repo-intake-and-plan

Ayudante de ingesta rigurosa para reproducción de repositorios de aprendizaje profundo con enfoque en README. Úsese cuando la tarea sea específicamente escanear un repositorio, leer el README y archivos comunes del proyecto, extraer comandos documentados, clasificar candidatos de inferencia, evaluación y entrenamiento, y devolver el plan de reproducción más pequeño y confiable al orquestador principal. No usar para configuración de entorno, descarga de activos, ejecución de comandos, informes finales, búsqueda de artículos ni orquestación integral.

npx skills add https://github.com/lllllllama/rigorpilot-skills --skill repo-intake-and-plan

repo-intake-and-plan

Use this as the Rigor Intake helper. The installed slug remains repo-intake-and-plan for compatibility.

When to apply

  • At the beginning of README-first reproduction work.
  • When the main skill needs a fast map of repo structure and documented commands.
  • When inference, evaluation, and training candidates must be classified conservatively.
  • When the user explicitly wants to inspect the repo first and not run anything yet.

When not to apply

  • When execution has already started and the task is now about running commands or writing outputs.
  • When the target is not a repository-backed reproduction task.
  • When the user only wants paper interpretation without repo inspection.
  • When the user already has a selected documented command and only needs setup or execution.

Clear boundaries

  • This skill scans and plans.
  • This skill is helper-tier and should usually be orchestrator-invoked.
  • It does not install environments.
  • It does not prepare large assets.
  • It does not execute substantive reproduction commands.
  • It does not decide high-risk patching.

Input expectations

  • Target repository path.
  • Access to README and common project files if present.
  • Optional user hints about desired priority, such as inference-first.

Output expectations

  • concise repo structure summary
  • documented command inventory
  • inferred candidate categories: inference, evaluation, training, other
  • minimum trustworthy reproduction recommendation
  • notable ambiguity or risk list

Notes

Use references/repo-scan-rules.md and helper scripts under scripts/.

Más skills de lllllllama

ai-research-explore
lllllllama
We need to translate the given text from English to Spanish. The text is a description of a skill. We must preserve the name "ai-research-explore" but it's not in the text, so we don't include it. Also preserve technical terms like "Rigor Explore", "SOTA", "README", etc. The text includes a slug reference "Rigor Explore compatible skill slug" - we should translate that but keep "Rigor Explore" as is. Also "current_research" and "explore_outputs/" should be preserved as they are likely code references. The instruction says to preserve URLs, numbers, technical terms. So we keep "SOTA", "README", "current_research", "explore_outputs/". Also "task family", "dataset", "benchmark", "evaluation method" are technical but can be translated. "idea gating" might be a term - we can translate as "filtrado de ideas" or keep? Probably translate. "fair comparison" -> "comparación justa". "governed experiments
researchdata-analysisapi
analyze-project
lllllllama
Habilidad de solo lectura de Rigor Analyze / Rigor Audit para repositorios de investigación de aprendizaje profundo. Úsala cuando el usuario quiera leer y comprender un repositorio, inspeccionar la estructura del modelo y los puntos de entrada de entrenamiento o inferencia, revisar configuraciones y puntos de inserción, o señalar patrones de implementación sospechosos sin modificar código ni ejecutar tareas pesadas. No la uses para ejecución activa de comandos, refactorización amplia, adaptación especulativa de código o corrección automática de errores.
developmentcode-reviewresearch
ai-research-reproduction
lllllllama
Orquestador en modo de reproducción de RigorPilot para la reproducción de repositorios de aprendizaje profundo con enfoque README-first. Úsalo cuando el usuario desee un flujo integral y de mínima confianza que primero lea el repositorio, seleccione el objetivo de inferencia o evaluación documentado más pequeño, coordine la ingesta, configuración, ejecución confiable, entrenamiento confiable opcional, análisis de repositorio opcional y resolución opcional de brechas en el artículo, aplique reglas conservadoras de parches, registre evidencia, suposiciones, desviaciones y puntos de decisión humana,...
researchdevelopmentdocument
explore-code
lllllllama
We need to translate the given text from English to Spanish, preserving the name "explore-code" if it appears. The text is a description of an agent skill. The instruction says: "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "explore-code" does not appear in the source text. So we just translate the text. Also preserve product names, protocol names, URLs, numbers, technical terms. The text has technical terms like "leaf skill", "auditable candidate implementation", "deep learning research repositories", "LoRA", "adapter layers", "rollback-aware records", "explore_outputs/", "current_research". We need to keep those as is or translate appropriately? The instruction says "preserve product names, protocol names, URLs, numbers, and technical terms." So technical terms like "LoRA", "adapter layers", "rollback-aware records" should be kept in English? Or translate? Usually technical terms are kept in English, but "leaf skill" might be
developmentresearchcode-review
minimal-run-and-audit
lllllllama
We need to translate the given text from English to Spanish. The text describes a skill called "minimal-run-and-audit" but the instruction says to preserve the name only if it appears in the source text. The name "minimal-run-and-audit" does not appear in the source text; the source text mentions "Rigor Run skill" but that's different. So we should not include the name. We just translate the text inside <text>. Also preserve product names, protocol names, URLs, numbers, technical terms. The text has "README-first", "repro_outputs/", "patch notes", etc. We need to keep those as is or translate appropriately? "README-first" is a term, likely keep as is. "repro_outputs/" is a directory name, keep as is. "patch notes" might be translated as "notas de parche" but it's a technical term, could keep as "patch notes" or translate. The instruction says "preserve product names, protocol names, URLs, numbers, and technical terms
developmenttestingcode-review
env-and-assets-bootstrap
lllllllama
Habilidad de configuración Rigor para la reproducción de repositorios de deep learning con enfoque README-first. Úsala cuando la tarea sea específicamente preparar un entorno conservador basado en conda, suposiciones de rutas de checkpoints y datasets, sugerencias de ubicación de caché y notas de configuración antes de cualquier ejecución en un repositorio documentado con README. No la uses para escaneo de repositorios, orquestación completa, interpretación de artículos, informes de ejecución final ni configuración genérica de entorno que no esté vinculada a un objetivo de reproducción específico.
developmentdevops
explore-run
lllllllama
We need to translate the given text from English to Spanish. The text describes a skill called "explore-run" but the instruction says to preserve the name if it appears in the source text. The name "explore-run" appears in the text? Actually, the text says "Rigor Improve / Rigor Explore run leaf skill" - the name is "explore-run" but it's not explicitly written as a separate name. The instruction says "Name to preserve: explore-run" but the source text does not contain "explore-run" as a standalone term. It contains "Rigor Explore run leaf skill". Possibly the name is part of the description. The instruction says: "Translate only the text inside <text>. Do not include the name unless it appears in the source text." So we should translate the entire text as is, preserving any product names, protocol names, URLs, numbers, technical terms. The name "explore-run" does not appear in the source text, so we don't need to include it. However, "Rigor Improve" and "R
researchdevelopmentdata-analysis
safe-debug
lllllllama
Habilidad de Rigor Debug / Rigor Audit para trabajo de investigación en deep learning. Úsala cuando el usuario pegue un traceback, error de terminal, CUDA OOM, fallo de carga de checkpoint, desajuste de formas, síntoma de pérdida NaN o fallo de entrenamiento y desee un diagnóstico conservador antes de cualquier parche, con correcciones de depuración claramente separadas de las contribuciones de investigación. No usar para refactorización amplia, adaptación especulativa, parches exploratorios automáticos o familiarización general con el repositorio.
developmenttestingcode-review