chore: auto-commit (799 archivos)

- .claude/CLAUDE.md - .claude/commands/subagentes.md - .claude/rules/INDEX.md - .mcp.json - bash/functions/cybersecurity/analyze_dns.md - bash/functions/cybersecurity/audit_http_headers.md - bash/functions/cybersecurity/audit_ssh_config.md - bash/functions/cybersecurity/check_firewall.md - bash/functions/cybersecurity/detect_suspicious_users.md - bash/functions/cybersecurity/encrypt_file.md - ... Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 00:28:20 +02:00
parent d110aa40f9
commit cfdf515228
805 changed files with 5515 additions and 810 deletions
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def aggregate_by_group(rows: list[dict], group_by: list[str], aggs: dict[str, str]) -> list[dict]"
 description: "GROUP BY + agregaciones sobre datos tabulares. aggs es un dict de columna a funcion (sum, mean, count, min, max, first, last, collect). collect acumula valores en lista. None se ignora en agregaciones numericas."
-tags: [datascience, tabular, groupby, aggregate, transform, python]
+tags: [datascience, tabular, groupby, aggregate, transform, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -8,7 +8,7 @@ version: "1.0.0"
 purity: pure
 signature: "def alpha_shape_concave_hull(points: list[tuple[float, float]], alpha: float) -> shapely.geometry.base.BaseGeometry | None"
 description: "Computes the alpha-shape (concave hull) of a 2-D point set via Delaunay triangulation, filtering triangles by circumradius <= alpha and merging survivors."
-tags: [geometry, spatial, concave-hull, alpha-shape, shapely, delaunay]
+tags: [geometry, spatial, concave-hull, alpha-shape, shapely, delaunay, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def autocorrelation(data: list, lag: int) -> float"
 description: "Calcula la autocorrelacion de una serie temporal para un lag dado."
-tags: [statistics, timeseries, correlation, python]
+tags: [statistics, timeseries, correlation, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -8,7 +8,7 @@ version: "1.0.0"
 purity: pure
 signature: "def best_central_tendency(values: list[float], dist_type: str) -> tuple[str, float]"
 description: "Selects the most appropriate central tendency measure for a given distribution type. Returns (label, value) pair."
-tags: [statistics, central-tendency, distribution, robust, mean, median]
+tags: [statistics, central-tendency, distribution, robust, mean, median, pendiente-usar]
 uses_functions:
  - geometric_mean_py_datascience
  - trimmed_mean_py_datascience
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def clip(data: list, lo: float, hi: float) -> list"
 description: "Recorta los valores de la lista al rango [lo, hi]."
-tags: [clipping, bounds, python]
+tags: [clipping, bounds, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -8,7 +8,7 @@ version: "1.0.0"
 purity: pure
 signature: "def detect_distribution_type(values: list[float]) -> dict"
 description: "Classifies the shape of a numeric distribution using skewness, excess kurtosis, tail ratio and log-skewness. Returns a type label and raw stats."
-tags: [statistics, distribution, classification, skewness, kurtosis]
+tags: [statistics, distribution, classification, skewness, kurtosis, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def detect_drift(history: list[dict], current: dict, fields: list[str], threshold: float = 2.0) -> list[dict]"
 description: "Detecta drift estadistico comparando metricas de la ejecucion actual contra el historial usando z-score. Si |z| > threshold, el campo ha drifteado. Util para monitorizar executions en operations.db."
-tags: [drift, statistics, z-score, monitoring, executions, operations, datascience]
+tags: [drift, statistics, z-score, monitoring, executions, operations, datascience, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def detect_outliers(data: list, threshold: float) -> list"
 description: "Detecta outliers por z-score. Retorna lista de bools, True donde |z-score| > threshold."
-tags: [statistics, outliers, python]
+tags: [statistics, outliers, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def diff_entities(before: list[dict], after: list[dict], key: str = 'id', ignore_fields: list[str] | None = None, compare_fields: list[str] | None = None) -> dict"
 description: "Compara dos snapshots de entities y devuelve diferencias campo a campo. Detecta añadidas, eliminadas, modificadas e inalteradas. Ignora created_at y updated_at por defecto."
-tags: [diff, entities, snapshot, operations, comparison, datascience]
+tags: [diff, entities, snapshot, operations, comparison, datascience, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def diff_relations(before: list[dict], after: list[dict], key: tuple[str, str, str] = ('source_id', 'target_id', 'relation_type'), ignore_fields: list[str] | None = None, compare_fields: list[str] | None = None) -> dict"
 description: "Compara relaciones entre dos snapshots usando key compuesta (source_id, target_id, relation_type). Detecta relaciones añadidas, eliminadas y modificadas con detalle campo a campo."
