Data & AI skills

Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.

The English summary is being prepared. Showing the original description.

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key constraints, OCC retry patterns, ORM migration (Django/EF Core/Hibernate/Rails/SQLAlchemy), DDL operations, query plan explainability, system diagnostics via CloudWatch AAS, SQL compatibility validation, and bulk data loading. Load before answering DSQL limit or error-code questions; it has limits docs omit. Triggers on phrases like: DSQL, Aurora DSQL, distributed SQL database, serverless PostgreSQL-compatible database, migrate to DSQL, DSQL query plan, DSQL EXPLAIN ANALYZE, DSQL ENUM, DSQL foreign key, DSQL OCC retry, DSQL multi-region, DSQL JSONB, DSQL GIN index, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader, DSQL slow, DSQL performance, DSQL wait events, DSQL AAS.

The English summary is being prepared. Showing the original description.

分析用户提供的表格、CSV 文本或统计结果，核对数据质量和指标口径，形成可复核的数据洞察。

The English summary is being prepared. Showing the original description.

Answer prediction questions using market trading data, not opinions. Use when the user asks probability questions about geopolitics, economics, markets, industries, or any topic where real money is being traded on the outcome. Examples: 'What's the probability of WW3?', 'Will there be a recession?', 'Is AI in a bubble?', 'When will the Russia-Ukraine war end?', 'Is it a good time to buy gold?', 'Will SPY drop 5% this month?', 'Is NVDA options premium overpriced?'. The skill reads prices from prediction markets, commodities, equities, options chains, derivatives, yield curves, and currencies, then cross-validates multiple signals to produce a structured probability report.

The English summary is being prepared. Showing the original description.

Streaming data lines — a flowing techy backdrop. A bold, canvas-based effect from Open Design's html-ppt fx pack — for slides and launch videos. Guards prefers-reduced-motion (does not start). One per screen; on web use sparingly.

The English summary is being prepared. Showing the original description.

Check live performance KPIs from connected analytics: RAG status, trends, actions. "quick performance snapshot"

The English summary is being prepared. Showing the original description.

Write a stakeholder performance report from data. Sudden spikes → anomaly-scan. "write the monthly performance report"

The English summary is being prepared. Showing the original description.

Send a performance report to Slack, email or Sheets from connected analytics, approval-gated. "send the weekly report to Slack"

The English summary is being prepared. Showing the original description.

Export marketing data to a warehouse or Sheets, PII-redacted, approval-gated. "export contacts to a sheet"

The English summary is being prepared. Showing the original description.

Import CSV or Sheets data into a CRM or ESP with mapping and dedup, approval-gated. "dry-run this import first"

The English summary is being prepared. Showing the original description.

Design the analytics layer with script-backed benchmarks: KPI trees, report templates, MMM, cookieless. "define our KPIs"

The English summary is being prepared. Showing the original description.

Design an attribution model and credit rules. Real path data → attribution-report. "set up multi-touch attribution"

The English summary is being prepared. Showing the original description.

Write a white-labeled report for one client from tracked data. All clients → agency-dashboard. "prepare the monthly client report"

The English summary is being prepared. Showing the original description.

Use when authoring a Relayflows flow (@relayflows/surface / @relayflows/sdk, the journal-based v2 engine — the CLI is `flows`, package versions 2.0.x) in TypeScript or YAML/JSON. Covers the three-rung ladder (run/llm/agent), the resident verbs (human/dispatch/done), verification gates, TypeScript vs YAML authoring, per-step cli/model selection and its resolution order, flows.json, and `flows check`/`run`/`resume` with their real refusal shapes and exit codes. Not for the older, unrelated `@relayflows/core` WorkflowBuilder engine (`.pattern('dag')`/.agent()/.step() chains) that `writing-agent-relay-workflows` and `migrating-persona-to-relayflow` cover — that's a different product despite the similar name.

The English summary is being prepared. Showing the original description.

World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations.

The English summary is being prepared. Showing the original description.

Analyzes social media campaign performance across platforms with engagement metrics, ROI calculations, and audience insights for data-driven marketing decisions

The English summary is being prepared. Showing the original description.

Generate structured reflection prompts for a specific teaching experience or professional learning challenge. Use when debriefing lessons, journaling, or preparing for coaching conversations.

The English summary is being prepared. Showing the original description.

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task. Use when developing students' thinking-about-thinking during independent work.

The English summary is being prepared. Showing the original description.

Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read material passively without engaging with underlying principles.

The English summary is being prepared. Showing the original description.

Design a learning sequence teaching prompt quality — comparing vague vs. refined prompts to show why specificity and context transform AI output. Use when students use AI without understanding why output quality varies.

The English summary is being prepared. Showing the original description.

Interpret learning analytics data and translate dashboard findings into actionable teaching decisions. Use when reviewing LMS data, quiz patterns, or engagement metrics.

The English summary is being prepared. Showing the original description.

Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change help," or prompt regression testing. Outputs per-dimension win rates with statistical significance using OpenJudge PairwiseAnalyzer.

The English summary is being prepared. Showing the original description.

Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.

The English summary is being prepared. Showing the original description.

Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating graders from data, and analyzing results (pairwise win rates, statistics, validation metrics). Use when the user wants to evaluate LLM outputs, compare multiple models, design scoring criteria, or build an automated evaluation system.

The English summary is being prepared. Showing the original description.