ByteTerrace/Puck / .claude/skills/dashboard
dashboard
VerifiedMaps Puck.Dashboard (TypeScript, Vite, React): World Studio, the in-browser engine (Puck.World.Browser), its language server, official builds, drafts, the portal's storage, DuckDB and audit pages.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.3 KB |
| evals/d01-studio-language-features/graders/engine-is-the-implementation.md | markdown | 923 B |
| evals/d01-studio-language-features/graders/language-server.md | markdown | 105 B |
| evals/d01-studio-language-features/graders/skill-fired.md | markdown | 36 B |
| evals/d01-studio-language-features/prompt.md | markdown | 775 B |
| evals/d02-generated-world-types/graders/puck-schema.md | markdown | 61 B |
| evals/d02-generated-world-types/graders/regenerate-not-edit.md | markdown | 728 B |
| evals/d02-generated-world-types/graders/skill-fired.md | markdown | 36 B |
| evals/d02-generated-world-types/prompt.md | markdown | 707 B |
evals/d01-studio-language-features/graders/engine-is-the-implementation.md
View on GitHub---
type: llm
weight: 1
---
The response takes highlighting and diagnostics from the engine running in the browser, not from a portal-side grammar or checker.
PASS if it rejects the JavaScript grammar and checker as a second implementation of the language and says the studio gets highlighting (semantic tokens), completion and diagnostics from Puck's own language server running inside the in-browser engine (`Puck.World.Browser`), with the deeper compile and composition check also run by that engine. Example: "Don't write a Lezer grammar: the studio has no grammar of its own. It colours from the language server's semantic tokens and shows its diagnostics, both served by the WebAssembly engine over `Lsp`/`LspIdle`."
FAIL if it endorses writing a grammar, tokenizer or checker in the portal, even as a fallback for speed. Example: "A Lezer grammar is fine for colouring; keep the language server for errors only."
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |