liza-mas

25 verified skills4,176 total stars

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 Liza multi-agent mode.

development239

code-review

Code Review Protocol

development235

context-engineering

Analyze Liza `.liza/agent-prompts/` and `.liza/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 Liza agents received the right information at the right time.

tools229

user-story-writing

Transform requirements into user stories for coding tasks

tools228

epic-writing

Transform vision documents into structured epics that bound story-writing

documentation228

generic-subagent

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

testing204

code-quality-assessment

Quantitative and qualitative code quality assessment with prioritized refactoring recommendations

development172

software-architecture-review

Software Architecture Review Protocol

tools172

architecture-planning

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

testing164

spec-backfill

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

development138

spec-review

Specification Review Protocol

testing138

systemic-thinking

Systemic Coherence and Risk Analysis

research138

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.

development138

testing

Test Protocol

testing138

clean-code

Pre-commit Clean Code refactoring

development138

black-box-red-testing

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

testing138

checkpoint-summary

Summarize artifacts produced by liza agents for human checkpoint review

testing138

feynman

explain complex ideas as Richard Feynman

data-ai138

code-spec-backfill

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

development138