-tags: [diff, relations, graph, snapshot, operations, comparison, datascience]
+tags: [diff, relations, graph, snapshot, operations, comparison, datascience, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def estimate_hawkes(arrivals: list[int], max_lag: int = 30) -> dict"
 description: "Estima parámetros de un proceso Hawkes (alpha, beta, branching_ratio) desde la autocorrelación de arrivals ajustando una exponencial decreciente sobre la ACF."
-tags: [estimation, hawkes, stochastic-process, microstructure, timeseries]
+tags: [estimation, hawkes, stochastic-process, microstructure, timeseries, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def estimate_pareto_alpha(values: list[float], x_min_percentile: float = 90.0) -> dict"
 description: "Estima el exponente alpha de una distribución Pareto via MLE. Alpha bajo indica cola más pesada y mayor frecuencia de valores extremos."
-tags: [estimation, pareto, power-law, heavy-tail, statistics]
+tags: [estimation, pareto, power-law, heavy-tail, statistics, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: impure
 signature: "def extract_relations_mrebel(text: str, entities: list[EntityCandidate], tokenizer: Any, model: Any, src_lang: str = 'es_XX', sentence_split_re: str = r'(?<=[.!?])\\s+', min_sentence_chars: int = 20, num_beams: int = 4, max_length: int = 256) -> list[RelationCandidate]"
 description: "Extrae relaciones entre entidades usando mREBEL (seq2seq multilingue). Divide el texto por oraciones, genera triplets con mREBEL, parsea con parse_rebel_output y alinea a entidades conocidas con align_relations_to_entities. Drop-in con extract_relations_glirel para benchmarks."
-tags: [mrebel, relation-extraction, nlp, extract, knowledge-graph, seq2seq, multilingual, datascience, python]
+tags: [mrebel, relation-extraction, nlp, extract, knowledge-graph, seq2seq, multilingual, datascience, python, pendiente-usar]
 uses_functions:
  - mrebel_load_model_py_datascience
  - parse_rebel_output_py_datascience
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: impure
 signature: "def extract_triples_spacy_es(text: str, nlp: Any) -> dict"
 description: "Extraccion OpenIE schema-less en castellano via reglas de dependencia spaCy. Detecta patrones sujeto-verbo-objeto con el lemma del verbo como relacion (sin vocabulario fijo). Tambien extrae entidades NER (PER, ORG, LOC, MISC)."
-tags: [spacy, openie, nlp, spanish, triples, dependency, ner, schema-less, datascience, python, mit]
+tags: [spacy, openie, nlp, spanish, triples, dependency, ner, schema-less, datascience, python, mit, pendiente-usar]
 uses_functions:
  - spacy_es_load_model_py_datascience
 uses_types: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def fuzzy_merge_adaptive(left: list[dict], right: list[dict], left_key: str, right_key: str, thresholds: list[int] | None = None, how: str = 'left') -> list[dict]"
 description: "Fuzzy join adaptativo entre dos listas de dicts usando rapidfuzz.token_sort_ratio. Prueba thresholds de mayor a menor y asigna el mayor cumplido. Soporta how='left' (todos los de left) e how='inner' (solo con match). Campos colisionantes reciben sufijos _left/_right."
-tags: [fuzzy, matching, join, merge, rapidfuzz, string-similarity, datascience]
+tags: [fuzzy, matching, join, merge, rapidfuzz, string-similarity, datascience, pendiente-usar]
 params:
  - name: left
    desc: Lista de dicts (lado izquierdo del join).
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def histogram(data: list, buckets: int) -> list"
 description: "Calcula histograma con N buckets. Retorna lista de conteos por bucket."
-tags: [statistics, histogram, python]
+tags: [statistics, histogram, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def hotness_score(active_count: int, updated_at: datetime | None, now: datetime | None = None, half_life_days: float = 7.0) -> float"
 description: "Calcula un score de hotness combinando frecuencia de acceso y recencia temporal. Util para ranking de resultados, memoria hot/cold y cache eviction."
-tags: [ranking, decay, recency, frequency, scoring, cache, memory, datascience]
+tags: [ranking, decay, recency, frequency, scoring, cache, memory, datascience, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def impute(data: list) -> list"
 description: "Reemplaza None y NaN con la media de los valores validos."
