OpenDCAI

DataFlow 开发专家上下文加载器。当用户在 DataFlow 仓库中进行开发时触发， 涵盖：新建算子/Pipeline/Prompt、诊断报错、规范审查、 以及感知仓库变更并建议更新知识库。 Trigger: user is developing in DataFlow repo, asks to create operator/pipeline/prompt, encounters errors, wants code review, or asks about operators.

Reasoning-guided pipeline planner that generates standard DataFlow pipeline code

Reference documentation for the BenchDatasetEvaluatorQuestion operator. Extended version of BenchDatasetEvaluator with question and subquestion support. Use when: evaluating answers with question context or multiple subquestions.

Reference documentation for the BenchDatasetEvaluator operator. Covers the constructor, two comparison modes (match/semantic), and pipeline usage. Use when: comparing predicted answers against ground truth answers in benchmark evaluation.

Reference documentation for the PromptedEvaluator operator. Use when: scoring text quality with LLM without filtering rows.

Reference documentation for the Text2QASampleEvaluator operator. Use when: evaluating QA pair quality across multiple dimensions.

Reference documentation for the UnifiedBenchDatasetEvaluator operator. Use when: evaluating model answers on benchmark datasets.

Reference documentation for the GeneralFilter operator. Covers the constructor, rule-based filtering logic, and pipeline usage notes. Use when: filtering rows based on column value conditions that can be expressed as lambda functions without LLM calls.

Reasoning-guided pipeline planner that generates standard DataFlow pipeline code

Reasoning-guided pipeline planner that generates standard DataFlow pipeline code. Use when the user asks to generate, create, or build a DataFlow pipeline, wants to process JSONL data with LLM operators, mentions PromptedGenerator / PromptedFilter / Text2MultiHopQAGenerator, or asks about DataFlow operator chains. Also use when user provides a .jsonl file and asks what pipeline to write.

DataFlow 开发专家上下文加载器。当用户在 DataFlow 仓库中进行开发时触发， 涵盖：新建算子/Pipeline/Prompt、诊断报错、规范审查、 以及感知仓库变更并建议更新知识库。 Trigger: user is developing in DataFlow repo, asks to create operator/pipeline/prompt, encounters errors, wants code review, or asks about operators.

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 OPERATOR_REGISTRY registration, generate DataFlowStorage-based CLI wrappers, or generate operator unit/registry/smoke tests.

Build reusable DataFlow prompt_template classes for existing operators with two-round AskUserQuestion intake, two-stage auditable outputs, and static acceptance checks. Trigger when users ask to generate/rewrite/optimize prompt_template or reuse operator logic with new prompt requirements.

DataFlow development expert context loader. Use when developing in the DataFlow repo: creating operators/pipelines/prompts, diagnosing errors, code review, or detecting repo changes to update the knowledge base. Trigger: user is developing in DataFlow repo, asks to create operator/pipeline/prompt, encounters errors, wants code review, or asks about operators.

Build production-grade DataFlow operator scaffolds (generate/filter/refine/eval). Use when users ask to create/new/scaffold operators, add OPERATOR_REGISTRY registration, generate DataFlowStorage-based CLI wrappers, or generate operator unit/registry/smoke tests.

Build reusable DataFlow prompt_template classes for existing operators with structured intake, two-stage auditable outputs, and static acceptance checks. Use when users ask to generate/rewrite/optimize prompt_template or reuse operator logic with new prompt requirements.

Use when turning a research idea, paper claim, hypothesis, or experiment request into a generated runnable experiment repository and validated handoff for exprun.

Use when expgen has produced an experiment handoff and the task is to execute, monitor, repair operational failures, and report full experiments.

Comprehensive code review guidance — process, checklist, feedback conventions. Use when the user asks about code review flow, review criteria, best practices, or how to give/receive review feedback.

Database operations runbook — backup, recovery, performance tuning, troubleshooting. Use for SQLite / MySQL / PostgreSQL ops questions, slow-query diagnosis, or outage response.

驱动 One-Eval 对「纯文本 LLM」做端到端评测。当用户想评测一个模型（API 或本地 vLLM）在某些 benchmark 上的表现、对比多个 benchmark 分数、补充多维度 metric、或生成图文评测报告时使用本 skill。

Solve a physics problem (text + optional figure) using the SciReasoner caption→reason→critic pipeline. Trigger when the user asks to solve, verify, or critique a physics problem that has a diagram, plot, circuit, or other figure.