'jsonl' 검색 결과

Adapt large language models to specific tasks through fine-tuning, or additional training. Prepares and validates datasets, configures LoRA or QLoRA to train a small subset of parameters, and supplies training settings, evaluation scripts, and deployment optimization guidance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing and validating JSONL training data
• Choosing LoRA or QLoRA for available GPU memory
• Configuring training and monitoring overfitting

Generate videos from DEFT media samples using PAIDF Cosmos Predict. Prepare configuration, run generation in Docker, avoid repeated processing of duplicate media paths, and produce JSONL records linking each original sample ID to successful or missing video outputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generating synthetic videos for DEFT media samples
• Avoiding repeated generation for duplicate media paths
• Passing generated video mappings to downstream workflows

Submit groups of AI requests as batch jobs with the OmniRoute command line. Manage input files, monitor or cancel jobs, save results and errors, and incorporate batch processing into automated build and deployment workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Submitting AI requests from a JSONL file
• Monitoring batch jobs and waiting for completion
• Saving batch results and error details

Recover context from local coding-agent transcripts and produce a checkpoint covering the objective, completed work, blockers, and next step. Explicit import requests support read-only recovery, with continuation governed by the current workspace rules and the user's request.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recover context using a session ID
• Summarize unfinished work from local logs
• Review JSONL exports or Markdown handoffs

JSONL比例切分工具。读取JSONL数据集，按给定比例拆成多个子集，支持随机切分和按字段分层切分。 当用户明确提到按比例拆分JSONL、训练集/验证集/测试集切分、分层保持类别分布等需求时使用此skill。 即使用户没有明确说出"切分"，只要任务是把一份JSONL按比例分成多个子集，就应该使用此skill。 不负责按固定条数均匀分块，不负责按份数切块，也不负责处理非JSONL输入。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Prepare datasets for language model training by formatting examples, checking conversation templates, and packing examples into training sequences. Document data sources, synthetic data ratios, and validation results in a dataset card before starting a run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert raw examples into training-ready JSONL
• Check conversation templates and assistant-only training targets
• Review example boundaries after sequence packing

Investigate difficult bugs by adding temporary logs to the actual execution path and reproducing the reported behavior. Analyze JSONL logs, which store one structured event per line, then fix the cause, verify regression tests, and remove debugging artifacts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating bugs that occur only during manual use
• Tracing event order in streaming or concurrent operations
• Checking whether passing tests cover the reported bug

Analyze gh-aw execution traces, which record individual processing steps, to investigate slow or failing workflows. Using local JSONL files or telemetry backends, the skill checks timing, errors, missing attributes, and trace connections to support focused improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating slow workflow or agent runs
• Comparing errors across workflows and execution engines
• Finding missing trace attributes or broken connections

JSONL 随机采样工具。读取 JSONL 数据集，按抽样数量或抽样比例无放回抽取样本，输出保留原字段结构的采样结果。 当用户提到随机采样、按数量抽样、按比例抽样、JSONL 抽样筛查等需求时使用此skill。 即使用户没有明确说出"random_sampler"，只要任务涉及对 JSONL 记录做无放回随机抽取，就应该使用此skill。 不负责分层采样、领域均衡采样、表格采样或其他格式转换。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

영업 에이전트 작업을 한 차례 시험 실행합니다. 운영 전에 템플릿과 예산 설정을 검증하고 담당별 지시문과 실행 결과 기록을 확인합니다.

• 영업 자동화 한 주기 시연
• 템플릿과 에이전트 유형 검증
• 예산 상한과 예약 처리 점검

Turn local Q&A session files into an English weekly report with topic rankings, unresolved issues, activity metrics, and comparisons with the previous week. Include supporting message excerpts and structured data for later document and dashboard rendering.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a weekly community Q&A report
• Compare topics and activity with the previous week
• Review unresolved high-priority issues

Reproduce Mastra Code bugs with a real model and compare timestamped logs across network, streaming, execution, and terminal interface layers. Use the evidence to locate timing problems, incorrect token rates, flicker, or stuck status displays.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating incorrect token rate displays
• Reproducing intermittent bugs with a real model
• Tracing flicker or stuck status displays

