duplicated or missing context, instruction hierarchy, tool-output pressure, role-specific context fit, and prompt-output feedback loops. Use when diagnosing agent context bloat, prompt drift, poor agent handoffs, repeated misunderstandings, excessive tool output, or whether §BRAND_NAME_TITLE§ agents received the right information at the right time.

Transform requirements into precise specifications for coding tasks

Transform vision documents into structured epics that bound story-writing

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

Analyze §BRAND_NAME_TITLE§ agents logs

Operate a running §BRAND_NAME_TITLE§ 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 §BRAND_NAME_TITLE§ run (interactive `§BRAND_BINARY_NAME§ tui` or a headless watch loop), not when authoring the work yourself.

Software Architecture Review Protocol

Systemic Coherence and Risk Analysis

Transform requirements into user stories for coding tasks

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

Backfill missing ADR from git history and documentation

Surface alternatives — different ways to address the same need.

Black-Box Red Testing — red tests that expose real bugs

Backfill function-level contracts (docstrings, type annotations) where missing. Report unresolvable gaps with misuse scenarios. Incremental by default (state-driven).

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

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.

explain complex ideas as Richard Feynman

Specification Review Protocol

Debugging Protocol

Test Protocol