avidaldo

Use when writing a git commit message. Proposes a clear, Conventional Commits-compliant message from the staged changes. Invoke with: /conventional-commit, commit message, write commit, git commit, stage and commit.

Use when deciding which Copilot customization primitive to use for a new requirement. Compares instructions, prompts, skills, agents, and hooks and recommends the best fit. Invoke with: /comparar-primitivas, choose primitive, which primitive, instruction vs prompt, skill vs prompt, agent vs skill.

Use when starting exploratory data analysis on a CSV file. Detects columns, types, missing values, and distributions. Proposes initial questions and produces a structured EDA notebook. Invoke with: /csv-eda-basica, eda, explore dataset, analyze csv, check data quality.

Use when documenting a dataset for a project. Creates a structured dataset card covering origin, variables, known biases, licence, and limitations. Invoke with: /dataset-card, document dataset, create dataset card, dataset documentation, data card.

Use when a Python script raises an exception or produces unexpected output. Follows a structured protocol: read the traceback, locate the line, isolate a hypothesis, propose the minimal fix. Invoke with: /debug-python-basico, debug, fix error, traceback, exception, python error.

Use when preparing a complex task for an AI agent. Evaluates what files, examples, or templates should be attached as context to get the best result. Invoke with: /evaluar-contexto-necesario, what context do I need, prepare context, context for agent, attach files.

Use when creating a new Copilot customization file (skill, prompt, agent, or instruction). Proposes the correct frontmatter fields and values. Invoke with: /frontmatter-designer, design frontmatter, write frontmatter, new skill frontmatter, new agent frontmatter.

Use when designing or preparing a practical exercise with clear steps, checkpoints, and deliverables. Structures a practice session for students or for personal learning. Invoke with: /preparar-practica, prepare exercise, design practice, create lab, practice structure.

Continue Stage 3 generation across an approved Stage 2 scope until the selected subcategories have tracked SURF coverage or a declared stop condition is reached. Use when you want an advanced delegated or background lane that keeps designing batches after the first breadth-first wave.

Traverse multiple Stage 2 subcategory files in one Stage 3 run. Use when you want an advanced delegated or background lane that writes at most one new question batch per subcategory while keeping checkpointed progress under a user-provided Stage 3 root.

Fan out Stage 1 summarization across multiple material paths. Use when a subject spans several repos or topic folders and you want one summary per path while keeping each summarization in an isolated context window.

Fetch current VS Code customization docs and audit this repo's `.github` customization layer for deprecated patterns, missing recommended fields, and newly available primitives.

Install all four enforcement layers for notebook output hygiene in a new project. Use when setting up notebook privacy controls, nbstripout integration, CI output checks, or agent hooks for .ipynb files.

Export reviewed quiz-editor JSON state to Moodle XML. Use when opening generated JSON in the editor, checking question statuses, and running the status-filtered json_to_moodle_xml.py script.