Results for “rouge-l”

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Evaluates machine-generated log summaries without human-written references, using LLM judgment and dense embeddings to score relevance, informativeness, and coherence.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

Audit a Supabase/Postgres project for Row-Level Security and access-control gaps, then produce a phased remediation plan. Use when "RLS", "is my Supabase secure", "anyone can read my data", "lock down my tables". App-layer session/route gates → audit-auth-flows.

Guides users through configuring a LaRuche node by reading its live API state and providing click paths for settings, including LLM providers, messaging channels, secrets vault, MCP server, and memory.

Lint and format Python code for Megatron-LM using ruff, black, isort, pylint, and mypy, with commands for autoformatting and import ordering.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Creates IoT and automation flows with Node-RED, visual programming for event-driven applications.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Generates a single-frame HTML template with a cinematic film-leak aesthetic: warm light leaks, 35mm grain, 2.39:1 letterbox, and serif typography for opening titles or chapter cards.

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

Aggregate RSS feeds from YouTube, Vimeo, Behance, Twitter/X, Bilibili, Weibo, Douyin, Xiaohongshu, and Zhihu with incremental updates, deduplication, and AI classification.

Creates safety alert decks with hazard stripes, tiered cards, and policy code blocks for incident reviews and risk communication.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.

Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does, ranking failure modes by impact, likelihood, and cheapness to test.

Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.

High-fidelity ASCII/Braille rendering via the Risomorphism-1911 pipeline — edge-aware downsampling, presets, quality gates, and eikon mirror workflows

Lark/Feishu CLI router: match intent, then Read the Entry file under lark-*/ (e.g. lark-doc/lark-doc.md). Covers docs, markdown, sheets, base, calendar, im, mail, task, okr, drive, wiki, slides, whiteboard, apps, approval, attendance, contact, vc, minutes, note, event via lark-cli. Use when operating Feishu/Lark workspace resources, messaging, docs, calendars, tasks, OKRs, or Miaoda deploys.

Create a clear project status brief with progress, risks, blockers, decisions, and next actions.

Verificar status do serviço, renomear serviços, alterar ícones de serviço, vincular serviços ou criar serviços com imagens Docker. Para criar serviços com código local, prefira a skill railway-new. Para fontes de repositório GitHub, use a skill railway-new para criar serviço vazio e depois railway-environment para configurar a fonte.

Write and run Perl tests using Test2::V0, Test::More, prove, mocking, and Devel::Cover with a TDD workflow.

Universal transformation λ(ο,K).τ with recursive self-improvement. USE WHEN routing reasoning, validating knowledge graphs, preparing CICM/ANZCA examinations, or when self-improvement of reasoning/architecture/context is required. Routes queries through R0-R3 complexity pipelines, validates topology (η≥target) and governance (KROG), emits per style (Φ), and compounds learnings into knowledge K. Triggers on complexity assessment, multi-step reasoning, examination mode, or /λ invocation.

Redis in-memory data store. Covers data structures, caching, and pub/sub. Use for caching and real-time features. USE WHEN: user mentions "redis", "caching", "session storage", "rate limiting", "pub/sub", "sorted sets", "in-memory database", "cache invalidation" DO NOT USE FOR: relational data - use `postgresql` or `mysql` instead, document storage - use `mongodb` instead, full-text search - use `elasticsearch` instead

Query a pre-indexed codebase via CLI to understand structure, find symbols, assess change impact, debug failures, and evaluate PR risk.

Documents Renault's brand design system including color palette, typography hierarchy, and layout principles for web implementation.

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge

Creates a print-friendly architecture or pipeline presentation deck with a blueprint-grid mask, rust-red callouts, and serif typography.

Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→5600.

Audits icon usage in a codebase, enforcing lucide-react as the single icon library, correct sizes, semantic colors, and accessibility standards, then applies fixes.

Audit and reconcile the shared project glossary — find stale terms, missing definitions, conflicts, shadows, inheritance gaps, and cross-path divergences across research docs