liza-mas

36 mods across 1 repository, 362 stars between them.

liza-mas/liza

Agent

Files under /.liza/ are installed copies, not sources — some symlinks, some regular files. Edits there are lost on next install and diverge from the repo. The Edit tool also silently replaces symlinks with regular files.

362 5d ago A 0 tokens original Apache-2.0

liza-mas/liza

Agent

Go test files in this project often exceed 10K tokens (table-driven tests, helpers, setup).

362 5d ago A 0 tokens original Apache-2.0

liza-mas/liza

Agent

Repository-wide validation such as rtk make test-race, rtk make coverage, or a repeated race/shuffle package run can run for several minutes. RTK may buffer successful package output while the execution tool exposes the still-running process through a session ID.

362 5d ago A 0 tokens original Apache-2.0

liza-mas/liza

Agent

Some validation tools consume their primary input from stdin, including gocover-cobertura when converting a Go coverage profile.

362 5d ago A 0 tokens original Apache-2.0

liza-mas/liza

Agent

Liza embeds contracts and skills from internal/embedded/ at build time. In a worktree, those embedded copies can lag behind the repo masters after branch switches or edits.

362 5d ago A 0 tokens original Apache-2.0

liza-mas/liza

Agent

Claude Code's Edit tool tracks prior reads by exact string path. If you Read via one path and Edit via a slightly different string (even if both resolve to the same inode), the edit is rejected.

362 5d ago A 0 tokens original Apache-2.0

liza-mas/liza

Agent

The worktree root already ends in the task id: .worktrees/ . Relative paths inside the worktree are rooted there — you do NOT prepend the task id again.

362 5d ago A 0 tokens original Apache-2.0

adr-backfill

09

liza-mas/liza

Skill Claude CodeCodex

Backfill missing ADR from git history and documentation.

362 5d ago A 13 tokens original Apache-2.0

adversarial-pairing

10

liza-mas/liza

Skill Claude CodeCodex

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 §BRANDNAMETITLE§…

362 5d ago A 73 tokens original Apache-2.0

liza-mas/liza

Skill Claude CodeCodex

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

362 5d ago A 16 tokens original Apache-2.0

bash-policy

12

liza-mas/liza

Skill Claude CodeCodex

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.

362 5d ago A 50 tokens original Apache-2.0

liza-mas/liza

Skill Claude CodeCodex

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

362 5d ago A 17 tokens original Apache-2.0

liza-mas/liza

Skill Claude CodeCodex

Assess whether an input document is ready for a specific §BRANDNAMETITLE§ 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 §BRANDBINARYNAME§ with --entry-point…

362 5d ago A 122 tokens original Apache-2.0

checkpoint-summary

15

liza-mas/liza

Skill Claude CodeCodex

Summarize artifacts produced by §BRANDBINARYNAME§ agents for human checkpoint review.

362 5d ago A 20 tokens original Apache-2.0

clean-code

16

liza-mas/liza

Skill Claude CodeCodex

Pre-commit Clean Code refactoring.

362 5d ago A 10 tokens original Apache-2.0

liza-mas/liza

Skill Claude CodeCodex

Quantitative and qualitative code quality assessment with prioritized refactoring recommendations.

362 5d ago A 17 tokens original Apache-2.0

code-review

18

liza-mas/liza

Skill Claude CodeCodex

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.

362 5d ago A 43 tokens original Apache-2.0

code-spec-backfill

19

liza-mas/liza

Skill Claude CodeCodex

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

362 5d ago A 37 tokens original Apache-2.0

context-engineering

20

liza-mas/liza

Skill Claude CodeCodex

Analyze §BRANDNAMETITLE§ §BRANDPROJECTDIRNAME§/agent-prompts/ and §BRANDPROJECTDIRNAME§/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…

362 5d ago A 123 tokens original Apache-2.0

debugging

21

liza-mas/liza

Skill Claude CodeCodex

Debugging optimizes for certainty, not speed. Speed is a byproduct of certainty. Debugging always starts by ruling out trivial causes. If not sufficient, there are two different paths to pursue: Fast Path and Normal Path.

362 5d ago A 6 tokens original Apache-2.0

liza-mas/liza

Skill Claude CodeCodex

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.

362 5d ago A 50 tokens original Apache-2.0

epic-writing

23

liza-mas/liza

Skill Claude CodeCodex

Transform vision documents into structured epics that bound story-writing.

362 5d ago A 15 tokens original Apache-2.0

feynman

24

liza-mas/liza

Skill Claude CodeCodex

You are a master explainer who channels Richard Feynman’s ability to break complex ideas into simple, intuitive truths. Your goal is to help the user understand any topic through analogy, questioning, and iterative refinement until they can teach it back confidently.

362 5d ago A 13 tokens original Apache-2.0