Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals, apps/web-evals) and the public website evals display page (apps/web-roo-code/src/app/evals).
.claude/skills/foryourhealth111-pixel-evals-context/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 82% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 39% | 0% |
Use this skill when the task involves:
Do NOT use this skill when:
This monorepo has two distinct evals-related locations that can cause confusion:
| Component | Path | Purpose | | --------------------------- | -------------------------------------------------------------- | -------------------------------------------------------------- | | Evals Execution System | packages/evals/ | Core eval infrastructure: CLI, DB schema, Docker configs | | Evals Management UI | apps/web-evals/ | Next.js app for creating/monitoring eval runs (localhost:3446) | | Website Evals Page | apps/web-roo-code/src/app/evals/ | Public roocode.com page displaying eval results | | External Exercises Repo | Roo-Code-Evals | Actual coding exercises (NOT in this monorepo) |
packages/evals/ - Core Evals Packagepackages/evals/
├── ARCHITECTURE.md # Detailed architecture documentation
├── ADDING-EVALS.md # Guide for adding new exercises/languages
├── README.md # Setup and running instructions
├── docker-compose.yml # Container orchestration
├── Dockerfile.runner # Runner container definition
├── Dockerfile.web # Web app container
├── drizzle.config.ts # Database ORM config
├── src/
│ ├── index.ts # Package exports
│ ├── cli/ # CLI commands for running evals
│ │ ├── runEvals.ts # Orchestrates complete eval runs
│ │ ├── runTask.ts # Executes individual tasks in containers
│ │ ├── runUnitTest.ts # Validates task completion via tests
│ │ └── redis.ts # Redis pub/sub integration
│ ├── db/
│ │ ├── schema.ts # Database schema (runs, tasks)
│ │ ├── queries/ # Database query functions
│ │ └── migrations/ # SQL migrations
│ └── exercises/
│ └── index.ts # Exercise loading utilities
└── scripts/
└── setup.sh # Local macOS setup scriptapps/web-evals/ - Evals Management Web Appapps/web-evals/
├── src/
│ ├── app/
│ │ ├── page.tsx # Home page (runs list)
│ │ ├── runs/
│ │ │ ├── new/ # Create new eval run
│ │ │ └── [id]/ # View specific run status
│ │ └── api/runs/ # SSE streaming endpoint
│ ├── actions/ # Server actions
│ │ ├── runs.ts # Run CRUD operations
│ │ ├── tasks.ts # Task queries
│ │ ├── exercises.ts # Exercise listing
│ │ └── heartbeat.ts # Controller health checks
│ ├── hooks/ # React hooks (SSE, models, etc.)
│ └── lib/ # Utilities and schemasapps/web-roo-code/src/app/evals/ - Public Website Evals Pageapps/web-roo-code/src/app/evals/
├── page.tsx # Fetches and displays public eval results
├── evals.tsx # Main evals display component
├── plot.tsx # Visualization component
└── types.ts # EvalRun type (extends packages/evals types)This page displays eval results on the public roocode.com website. It imports types from @roo-code/evals but does NOT run evals.
