Implementado:

No se puede marcar “vista” sin revelar la palabra antes.
Se puede volver a ver la palabra durante debate/votación/resultado.
Notas online privadas por partida y jugador.
Tests añadidos para notas scoped.
Ajusté roomId en el payload de inicio para que las notas no se mezclen entre partidas.

.atl/skill-registry.md

@@ -1,4 +1,4 @@
-# Skill Registry
+# Skill Registry
 
 **Delegator use only.** Any agent that launches sub-agents reads this registry to resolve compact rules, then injects them directly into sub-agent prompts. Sub-agents do NOT read this registry or individual SKILL.md files.
 
@@ -8,51 +8,69 @@ See `_shared/skill-resolver.md` for the full resolution protocol.
 
 | Trigger | Skill | Path |
 |---------|-------|------|
-| When creating a pull request, opening a PR, or preparing changes for review | branch-pr | /Users/freetlab/.config/opencode/skills/branch-pr/SKILL.md |
-| When creating a GitHub issue, reporting a bug, or requesting a feature | issue-creation | /Users/freetlab/.config/opencode/skills/issue-creation/SKILL.md |
-| When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen" | judgment-day | /Users/freetlab/.config/opencode/skills/judgment-day/SKILL.md |
-| When user asks to create a new skill, add agent instructions, or document patterns for AI | skill-creator | /Users/freetlab/.config/opencode/skills/skill-creator/SKILL.md |
+| Go tests, Bubbletea TUI testing | go-testing | C:/Users/jbwhi/.codex/skills/go-testing/SKILL.md |
+| Creating a GitHub issue, reporting a bug, or requesting a feature | issue-creation | C:/Users/jbwhi/.codex/skills/issue-creation/SKILL.md |
+| Creating a pull request or preparing changes for review | branch-pr | C:/Users/jbwhi/.codex/skills/branch-pr/SKILL.md |
+| Adversarial dual review / judgment day | judgment-day | C:/Users/jbwhi/.codex/skills/judgment-day/SKILL.md |
+| Creating new AI skills | skill-creator | C:/Users/jbwhi/.codex/skills/skill-creator/SKILL.md |
+| Browser automation for localhost/file/current browser tab | browser-use:browser | C:/Users/jbwhi/.codex/plugins/cache/openai-bundled/browser-use/0.1.0-alpha1/skills/browser/SKILL.md |
+| Document editing/render verification | documents:documents | C:/Users/jbwhi/.codex/plugins/cache/openai-primary-runtime/documents/26.430.10722/skills/documents/SKILL.md |
+| Presentation deck creation/edit/render/export | presentations:Presentations | C:/Users/jbwhi/.codex/plugins/cache/openai-primary-runtime/presentations/26.430.10722/skills/presentations/SKILL.md |
+| Spreadsheet creation/edit/analyze/visualize | spreadsheets:Spreadsheets | C:/Users/jbwhi/.codex/plugins/cache/openai-primary-runtime/spreadsheets/26.430.10722/skills/spreadsheets/SKILL.md |
 
 ## Compact Rules
 
 Pre-digested rules per skill. Delegators copy matching blocks into sub-agent prompts as `## Project Standards (auto-resolved)`.
 
-### branch-pr
-- Every PR MUST link an approved issue — no exceptions
-- Every PR MUST have exactly one `type:*` label
-- Automated checks must pass before merge is possible
-- Branch names must match: `^(feat|fix|chore|docs|style|refactor|perf|test|build|ci|revert)/[a-z0-9._-]+$`
-- Conventional commits: `^(build|chore|ci|docs|feat|fix|perf|refactor|revert|style|test)(\([a-z0-9\._-]+\))?!?: .+`
-- Commit type determines PR label: feat→type:feature, fix→type:bug, docs→type:docs, refactor→type:refactor, chore→type:chore, style→type:chore, perf→type:feature, test→type:chore, build→type:chore, ci→type:chore, revert→type:bug
-- PR body must contain: Closes #N (linked issue), PR type checkbox, Summary, Changes Table, Test Plan
+### go-testing
+- Use `go test` patterns and Bubbletea `teatest` when touching Go/TUI code.
+- Prefer deterministic tests and isolate terminal/model effects.
+- Keep tests close to behavior and avoid brittle timing assumptions.
+- Not applicable to this Flutter/Dart project unless Go files are introduced.
 
