liza-mas/liza

brand-binary-name-operator

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…

原文语言：英语

clean-code

Pre-commit Clean Code refactoring

原文语言：英语

detailed-spec-writing

Produce legacy PRD-format SMARC specifications. Use only when the user or assigned task explicitly names detailed-spec-writing; never infer activation from requests to write an objective, goal, requirements, specification, plan, or PRD.

原文语言：英语

brand-binary-name-logs

Analyze §BRAND_NAME_TITLE§ agents logs

原文语言：英语

lesson-capture

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

原文语言：英语

code-review

Two-sided code review protocol — reviewers raise findings, authors answer them. Use when reviewing code (PRs, pending changes) or when responding to review feedback, review comments, or a rejected verdict.

原文语言：英语

have-you-considered

Surface alternatives — different ways to address the same need.

原文语言：英语

adversarial-pairing

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,…

原文语言：英语

context-engineering

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…

原文语言：英语

bash-policy

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.

原文语言：英语

check-brand-name-lower-input-readiness

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…

原文语言：英语

architecture-planning

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

原文语言：英语

checkpoint-summary

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

原文语言：英语

code-quality-assessment

Quantitative and qualitative code quality assessment with prioritized refactoring recommendations

原文语言：英语

epic-writing

Transform vision documents into structured epics that bound story-writing

原文语言：英语

generic-subagent

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

原文语言：英语

software-architecture-review

Software Architecture Review Protocol

原文语言：英语

systemic-thinking

Systemic Coherence and Risk Analysis

原文语言：英语

user-story-writing

Transform requirements into user stories for coding tasks

原文语言：英语

adr-backfill

Backfill missing ADR from git history and documentation

原文语言：英语

black-box-red-testing

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

原文语言：英语

code-spec-backfill

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

原文语言：英语

spec-backfill

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

原文语言：英语

white-box-red-testing

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.

原文语言：英语

feynman

explain complex ideas as Richard Feynman

原文语言：英语

spec-review

Specification Review Protocol

原文语言：英语

debugging

Debugging Protocol

原文语言：英语

testing

Test Protocol

原文语言：英语