The evals system is a distributed evaluation platform that runs AI coding tasks in isolated VS Code environments:
┌─────────────────────────────────────────────────────────────┐
│ Web App (apps/web-evals) ──────────────────────────────── │
│ │ │
│ ▼ │
│ PostgreSQL ◄────► Controller Container │
│ │ │ │
│ ▼ ▼ │
│ Redis ◄───► Runner Containers (1-25 parallel) │
└─────────────────────────────────────────────────────────────┘Key components:
packages/evals/ADDING-EVALS.md for structureEdit files in packages/evals/src/cli/:
runEvals.ts - Run orchestrationrunTask.ts - Task executionrunUnitTest.ts - Test validationEdit files in apps/web-evals/src/:
app/runs/new/new-run.tsx - New run formactions/runs.ts - Run server actionsEdit files in apps/web-roo-code/src/app/evals/:
evals.tsx - Display componentplot.tsx - Chartspackages/evals/src/db/schema.tscd packages/evals && pnpm drizzle-kit generatepnpm drizzle-kit migratebash# From repo root pnpm evals # Opens web UI at http://localhost:3446
Ports (defaults):
bash# packages/evals tests cd packages/evals && npx vitest run # apps/web-evals tests cd apps/web-evals && npx vitest run
@roo-code/evalsThe package exports are defined in packages/evals/src/index.ts:
getRuns, getTasks, getTaskMetrics, etc.Run, Task, TaskMetricsapps/web-evals and apps/web-roo-code| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,884 | 6,016 | -39% | 1 | 1 | 0% | 1,696 | 3,087 | +82% | 0 | 0 | — |
case-02 | fail→pass | 12,342 | 8,583 | -30% | 1 | 1 | 0% | 2,050 | 3,424 | +67% | 0 | 0 | — |
case-03 | fail→pass | 14,847 | 7,392 | -50% | 1 | 1 | 0% | 2,715 | 3,454 | +27% | 0 | 0 | — |
case-04 | fail→pass | 10,098 | 4,025 | -60% | 1 | 1 | 0% | 1,635 | 2,682 | +64% | 0 | 0 | — |
case-05 | fail→pass | 9,460 | 1,821 | -81% | 1 | 1 | 0% | 1,559 | 2,168 | +39% | 0 | 0 | — |
case-06 | fail→pass | 10,055 | 2,705 | -73% | 1 | 1 | 0% | 1,605 | 2,300 | +43% | 0 | 0 | — |
case-07 | fail→pass | 7,997 | 2,162 | -73% | 1 | 1 | 0% | 1,196 | 2,268 | +90% | 0 | 0 | — |
case-08 | fail→pass | 9,371 | 2,655 | -72% | 1 | 1 | 0% | 1,629 | 2,355 | +45% | 0 | 0 | — |
case-09 | fail→pass | 12,372 | 1,943 | -84% | 1 | 1 | 0% | 2,158 | 2,101 | -3% | 0 | 0 | — |
case-10 | fail→pass | 17,452 | 1,572 | -91% | 1 | 1 | 0% | 2,994 | 2,146 | -28% | 0 | 0 | — |
case-11 | fail→pass | 3,628 | 1,190 | -67% | 1 | 1 | 0% | 467 | 2,044 | +338% | 0 | 0 | — |
case-12 | fail→pass | 9,640 | 4,047 | -58% | 1 | 1 | 0% | 1,676 | 2,651 | +58% | 0 | 0 | — |
case-13 | fail→pass | 14,565 | 1,924 | -87% | 1 | 1 | 0% | 1,202 | 2,109 | +75% | 0 | 0 | — |
case-14 | fail→pass | 10,195 | 2,505 | -75% | 1 | 1 | 0% | 1,720 | 2,326 | +35% | 0 | 0 | — |
case-15 | fail→pass | 9,816 | 3,142 | -68% | 1 | 1 | 0% | 1,672 | 2,369 | +42% | 0 | 0 | — |
case-16 | fail→pass | 12,657 | 2,173 | -83% | 1 | 1 | 0% | 2,119 | 2,116 | -0% | 0 | 0 | — |
case-17 | fail→pass | 10,169 | 2,069 | -80% | 1 | 1 | 0% | 1,661 | 2,118 | +28% | 0 | 0 | — |
case-18 | fail→pass | 9,630 | 2,439 | -75% | 1 | 1 | 0% | 1,589 | 2,143 | +35% | 0 | 0 | — |
case-19 | pass→pass | 10,710 | 2,008 | -81% | 1 | 1 | 0% | 1,953 | 2,101 | +8% | 0 | 0 | — |
case-20 | pass→pass | 6,691 | 3,760 | -44% | 1 | 1 | 0% | 1,037 | 2,427 | +134% | 0 | 0 | — |
case-21 | pass→pass | 3,904 | 3,155 | -19% | 1 | 1 | 0% | 573 | 2,368 | +313% | 0 | 0 | — |
case-22 | pass→pass | 8,919 | 4,333 | -51% | 1 | 1 | 0% | 1,326 | 2,604 | +96% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +82 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.