Menu
High-efficiency log parser for 'The Chronicler'. Extracts failures and NPC routine patterns from JSONL logs without LLM inference.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Patrón de escalado de capacidad del modelo por subtarea — cuándo cambiar RALPH_MODEL_CAPABILITY en .ralph/.env
Metodología de planificación para el bucle ralph en AbadIA-MCP — granularidad, estructura de tareas y prerrequisitos
Estrategia para promover componentes compartidos en vault/components/ — cuándo emitir un fichero vs. anotar en pending-components.md
Patrón de 3 capas (Alcance, Criterios, Evidencias) para [juez] checkpoints en tasks de vault
Estructura modular del vault de AbadIA-MCP — separación server-core/server-map y orden de dependencias entre pasadas
Reglas universales al escribir ficheros en vault/ — frontmatter de provenance, bloques Evidence y prohibición de código fuente
| name | chronicler-parser |
| description | High-efficiency log parser for 'The Chronicler'. Extracts failures and NPC routine patterns from JSONL logs without LLM inference. |
| category | research |
| version | 1.0.0 |
This skill processes the game_trajectory.jsonl file to extract high-signal data for the post-mortem analysis.
obsequium decreased.state_before and state_after.Run the parser to get a high-signal summary:
python3 scripts/chronicler_parser.py --log logs/game_trajectory.jsonl --npc-id <id>
Replaces long LLM "reflection" turns with structured data summaries, allowing the LLM to focus only on the high-level "why" of the failure.
Standard: [[osmani-standard-workflow]] | Part of Pack 012