🧪
QualityTypeScript

Tutti Test Audit

by tutti-os

Tutti Test Audit is a Quality skill for Claude Code, published by tutti-os in tutti.

3.3K stars328 forkson tutti-os/tuttiAdded 2026/08/17+1% in starsRepository updated 2026/08/17
agent-collaborationagent-orchestrationagent-workspaceagentic-aiagentic-workflowai-agentsai-toolsai-workspaceclaude-codecodexcoding-agentdesktop-appdeveloper-toolshermes-agentlocal-firstmacos-appmcpmulti-agentshared-contextvibe-coding
Install in seconds
Install Tutti Test Audit
Copy Tutti Test Audit into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/tutti-os/tutti/tree/main/.codex/skills/tutti-test-audit ~/.claude/skills/tutti-test-audit

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/tutti-os/tutti.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
.codex/skills/tutti-test-audit/SKILL.md in tutti-os/tutti
Installs to
~/.claude/skills/tutti-test-audit
Collection
One of 8 skills cataloged from this repository
Category
Quality1354 skills

What Tutti Test Audit does

Tutti Test Audit audits, designs, writes, revises, or removes Tutti tests. Use it when changing or reviewing unit, component, conformance, integration, regression, platform, or repository tests, enforcing protected contracts, credible failure, correct ownership, negative controls, overlap review, deterministic setup, and CI execution.

Tutti Test Audit is cataloged under Quality on DirSkills. Tutti Test Audit comes from a repository tagged agent-collaboration, agent-orchestration, agent-workspace, agentic-ai and agentic-workflow.

Documentation

README

Tutti Test Audit

Make every changed test earn its maintenance cost. A green test, a coverage increase, or a larger test count is not a quality verdict.

Read the root and closest scoped AGENTS.md, then read docs/conventions/unit-testing.md before a non-trivial test change or review. Follow docs/conventions/testing.md#validation-selection for commands and validation scope.

Establish the evidence map

Before editing, inspect:

  1. the production owner, public entry point, relevant caller and callee;
  2. sibling implementations that share the same invariant;
  3. existing tests, fixtures, conformance suites, and repository checks;
  4. the changed-aware and platform lane that will select the evidence;
  5. relevant history for a regression or a suspicious existing test.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Tutti Test Audit

  • What else does tutti-os publish alongside Tutti Test Audit?

    Tutti Test Audit is one of 8 skills that DirSkills catalogs from tutti-os/tutti, the repository it ships in. Its siblings there include Analyze Performance Traces, Tutti Agent Session Replay and Tutti Agent Workspace App. Each one is a separate skill with its own page in this directory, installs the same way Tutti Test Audit does, and is maintained by tutti-os in that same repository. The rest of the collection is listed on the tutti-os/tutti page.

  • How does Tutti Test Audit compare to other Quality skills?

    Tutti Test Audit ranks #399 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Tutti Test Audit against them. Open each page to compare what they document and how they install.

More from tutti-os/tutti

Tutti Test Audit is one of 8 skills cataloged on DirSkills from tutti-os/tutti.

See all 8 skills
🔍
2w ago

Analyze Performance Traces

Analyze Performance Traces audits Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces to prove trigger-to-render chains, isolate source-level bottlenecks, classify forced layout and render fanout, and apply safe fixes. Use it for trace files, reported profiling durations, dropped frames, long tasks, jank, render storms, layout thrashing, or interaction latency.
Frontend
3.3K328
🎞️
2w ago

Tutti Agent Session Replay

Tutti Agent Session Replay runs, audits, and freshly replays CDP-recorded Session Replay cassettes from case-repository scenario scripts against live AI Providers. Use it to diagnose transport or semantic-state mismatches and add support for new Agent Targets.
Quality
3.3K328
🤖
2w ago

Tutti Agent Workspace App

Tutti Agent Workspace App builds or evolves complex agent-enabled Tutti app repositories with web/server/shared monorepos, @tutti-os/agent-acp-kit local runtimes, dynamic agent catalogs, and run-scoped MCP tool gateways. Use it for full Tutti app architecture, packaging, and production validation; for simple package creation use tutti-workspace-app-factory instead.
AI Engineering
3.3K328
🚀
2w ago

Tutti App Release

Tutti App Release sets up, reviews, runs, or debugs external repositories that publish a Tutti workspace app using a reusable release workflow, including manifests, S3/CloudFront hosting, latest/versions/catalog JSON, and App Center visibility.
DevOps
3.3K328
🏛️
2w ago

Tutti Architecture Review

Tutti Architecture Review reviews Tutti git diffs for project structure, layering, module ownership, and duplicate event-center infrastructure. Use it when reviewing a Tutti change or named module for architecture compliance.
Quality
3.3K328
🧩
2w ago

Tutti UI System

Tutti UI System guides use of the @tutti-os/ui-system component library, including reusing existing components, promoting new shared base or business components, and maintaining metadata and storyboard inventory.
Frontend
3.3K328