Prepare to fine-tune open models or Gemini models on Agent Platform. Check the environment, convert and validate training data, choose supported models and settings, and estimate tuning costs for open models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether an Agent Platform tuning environment is ready
• Converting and validating training datasets
• Choosing models and training settings for a task

Preserve the context of long Claude Code sessions across compaction, which shortens conversation history. Create a restore map linking decisions, files, and next steps, then use ranked readings and targeted transcript lookups to rebuild working context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a restore map before conversation compaction
• Rebuilding working context after /compact
• Preserving decision history across long-running work

onboarding workflow for creating datasets and applications in Viking AI Search. Supports one-time import from local files (JSON, JSONL, CSV) and MySQL databases, plus scheduled incremental sync for append-only JSONL files and MySQL. All sources are first exported to a bootstrap JSONL file; backend-driven schema inference handles detection, and optional background sync keeps the dataset up to date as new data arrives.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Analyze pi (coding-agent) session JSONL and ego-benchmark-harness run artifacts to explain slow or failed individual tasks, compare execution-path differences between agents or browser tools, and count tool calls and error types. Use this skill whenever users ask to analyze a pi session, explain why a task was slow or failed, compare two runs, investigate an error, locate the session corresponding to tasks.jsonl, inspect an agent execution path, count tool calls, analyze a run ID, or perform any forensic or retrospective analysis of JSONL under ~/.pi/agent/sessions/ or agent-home/.pi/agent/sessions/.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

대규모 언어 모델의 답변을 채점하는 평가 세트를 만들고 실행합니다. 진행 상황과 개별 답변의 통과 여부를 확인하고, 모델 비교나 CI의 품질 판정에도 활용합니다.

• 입력과 예상 답변으로 평가를 만듭니다
• 평가 진행 상황을 확인합니다
• 실패한 답변과 점수를 조사합니다

Claude Code 세션 로그에서 모델별 토큰 사용량과 미국 달러 비용을 집계해 AgentDB에 저장합니다. 작업 후 비용을 기록하고 보고서용 데이터를 축적할 수 있습니다.

• 작업이 끝난 시점에 비용을 기록합니다
• 세션 종료 시 사용량을 저장합니다
• 긴 작업 중 비용을 정기 집계합니다

Delegate a clearly scoped repository analysis or implementation task to Pi without an interactive session. The skill limits the working directory and available tools, then checks structured output for errors before using the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delegate a read-only code diagnosis to Pi
• Assign Pi an explicitly authorized implementation task
• Check Pi's structured output for model or tool failures

Delegate code analysis and implementation to Codex CLI without an interactive session. The skill reads ordered output events, extracts the final agent response, and reports errors, with a read-only sandbox used by default.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review code in a read-only sandbox
• Delegate implementation to Codex
• Get a second coding agent's assessment

Delegate repository analysis and coding tasks to GitHub Copilot CLI without an interactive session. The skill reads structured output, checks errors, and summarizes the final result along with any denied tool requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Ask Copilot to explain a failing test
• Delegate repository analysis to Copilot
• Request code changes with narrowly scoped tool permissions

Delegate a clearly scoped repository task to Kimi Code without opening its interactive interface. The skill reads structured execution events, extracts the final response, and checks for errors, with separate handling for read-only work and authorized changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delegate changes to specific files
• Inspect a repository using a read-only copy
• Extract Kimi Code's final response and check errors

Search the agent’s conversation history by topic or date to retrieve relevant past entries. Inspect neighboring records when needed to understand the surrounding discussion, using the history log specified for the agent’s workspace.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding an earlier conversation about a topic
• Looking up conversation records by date
• Checking context around a matching entry

Turn documents, notes, research, or code into a knowledge graph that maps identifiable things and their relationships. Create or update entity files and typed connections, with source evidence attached for inspection and later visualization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Map people and organizations across documents
• Organize research with traceable evidence
• Map relationships between software modules