 ### issue-creation
-- Blank issues are disabled — MUST use a template (bug report or feature request)
-- Every issue gets `status:needs-review` automatically on creation
-- A maintainer MUST add `status:approved` before any PR can be opened
-- Questions go to Discussions, not issues
-- Bug report template required fields: Pre-flight Checks, Bug Description, Steps to Reproduce, Expected Behavior, Actual Behavior, Operating System, Agent/Client, Shell
-- Feature request template required fields: Pre-flight Checks, Problem Description, Proposed Solution, Affected Area
+- Follow issue-first workflow before PR work when a feature/bug needs tracking.
+- Capture problem, expected behavior, acceptance criteria, and verification steps.
+- Do not create noisy or duplicate issues without checking existing context.
+
+### branch-pr
+- Use conventional commit/PR language.
+- Never add AI attribution or `Co-Authored-By`.
+- Ensure code review summary includes what changed, tests/analyze status, and risks.
 
 ### judgment-day
-- Launch TWO sub-agents via delegate (async, parallel — never sequential)
-- Each agent receives the same target but works independently
-- Neither agent knows about the other — no cross-contamination
-- Classify warnings as WARNING (real) or WARNING (theoretical)
-- If confirmed CRITICALs or real WARNINGs exist → delegate Fix Agent
-- After Fix Agent completes → re-launch both judges in parallel
-- After 2 fix iterations, if issues remain → escalate to user
+- Run two independent blind reviews of the same target.
+- Synthesize findings, fix real issues, and re-review until both pass or escalation is needed.
+- Keep judges focused on correctness, regressions, and requirement coverage.
 
 ### skill-creator
-- Create a skill when: pattern is used repeatedly, project-specific conventions differ, complex workflows need steps, decision trees help AI
-- Don't create a skill when: documentation exists, pattern is trivial, one-off task
-- Skill structure: frontmatter (name, description, triggers, allowed-tools), Critical Rules, When to Use, Patterns, Commands
+- Create skills with clear trigger, concise rules, and progressive disclosure.
+- Avoid embedding large references in `SKILL.md`; link supporting files instead.
+- Include actionable constraints and examples only where they prevent mistakes.
+
+### browser-use:browser
+- Use the in-app browser for explicit localhost/file/current-tab inspection.
+- Do not substitute shell `open` or generic browsing for explicit Browser Use requests.
+- After frontend UI changes, suggest browser testing unless already requested.
+
+### documents:documents
+- For `.docx`, render pages to images and visually verify before delivering.
+- Iterate layout until verified; do not assume generated document layout is correct.
+
+### presentations:Presentations
+- Build decks around a clear narrative and chart-first storytelling.
+- Render and critique slides before final export.
+
+### spreadsheets:Spreadsheets
+- Use spreadsheet-native formulas/tables/charts when editing `.xlsx`/CSV workflows.
+- Recalculate and verify outputs after edits.
 
 ## Project Conventions
 
 | File | Path | Notes |
 |------|------|-------|
-| SPEC.md | /Users/freetlab/Proyectos/farolero/SPEC.md | Existing SDD artifacts with Explore/Propose/Spec/Tasks/Apply/Verify phases |
-| .gga | /Users/freetlab/Proyectos/farolero/.gga | Gentleman Guardian Angel config (AI provider, file patterns, rules file) |
+| AGENTS.md | c:/Proyectos/gitea/farolero/AGENTS.md | Flutter/Dart rules: Provider, Clean Architecture, flutter_test, analyze before commit, no Co-Authored-By. |
+| analysis_options.yaml | c:/Proyectos/gitea/farolero/analysis_options.yaml | Uses `package:flutter_lints/flutter.yaml`. |
+| pubspec.yaml | c:/Proyectos/gitea/farolero/pubspec.yaml | Flutter app dependencies and asset declarations. |
 
 Read the convention files listed above for project-specific patterns and rules. All referenced paths have been extracted — no need to read index files to discover more.