Conception de pipelines NLP (tokenization, embeddings, NER, sentiment, summarization) — from general/workflow-pipelines
Constructs data transformation pipelines using Pandas and the pipe() method chain pattern. Integrates with SQLAlchemy for database I/O and PyArrow for high-performance Parquet…
Chains pandas DataFrame transformations into reproducible pipelines using pipe() method composition. Handles missing data imputation with fillna() strategies, type coercion with…
FASE 1 — BriefAgent. Recoge la idea de negocio y genera un brief estructurado BRIEF.json.
PipelineCRM integration. Manage data, records, and automate workflows. Use when the user wants to interact with PipelineCRM data.
Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
Corrige un probleme specifique identifie dans un rapport de validation du pipeline Argumentum, regenere les medias affectes, et valide jusqu'a resolution.
Generate predictive pipeline forecasts with confidence intervals and scenario modeling for revenue planning
FASE 2 — GroundTruthAgent. Documenta supuestos base clasificados (confirmado/estimación/pendiente).
Analyze pipeline health, identify stalled deals, predict close probability, and suggest actions to move deals forward. Improves forecast accuracy and prevents revenue leakage.
Use when checking data pipeline health, workflow status, Maestro failures, or generating a daily pipeline report.
Orchestre un cycle complet validate-fix-validate sur le pipeline Argumentum, jusqu'a resolution ou limite d'iterations. Chef d'orchestre des corrections.
Pipeline Monitoring Setup - Auto-activating skill for Data Pipelines. Triggers on: pipeline monitoring setup, pipeline monitoring setup Part of the Data Pipelines skill category.
Run a team formation's multi-stage pipeline end-to-end with role switching, handoffs, validation, and rollback.
FASE 6 — BuildAgent. Genera el documento final .md del plan de negocio completo.
Use when users want to install or set up the atelier-pipeline multi-agent orchestration system in their project.
Use when users want to remove the atelier-pipeline multi-agent orchestration system from their project.
Use when the user wants to update deal stages, values, or notes in their CRM pipeline, track pipeline velocity, or manage deal progression.
Content pipeline visualization — see all content at every stage from idea to published. Track ideas, drafts, in-review, scheduled, and published states.
Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced X…
Use this agent when you need to track revenue, build financial forecasts, model P&L projections, or analyze revenue trends.
Builds revenue forecasts — cohort-based, pipeline-driven, or SaaS metric-driven models with top-down and bottom-up approaches, growth scenarios, and revenue composition analysis.
Aggregate per-unit @risk tags into task-level risk vector. Propagates blast via LCI callers tree (depth 3, log2 amplification, cap 3). Max across units for d/s/r.
Classify task: (task spec + touched files) -> risk vector + verdict + pipeline tier. Applies 8-check trivial-bypass pre-filter; on bypass returns smoke tier.
Backfill @risk tags across codebase. Enumerates untagged (or stale, or all with --force) symbols via LCI, drains hook queue, processes in 10-wide parallel batches invoking…
Tag one code unit with @risk vector. Reads unit body + imports + LCI 2-level call graph, asks haiku-4.5 for JSON risk vector, escalates to sonnet-4.6 when conf<0.7 or any axis=3,…
Replay .risk-pipeline/telemetry.jsonl to surface calibration drift: false-skip rate (low-scored tasks with post-deploy bugs), over-review rate (high-scored tasks reviewers pass…
Builds production Scrapy spiders with custom Item Pipelines for data cleaning and storage. Uses scrapy.linkextractors.LinkExtractor for crawl scoping and ItemLoader with…
Builds composable image transformation pipelines using the Sharp library with operations like resize(), composite(), and toFormat().
Sklearn Pipeline Builder - Auto-activating skill for ML Training. Triggers on: sklearn pipeline builder, sklearn pipeline builder Part of the ML Training skill category.
Constructs and executes SDXL image generation pipelines using diffusers library and ComfyUI API. Supports LoRA loading, ControlNet conditioning, and batch prompt scheduling.
Node.js stream pipeline management with automatic cleanup. pump/pipeline error propagation, transform stream chains, backpressure handling, and preventing stream leaks when one…
\"Backfill @risk tags across codebase. Invokes risk-tag-sweep skill with supplied flags. Use --scope to narrow, --force to re-tag, --dry-run to preview. Resumable via --resume.\
Debugs Tekton pipeline failures by querying TaskRun and PipelineRun status via kubectl and the Tekton Results API.
Analyzes Tekton Pipeline and Task resource definitions using the Tekton Results API. Recommends CPU/memory request adjustments based on historical TaskRun metrics from Prometheus.
Assembles Tekton CI/CD pipelines from reusable Task and ClusterTask definitions using tkn CLI and Tekton Hub catalog.
教學影片 render + publish 跨平台 pipeline 共用規則 — 5 階段管線(工作目錄→對話⇆預覽→後製→發佈,對話⇆預覽 內部 iterative)/ 雙 mp4(16:9 + 9:16)/ 字幕用 Remotion 元件 / BGM/縮圖/配音 全 Remotion 自動 / YT 章節 / 全平台 public 預設 /…
Vertex Ai Pipeline Creator - Auto-activating skill for GCP Skills. Triggers on: vertex ai pipeline creator, vertex ai pipeline creator Part of the GCP Skills skill category.
10 data wrangling skills. Trigger: messy data, format conversion, missing values, data reshaping. Design: pipeline-oriented recipes for common data cleaning and transformation…
This skill empowers Claude to build AutoML pipelines using the automl-pipeline-builder plugin. It is triggered when the user requests the creation of an automated machine learning…
Design a high-level data pipeline for source-to-target data flows
Use when building or hardening a GitHub Actions pipeline for a
Build natural language processing pipelines for text analysis and understanding
Track build success rates and identify flaky tests from CI logs