Data & Analytics

lingtai-ai Bundle

Nested system-manual reference for the additive SQLite/`log.sqlite` sidecar over LingTai's JSONL runtime traces. Read it when you need `lingtai-agent log doctor|query|rebuild`, read-only SQL safety and WAL/rebuild caveats, the events/chat_entries/token_entries schema, quick-start snippets, SQL recipes (`tool_call_id` lifecycle, tool result stats and percentiles, spilled/large tool results), gotchas, or the redaction rules. Runtime trace forensics start here; trajectory mining is the sibling `trajectory-mining`.

mr-kelly Bundle

Personal finance anomaly review desk (Busabase App-in-Skill) that imports the three business tables — orders, invoices, payments/receipts (回款) — from CSV/JSON exports, flags anomalies with deterministic rules, and runs a human review queue with auditable decisions. Use when the user invokes $kelly-audit or /kelly-audit, mentions finance audit, order invoice payment reconciliation, 对账, 应收, 回款, 发票异常, receivables aging, overdue receivables, duplicate payments, missing invoices, amount mismatches, or anomaly review.

alecs5am Skill

Publish or schedule a finished Ralphy Unit through the active workspace's saved Postiz connection. Prepares the target-shaped title, description, body, CTA, hashtags, thread parts, and required Postiz settings, then calls `ralphy publish` and records provenance for later analytics. USE WHEN the user asks to "publish this", "post it now", "schedule this post", "send this to Telegram", "post this thread to X", "publish the reel", or "put this on YouTube/Instagram". DO NOT FIRE for copy-only requests with no posting intent; use social-copy instead.

codealive-ai Bundle

Raw PostHog data queries via MCP — event catalog, query recipes, dashboards, funnels, experiments. Use for specific data questions. For CEO-level metric interpretation and frameworks, use metrics-briefing instead.

nearai Skill

Microsoft 365 business workflow patterns for the IronClaw agent. Covers Outlook email, Excel data operations, Teams channel communication, Word and PowerPoint document generation, and SharePoint and OneDrive file management via Microsoft Graph.

nearai Skill

Comprehensive YouTube intelligence, comment sentiment analysis, video transcript summarization, creator channel auditing, and engagement analytics using the youtube tool.

prone-dc302 Skill

This skill should be used when the user asks about "data journalism", "data visualization", "data storytelling", "FOIA request", "RTI request", "spreadsheet analysis", "chart design", "act as a data journalist", "data journalist mode", "infographic", "open data", "statistical analysis for journalism", "investigative data", "public records", "Datawrapper", "Flourish", "Tableau Public", "D3.js", "chart type selection", or needs expertise in finding, analyzing, and visualizing data for journalistic storytelling. Part of the AlterLab FC Skills collection (New Media & Communication department).

prone-dc302 Skill

This skill should be used when the user asks about "statistics", "statistical analysis", "SPSS", "R statistics", "hypothesis testing", "t-test", "ANOVA", "chi-square", "regression analysis", "correlation", "p-value", "effect size", "confidence interval", "descriptive statistics", "inferential statistics", "data visualization", "act as a statistics guide", "statistics guide mode", "statistical significance", "research statistics", "quantitative analysis", "normal distribution", "sample size", "power analysis", "non-parametric tests", "Mann-Whitney", "Kruskal-Wallis", "Likert scale analysis", "survey data analysis", "Excel statistics", "JASP", "factor analysis", "reliability analysis", "Cronbach's alpha", "research data analysis", or needs expertise in applying statistical methods to academic research data. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).

wyattowalsh Bundle

Gmail copilot via MCP. Triage, inbox-zero, filters, analytics, labels, cleanup. Use when managing email or automating Gmail. NOT for composing emails, calendar, or non-Gmail.

wyattowalsh Bundle

Design event-driven systems: contracts, topics, consumers, retries, idempotency, and sagas. Use for asynchronous workflows. NOT for CRUD APIs or ETL pipelines.

dragoon0x Skill

Understand what product metrics actually mean in context. A 3% conversion rate can be amazing or terrible depending on product type, stage, and market. Provides contextual benchmarks and interpretation frameworks. Use when evaluating whether a metric is good or bad, reporting to stakeholders, or when a metric changes unexpectedly.

dragoon0x Skill

Diagnose why users drop off at specific funnel steps. Moves beyond 'conversion is low' to identifying root causes and recommending specific fixes. Use when a funnel step has unexpectedly low conversion, overall funnel has degraded, or launching a new flow.

dragoon0x Skill

Analyze retention by cohort to understand how and why users stick around or leave. Moves beyond vanity metrics like MAU to actionable retention insights. Use when retention looks bad and you don't know where to focus, measuring impact of product changes, or comparing retention across segments.

snowflake-labs Skill

Register source code into the migration project — either by extracting from a live database or importing local SQL files.