-tags: [imputation, missing, python]
+tags: [imputation, missing, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -8,7 +8,7 @@ version: "1.0.0"
 purity: pure
 signature: "def kde_density_levels(xs: list[float], ys: list[float], bw_adjust: float = 0.6, abs_quantile: float = 0.1, dense_quantile: float = 0.85, bins: int = 80) -> dict | None"
 description: "Estimates 2-D density via KDE (scipy) or histogram fallback (numpy) and returns per-point density values plus absolute and dense quantile thresholds."
-tags: [statistics, kde, density, spatial, geospatial, scipy, numpy]
+tags: [statistics, kde, density, spatial, geospatial, scipy, numpy, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def linspace(start: float, stop: float, num: int) -> list"
 description: "Genera una lista de valores equiespaciados entre start y stop (inclusivos)."
-tags: [numeric, range, python]
+tags: [numeric, range, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def melt(rows: list[dict], id_vars: list[str], value_vars: list[str] | None = None, var_name: str = 'variable', value_name: str = 'value') -> list[dict]"
 description: "Inversa de pivot. Convierte columnas en filas (formato largo). Cada combinacion de id_vars + value_var genera una fila. Si value_vars es None, derrite todas las columnas no-id."
-tags: [datascience, tabular, melt, unpivot, transform, python]
+tags: [datascience, tabular, melt, unpivot, transform, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def merge_graphs(graphs: list[dict], entity_key: str = 'name', similarity_threshold: float = 0.85) -> dict"
 description: "Mergea multiples grafos de conocimiento en uno deduplicando entities por similitud de nombre (Levenshtein normalizado). Relaciones se re-apuntan a las entities canonicas. Atributos se combinan por union."
-tags: [graph, merge, deduplication, knowledge-graph, levenshtein, similarity, datascience]
+tags: [graph, merge, deduplication, knowledge-graph, levenshtein, similarity, datascience, pendiente-usar]
 uses_functions: [levenshtein_distance_py_cybersecurity]
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def min_max_scale(data: list) -> list"
 description: "Escala los valores al rango [0, 1] usando min-max normalization."
-tags: [normalization, scaling, python]
+tags: [normalization, scaling, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: impure
 signature: "def mrebel_base_load_model(model_name: str = 'Babelscape/mrebel-base', src_lang: str = 'es_XX', tgt_lang: str = 'tp_XX') -> tuple[Any, Any]"
 description: "Variante rapida de mrebel_load_model con checkpoint base (250M params, ~900 MB). Delega completamente en mrebel_load_model. Misma licencia CC BY-NC-SA 4.0 — solo uso no comercial."
-tags: [mrebel, relation-extraction, nlp, model, huggingface, multilingual, seq2seq, datascience, python]
+tags: [mrebel, relation-extraction, nlp, model, huggingface, multilingual, seq2seq, datascience, python, pendiente-usar]
 uses_functions: [mrebel_load_model_py_datascience]
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def ops_to_rdf_triples(db_path: str, namespace: str = 'http://osint.local/') -> list[tuple[str, str, str]]"
 description: "Convierte entities y relations de operations.db a triples RDF (subject, predicate, object). Prefija IDs con namespace para formar URIs. Solo stdlib."
-tags: [rdf, graph, osint, knowledge-graph, triples, operations, semantic-web]
+tags: [rdf, graph, osint, knowledge-graph, triples, operations, semantic-web, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def pearson(xs: list, ys: list) -> float"
 description: "Calcula el coeficiente de correlacion de Pearson entre dos listas de floats."
-tags: [statistics, correlation, python]
+tags: [statistics, correlation, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def pivot(rows: list[dict], index: str, columns: str, values: str, agg: str = 'sum') -> list[dict]"
 description: "Pivot table sin pandas. Agrupa por index, expande valores unicos de columns como nuevas columnas y agrega values con la funcion indicada (sum, count, mean, min, max, first, last)."
-tags: [datascience, tabular, pivot, transform, aggregation, python]
+tags: [datascience, tabular, pivot, transform, aggregation, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: impure
 signature: "def plot_heatmap_log(ax: Axes, xs: list[float] | np.ndarray, ys: list[float] | np.ndarray, extent: tuple[float, float, float, float], bins: int = 200, cmap: str = 'hot', alpha: float = 0.6) -> None"
 description: "Dibuja un heatmap 2D con escala log1p sobre un Axes de matplotlib. Usa np.histogram2d con el extent dado y ax.imshow para renderizar."
