데이터·AI 스킬

Design and improve the information an AI agent receives so it can work effectively within token limits. The skill covers context failures, compression, memory, multi-agent coordination, tool design, evaluation, and LLM-powered pipelines, with reference guides and analysis scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing context use in an agent system
• Investigating why an agent loses important information
• Designing memory or multi-agent workflows

Use Google Gemini to analyze audio, images, videos, and PDFs, or generate and edit images. Get results such as timestamped transcripts, summaries, extracted tables, answers about media, and images made from prompts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Transcribing audio with timestamps
• Finding information in images or screenshots
• Summarizing videos or asking about scenes

Build a persistent wiki from documents, papers, notes, or project documentation, then retrieve reusable evidence with source citations for agent tasks and recurring questions. It requires the llmwiki CLI or a connected llmwiki MCP server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a cited knowledge base from project documents
• Finding reusable evidence for an agent task
• Answering recurring questions from a document corpus

Set up or troubleshoot app install attribution across iOS and Android. Review privacy-aware signals such as SKAdNetwork and AdAttributionKit, MMP integrations, Google Play Install Referrer, conversion values, and deep links to clarify how campaigns connect to installs and revenue.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up install attribution for iOS or Android
• Troubleshooting missing campaign install data
• Designing SKAN conversion values around revenue

Analyze an app’s actual App Store Connect data synced through Appeeky Connect, including downloads, revenue, in-app purchases, subscriptions, trials, and country breakdowns. Compare time periods, spot trends or anomalies, and identify follow-up actions based on the app’s performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing app downloads across two periods
• Reviewing revenue, trials, or subscription trends
• Finding top countries by downloads or revenue

Set up an app measurement plan, choose useful events and KPIs, and interpret performance data across acquisition, engagement, retention, and revenue. It helps identify tracking gaps, organize dashboards, and turn metric trends into specific product or marketing decisions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning events to track in an app
• Choosing KPIs for app performance
• Reviewing acquisition and conversion funnels

Adds file-based tracking to LLM and agent experiments, recording conversations, tool calls, results, traces, and token or cost data. Includes viewers and comparison reports to inspect failed runs, replay episodes, and compare models or experiment variants across supported platforms.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspecting why an agent run failed
• Replaying and comparing experiment episodes
• Comparing models or experiment variants

Run and troubleshoot model inference on Fireworks AI through its direct API or the Leanmcp gateway. Compare models, configure SDK or HTTP clients, handle reasoning and tool-call responses, and test latency, concurrency, and failures across model runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a Fireworks model with tool-calling support
• Routing inference through a gateway for observability
• Debugging empty responses or cold deployments

Analyze tau2-bench task exports to pinpoint where an agent diverged from expected actions. Trace tool calls by conversation round, explain likely causes, check whether relevant knowledge-base documents were available, and cite transcript and source evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find the round where a benchmark task failed
• Compare actual tool calls with expected actions
• Check whether needed knowledge-base docs were available

Use Tinker to fine-tune models with supervised or reinforcement learning, then sample from, resume, or export checkpoints. The skill also covers inference, token-level training data, hyperparameters, and estimating run costs from Tinker's pricing information.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tuning a model on Tinker
• Preparing supervised training data with loss masking
• Running reinforcement learning or agentic RL

Create or revise agent skills with clear triggers and practical instructions. Review descriptions, diagnose skills that load too often or too rarely, check for overlap in a library, and test whether example requests select the skill appropriately.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing a new agent skill
• Improving an existing skill's trigger description
• Diagnosing missed or excessive skill activation

Plan and assess data migrations by profiling real source data, documenting field mappings, rehearsing at full volume, and reconciling counts and values. Use it to choose a cutover approach, manage exceptions, investigate incorrect results, and create an executable rollback plan.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a migration between systems
• Reviewing a migration plan or cutover approach
• Investigating incorrect numbers after migration

Diagnose why a prompt produces weak or inconsistent results, then rewrite its task, context, and output format. Create reusable prompts, compare different prompt styles, and retest when moving between AI models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fixing a prompt that misses the intended result
• Reducing variation across repeated runs
• Creating a reusable prompt for a regular task

Design warehouse layers, table grain, dimensions, and shared metric definitions for analytics. Use it to model new data sources, restructure marts, or investigate inflated results and slow queries, with guidance on history and query performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan a warehouse for a new data source
• Choose a table’s grain and structure
• Define metrics shared across dashboards

Use this skill to define an AI system’s intended use, evaluate its errors across user groups, plan monitoring and meaningful human review, and document its limits. It supports deployment and retirement decisions, especially when AI could affect consequential outcomes for people.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set evaluation criteria before deployment
• Investigate model behavior drift
• Plan monitoring and human review

Answer business questions with careful data analysis: define the decision, choose a meaningful comparison, inspect data quality, and check for common statistical traps. Report estimates, uncertainty, and limits so teams can review evidence before acting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running an analysis for a business decision
• Reviewing an analysis before acting on it
• Choosing a fair comparison for a metric

Use this skill to clarify what metrics mean, assign dataset owners, set access expectations, and check data quality and lineage. It helps teams resolve conflicting numbers, identify authoritative datasets, and make shared data easier to use responsibly.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resolve conflicting metric definitions
• Assign owners to datasets
• Set internal data access rules

Design and troubleshoot data pipelines that ingest, transform, and deliver reliable data. Get guidance on batch or streaming choices, safe reruns, delayed or duplicate records, data quality checks, and investigating unexpected changes in dashboard numbers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a new data pipeline
• Choosing batch or streaming delivery
• Adding checks for data quality

Build reports and dashboards around decisions people need to make. Structure metrics as drivers and outcomes, provide trusted self-serve analytics, show useful comparisons and data freshness, and review reporting so unused dashboards do not multiply.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a metrics framework for a business outcome
• Building a dashboard that answers a specific decision question
• Setting up governed self-serve analytics for common questions

Set direction for how an organization defines, governs, stores, and shares data. The skill helps resolve conflicting metrics, assess data quality for decisions, shape analytics capabilities, and establish governance for AI models, including what may be deployed and how it is monitored.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resolving conflicting numbers across teams
• Defining ownership and access rules for datasets
• Planning a data function or analytics platform

Use this skill to run social science analyses or read Stata and SPSS data. It reports estimates and uncertainty, checks code against a preregistration plan, verifies fixed random seeds, and reproduces results through R while flagging risks without certifying the analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reporting regression estimates without unsupported causal claims
• Checking analysis code against a preregistration plan
• Verifying fixed seeds in randomized analyses

Inspect large data files before reading their contents into an agent’s context. The skill returns a compact pointer with schema, shape, samples, and key values using bounded memory, so the agent can select specific rows, columns, or ranges to read.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspecting a large CSV before analysis
• Checking the structure of HDF5 or NetCDF data
• Sampling FASTQ, FASTA, or VCF files safely

Run compute jobs that need cloud CPUs, GPUs, or elastic capacity on Modal. The skill writes a function in the workspace, runs it with the user's authenticated Modal CLI, and saves outputs and run details for later traceability.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running a GPU job too large for a laptop
• Scaling a compute task without a Slurm cluster
• Saving remote job outputs to the workspace

Create a skill from an idea or improve an existing draft through test prompts, output review, and benchmarks that compare results. The workflow can also refine a skill description to help it trigger for the right requests. A later part of the source material was unavailable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting a skill from a workflow
• Testing and revising an existing skill
• Comparing skill results with benchmarks