Skill Claude CodeCodex
Reference documentation for the BenchAnswerGenerator operator. Covers the constructor, full run() signature, actual generation behavior, and integration notes for unified bench evaluation pipelines. Use when: generating model answers from benchmark question rows before passing the dataframe into…
Skill Claude CodeCodex
Reference documentation for the ChunkedPromptedGenerator operator. Covers the constructor, file-path based chunking flow, actual prompt construction, and output file writing behavior. Use when: the dataframe stores file paths, the file content may exceed a single LLM context window, and you want the generated results…
Skill Claude CodeCodex
Reference documentation for the EmbeddingGenerator operator. Covers the constructor, embedding serving requirements, actual dataframe flow, and runnable pipeline usage. Use when: converting one text column in a dataframe into embedding vectors for retrieval, clustering, similarity search, or downstream vector-based…
Skill Claude CodeCodex
Reference documentation for the FormatStrPromptedGenerator operator. Covers the constructor, prompt template restrictions, placeholder-to-column mapping, actual prompt-building logic, and runnable example usage. Use when: one generation task needs multiple dataframe columns combined into a single prompt through a…
Skill Claude CodeCodex
Reference documentation for the PromptedGenerator operator. Covers constructor parameters, run() signature, actual row-processing behavior, and pipeline usage notes. Use when: integrating PromptedGenerator into a DataFlow pipeline for single-field LLM generation.
Skill Claude CodeCodex
Reference documentation for the RandomDomainKnowledgeRowGenerator operator. [Purpose] Calls an LLM repeatedly with the same domain-generation prompt and writes the generated results into one column of an existing DataFrame. [When to use] Use it when you already have a seed DataFrame with the exact target row count and…
Skill Claude CodeCodex
Reference documentation for the RetrievalGenerator operator. [Purpose] Reads one text column from storage, forwards every non-empty row to llmserving.generatefrominput(...), and writes the returned list into a new output column. [Default backend] Use LightRAGServing by default. [Important] run() is async. The operator…
Skill Claude CodeCodex
Reference documentation for the Text2MultiHopQAGenerator operator. [Purpose] Generates multi-hop QA pairs from one text column and writes two output columns: one for qapairs and one for metadata. [When to use] Use it when you want reasoning-style QA pairs derived from longer text chunks. If only simple single-hop QA…
Skill Claude CodeCodex
Reference documentation for the PandasOperator operator. Use when: applying custom DataFrame transformations without LLM.
Skill Claude CodeCodex
Reference documentation for the PromptedRefiner operator. Use when: refining text with LLM, overwriting original column.
Skill Claude CodeCodex
A DataFlow development context guide for coding agents. DataFlow is a framework for building data-processing operators and pipelines.
Skill Claude CodeCodex
Build production-grade DataFlow operator scaffolds (generate/filter/refine/eval) for Codex and coding agents. Trigger when users ask to create/new/scaffold operators, add OPERATORREGISTRY registration, generate DataFlowStorage-based CLI wrappers, or generate operator unit/registry/smoke tests.
Skill Claude CodeCodex
Plan and write a standard DataFlow pipeline from a target and representative JSONL data. Use when a user asks to select DataFlow operators, trace field dependencies, generate runnable pipeline code, or repair a pipeline with schema or field-flow errors.
Skill Claude CodeCodex
Build reusable DataFlow prompttemplate classes for existing operators with two-round structured intake, two-stage auditable outputs, and static acceptance checks. Trigger when users ask to generate/rewrite/optimize prompttemplate or reuse operator logic with new prompt requirements.
Skill Claude CodeCodex
Promote exceptionally reviewed DataFlow pipelines into reusable task-pattern skills, or update an inferior same-task skill while preserving comparison evidence and history.
Skill Claude CodeCodex
Reuse a reviewed pipeline pattern for constructing benchmark-aligned math reasoning SFT records from question-and-answer datasets with verifiable final answers.
Skill Claude CodeCodex
Reasoning-guided pipeline planner that generates standard DataFlow pipeline code.
Skill Claude CodeCodex
Independently audit a generated DataFlow training-data pipeline and its trial artifacts with delegated rubric reviewers before it can be delivered or scaled.
Skill Claude CodeCodex
Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.
Skill Claude CodeCodex
Analyzer Skill is the Codex/Agent-facing capability for running LoopAI Analyzer independently. It analyzes evaluation outputs, writes Analyzer reports, emits stream events, returns unified success/error payloads, and can compare current results with a historical baseline.
Skill Claude CodeCodex
A configuration and runtime-status tool for LoopAI tasks. It handles task settings and shows where task nodes are in their execution history.
Skill Claude CodeCodex
Skill "Judger" from OpenDCAI/Dataflow-LoopAI, covering judger skill, purpose, how to invoke, configuration and 全局字段（state["judger"] 顶层，所有 bench 共享）.
Skill Claude CodeCodex
Use this skill when the user wants LoopAI to validate training data, generate and approve training YAML, run LLaMA-Factory SFT or Verl GRPO, configure rewards, monitor or reconnect to Trainer workers, compare checkpoints, export a trained model, or inspect Trainer failures from starter.yaml or runtime state.
Skill Claude CodeCodex
Use this skill when LoopAI needs dataset discovery, acquisition, web-page collection, DataMixer lakehouse operations, data processing, indexing, recipe planning, or production training-data export. In long-running Codex SDK loops, when Analyzer produces an analysis report, failure taxonomy, or user request that…