「pipe flow」の検索結果

Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine". Activates when the coder agent is about to process N items with N LM calls (per-doc summarize, per-query retrieve, per-candidate rank, parallel tool fan-out). Encodes the *when*, *how many at once*, *what to do when one fails*, and *how to reduce* — not the API of any single framework. Cross-framework: LangGraph `Send`, CrewAI parallel tasks / Flow, `asyncio.gather`, `ThreadPoolExecutor`, LlamaIndex batch retrieval.

日本語の概要は準備中です。原文の説明を表示しています。

ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. The local `dspy` skill lists the modules but never surfaces the *selection criterion*: reasoning shape is chosen by task structure, not by reflexively defaulting to CoT. Activate every time a new LM-calling node/step is added to a pipeline. Do NOT activate for one-shot prompts, optimizer/teleprompter choice (that is the dspy SOP's job), or non-LM control flow. Search keywords: chain of thought vs ReAct, when to use CoT, reasoning type, ReAct vs CoT vs PoT, which dspy module, predict vs chain of thought.

日本語の概要は準備中です。原文の説明を表示しています。

SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipelines.

日本語の概要は準備中です。原文の説明を表示しています。

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor, DSPy optimizer-LM vs task-LM, vLLM speculative draft+target, LangGraph supervisor+worker are the same shape). Use when designing or cost-optimizing a pipeline that calls an LM many times, when deciding which steps need a strong reasoner vs a cheap executor, or when adding an escalation valve for when the cheap tier degrades. Search keywords: reduce LLM cost, cheaper model, lower token cost, model cascade, route to cheap model, strong model plus cheap model, LLM cost optimization.

日本語の概要は準備中です。原文の説明を表示しています。

LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.

日本語の概要は準備中です。原文の説明を表示しています。

Lab automation platform for Flex/OT-2 robots. Write Protocol API v2 protocols, liquid handling, hardware modules (heater-shaker, thermocycler), labware management, for automated pipetting workflows.

日本語の概要は準備中です。原文の説明を表示しています。

Digital pathology image processing toolkit for whole slide images (WSI). Use this skill when working with histopathology slides, processing H&E or IHC stained tissue images, extracting tiles from gigapixel pathology images, detecting tissue regions, segmenting tissue masks, or preparing datasets for computational pathology deep learning pipelines. Applies to WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows.

日本語の概要は準備中です。原文の説明を表示しています。

DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.

日本語の概要は準備中です。原文の説明を表示しています。

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

日本語の概要は準備中です。原文の説明を表示しています。

Use when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted inbound email. Always use this skill when the user wants to receive emails and act on them programmatically, even if they don't mention "agent" — the skill contains critical security patterns (sender allowlists, content filtering, sandboxed processing) that prevent untrusted email from controlling your system.

日本語の概要は準備中です。原文の説明を表示しています。

smina molecular docking CLI. AutoDock Vina fork with customizable scoring functions, native SDF/MOL2/PDB ligand input, autoboxing, local energy minimization, and per-atom score breakdowns. Pipeline: receptor PDBQT prep -> ligand prep (RDKit/OpenBabel) -> dock via autobox or explicit grid -> rescore/minimize with custom scoring -> rank poses by affinity. Choose smina over Vina when you need custom scoring terms (--custom_scoring), local optimization of an existing pose (--local_only), per-atom contributions (--atom_term_data), or SDF/MOL2 ligands without manual PDBQT conversion. For unknown binding sites use diffdock; for the Python-bindings/Vinardo workflow use autodock-vina-docking.

日本語の概要は準備中です。原文の説明を表示しています。

Three-tiered approach to omics data analysis (transcriptomics, proteomics) covering validated pipelines, standard workflows, and custom methods

日本語の概要は準備中です。原文の説明を表示しています。

Read, decompose, and analyze IEEE-style papers using routed technical-reading workflows. Use when extracting problem setting, object-method-condition logic, contributions, method pipeline, equations, datasets, baselines, metrics, ablations, limitations, replication details, citation role, related-work positioning, implementation notes, or reviewer-style assessment from a paper, PDF, abstract, or manuscript excerpt.

日本語の概要は準備中です。原文の説明を表示しています。

Create n8n workflow for daily task assignment from PTO engineer to foreman via Telegram bot with status reporting.

日本語の概要は準備中です。原文の説明を表示しています。

Develop and deploy Lakeflow Jobs on Databricks via DABs, Python SDK, or the CLI. Use when creating data engineering jobs with notebooks, Python wheels, SQL, dbt, or pipelines. Invoke BEFORE starting implementation.

日本語の概要は準備中です。原文の説明を表示しています。

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

日本語の概要は準備中です。原文の説明を表示しています。

Use when a paper needs publication-ready figures or a visual abstract. Makes ROC, forest, calibration, Kaplan-Meier and Bland-Altman plots, CONSORT/STARD/PRISMA flow diagrams, confusion matrices, pipeline diagrams and journal visual abstracts, checking the journal's AI-image policy first.

日本語の概要は準備中です。原文の説明を表示しています。

Use FlashRAG for retrieval-augmented generation research workflows: config/data validation, retrieval and index building, generation/refinement components, RAG pipelines/method reproduction, evaluation, and WebUI setup.

日本語の概要は準備中です。原文の説明を表示しています。

Use Hugging Face Evaluate to load metrics, comparisons, and measurements; compute and combine results; run evaluator pipelines; create custom modules; troubleshoot optional dependencies, cache, Hub, and CLI workflows.

日本語の概要は準備中です。原文の説明を表示しています。

Use Docling to convert, parse, configure, extract, chunk, serve, and maintain document-processing workflows across Python APIs, CLI commands, optional pipelines, and repository edits.

日本語の概要は準備中です。原文の説明を表示しています。

Routes DI-engine users to the right workflow for CLI/config launches, serial and framework-based RL pipelines, and environment integration.

日本語の概要は準備中です。原文の説明を表示しています。

Routes DataChain operating guidance for Python SDK pipelines, query expressions, CLI and Studio commands, agent-harness knowledge workflows, and repository maintenance.

日本語の概要は準備中です。原文の説明を表示しています。

Routes CogDL graph-learning workflows for experiments, graph data, models, training wrappers, and pipeline apps.

日本語の概要は準備中です。原文の説明を表示しています。

Routes Cognee AI memory platform tasks across SDK memory APIs, graph/RAG retrieval, configuration, custom pipelines, session memory, CLI, API, MCP, and deployment workflows.

日本語の概要は準備中です。原文の説明を表示しています。