-tags: [visualization, heatmap, histogram, matplotlib, datascience, log]
+tags: [visualization, heatmap, histogram, matplotlib, datascience, log, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: impure
 signature: "def plot_kde_2d(ax: Axes, xs: list[float] | np.ndarray, ys: list[float] | np.ndarray, cmap: str = 'magma', alpha: float = 0.35, thresh: float = 0.02, levels: int = 30, bw_adjust: float = 0.6) -> None"
 description: "Dibuja un KDE 2D como contornos rellenos sobre un Axes de matplotlib usando seaborn.kdeplot. Si los arrays están vacíos retorna sin pintar."
-tags: [visualization, kde, density, seaborn, matplotlib, datascience]
+tags: [visualization, kde, density, seaborn, matplotlib, datascience, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: impure
 signature: "def rebel_load_model(model_name: str = 'Babelscape/rebel-large') -> tuple[Any, Any]"
 description: "Carga (y cachea) el tokenizer y modelo REBEL (BART-based, ~1.5 GB). Solo ingles. Licencia Apache 2.0 — uso comercial permitido. Cache por model_name."
-tags: [rebel, relation-extraction, nlp, model, huggingface, english, seq2seq, apache2, datascience, python]
+tags: [rebel, relation-extraction, nlp, model, huggingface, english, seq2seq, apache2, datascience, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def remove_words_from_column(values: Iterable[str | None], words: list[str]) -> list[str]"
 description: "Elimina palabras especificas de un iterable de strings usando regex de palabra completa (\\b). Case-insensitive. Colapsa espacios multiples y hace strip. None se convierte en cadena vacia. Sin pandas."
-tags: [text, cleaning, regex, words, nlp, datascience]
+tags: [text, cleaning, regex, words, nlp, datascience, pendiente-usar]
 params:
  - name: values
    desc: Iterable de strings o None a limpiar.
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: impure
 signature: "def render_sigma_html(graph_data: dict, output_path: str, title: str = 'OSINT Graph') -> str"
 description: "Genera un archivo HTML standalone con sigma.js v2.4 que visualiza un grafo OSINT. Aplica ForceAtlas2, dark theme, filtros por tipo de nodo y tooltip con metadata. Retorna el path absoluto del archivo escrito."
-tags: [graph, sigma, osint, visualization, html, forceatlas2, network, dark-theme]
+tags: [graph, sigma, osint, visualization, html, forceatlas2, network, dark-theme, pendiente-usar]
 uses_functions: [ops_to_sigma_json_py_datascience]
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def rolling_window(xs: list, size: int) -> list"
 description: "Genera ventanas deslizantes de tamanio fijo sobre una lista."
-tags: [windowing, timeseries, python]
+tags: [windowing, timeseries, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def standardize(data: list) -> list"
 description: "Estandarizacion Z-score: transforma los datos a media=0 y desviacion=1."
-tags: [statistics, normalization, python]
+tags: [statistics, normalization, python, pendiente-usar]
 uses_functions: []
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: impure
 signature: "def translate_es_to_en(text: str, tokenizer: Any, model: Any, max_length: int = 512, num_beams: int = 4) -> str"
 description: "Traduce texto espanol a ingles frase a frase usando MarianMT. Divide por boundaries de oracion, traduce cada una independientemente y une con espacio. Preserva nombres propios mejor que pasar el parrafo entero."
-tags: [marianmt, translation, es-en, nlp, datascience, python]
+tags: [marianmt, translation, es-en, nlp, datascience, python, pendiente-usar]
 uses_functions: [marianmt_es_en_load_model_py_datascience]
 uses_types: []
 returns: []
@@ -7,7 +7,7 @@ version: "1.0.0"
 purity: pure
 signature: "def words_to_dataset(texts: Iterable[str | None], min_ocurrencias: int = 1, eliminar_stopwords: bool = False) -> list[dict]"
 description: "Extrae palabras y sus ocurrencias de un iterable de textos. Tokeniza con \\b\\w+\\b, convierte a mayusculas, cuenta con Counter, filtra por minimo de ocurrencias y opcionalmente elimina stopwords en espanol. Sin pandas."
-tags: [nlp, text, words, frequency, counter, stopwords, spanish, datascience]
+tags: [nlp, text, words, frequency, counter, stopwords, spanish, datascience, pendiente-usar]
 params:
  - name: texts
    desc: Iterable de strings o None. Los None se ignoran silenciosamente.