snowflake-labs Bundle

Surface assets the conversion engine doesn't generate (FiveTran, dbt, Airflow, SSAS cubes, Oracle PL/SQL packages, custom shell scripts, etc.) and register them as code units with `kind=custom` and a free-form `customKind` discriminator (any string outside the reserved Kind enum) so the orchestration layer (next_object + state machine) tracks them alongside built-in units. Triggers from the setup state machine as its last step; can also be re-entered any time the user identifies more custom assets.

snowflake-labs Skill

Flags migration anti-patterns (performance, architecture/security, behavior) by running `scai assessment anti-patterns`, which buckets SnowConvert's recorded issue codes and writes JSON for the assessment multi-report. Supports SQL Server and Redshift.

snowflake-labs Bundle

Analyze SSIS packages from SnowConvert ETL.* outputs and source .dtsx files. Classifies packages, scores migration complexity, and produces JSON for the parent assessment multi-report.

snowflake-labs Skill

Generates migration effort estimates by running `scai assessment effort-estimate`, which writes JSON for the assessment multi-report. Supports SQL Server and Redshift.

snowflake-labs Bundle

Analyze SQL object dependencies and create deployment waves/partitions for database migrations. Use when working with SQL migration planning, SnowConvert outputs, or deployment wave creation.

snowflake-labs Skill

Stabilize an ETL code unit (SSIS, Informatica, or other platforms) by handing the converted artifacts off to etl-stabilization and recording the result on the registry entry.

snowflake-labs Bundle

Preview. Convert SAS code to Snowflake SQL and stored procedures. Use for: DATA steps, PROC SQL, macros, PROC steps, EGP projects (extracted .sas files only). Triggers: convert SAS, migrate SAS, SAS to Snowflake, translate SAS code, SAS migration, SAS analysis, SAS dependency diagram, validate SAS conversion. Note: For .egp files, extract the embedded .sas code first using SAS Enterprise Guide export.

snowflake-labs Bundle

SQL Server Connection Skill

snowflake-labs Skill

Preview. Attach converted Snowflake SQL to existing SAS Code Unit Registry entries so scai test can validate them. Reads conversion_state.json, sets files.converted + confirms objectType from the generated SQL, stamps codeStatus.conversion. Skill-side JSON only — no SnowConvert dialect, no .NET registry engine. Triggers: attach converted SAS SQL, register converted SAS, complete SAS CUR, make converted SAS testable, scai test SAS validate.

snowflake-labs Bundle

Analyze Informatica Power Center workflows/mappings from SnowConvert ETL.* outputs and source XML files. Classifies workflows, scores migration complexity, and produces JSON for the parent assessment multi-report.

snowflake-labs Skill

Find applicable migration rules for a SQL file using Snowflake. Combines regex pattern matching (REGEXP_LIKE) with Cortex semantic search.

snowflake-labs Bundle

AI-First convert path for ETL platforms SnowConvert does not natively support. Identifies elements, hydrates IR, runs verification gates, and emits dbt output with honest degradation exit codes. Use when convert routes unsupported ETL to the AI-first migrator. Sibling of etl-stabilization (post-convert repair).

snowflake-labs Bundle

Analyzes Dynamic SQL occurrences from SnowConvert issues, classifies patterns, scores complexity, and records migration considerations. Use for SQL Server, Redshift, Oracle, or Teradata to Snowflake migrations. Driven entirely by `scai assessment sql-dynamic`; no custom scripts.

snowflake-labs Bundle

Generate two-sided synthetic data tests (source + Snowflake) for migrated stored procedures and functions. Derives test scenarios from source SQL branch analysis, writes step-based validation YAML artifacts, and enriches them with isolation metadata. Use when generating or refreshing test cases for a migrated object. Delegates object repair to migrate-object. Triggers: generate tests, create tests, write test YAML, test generation, synthetic tests.

snowflake-labs Bundle

Drive the workload-scoped Synthetic Testbed Generator through its MINE → VALIDATE → ENRICH → COMPILE → GENERATE phases for a migration. Sequences `scai testbed init` → `list-unsolved` (mine) and surfaces the categorized unsolved-constraint view; `scai testbed validate` and surfaces the readiness view (fk gaps / type conflicts / unsatisfied constraints); `scai testbed compile` and surfaces the cluster summary; runs the two-pass ENRICH reasoning (structural then value prompts) that turns unsolved constraints into enrichment JSON; `scai testbed generate` (readiness-gated) and surfaces the row counts + CSV/manifest deliverable. Resumes each phase after a kill by recomputing from on-disk state. Reads machine-readable JSON views; mutates state only through scai testbed subcommands, never the opaque state.bin. Triggers: generate testbed, mine testbed, validate testbed, compile testbed, enrich testbed, run testbed phases, resume testbed, inspect unsolved constraints, testbed data source. Runs the two-pass ENRICH phas

snowflake-labs Skill

Fix dbt models via iterative compile-fix loop. Scoped to dbt projects assigned to the current phase. Use when the stabilization skill invokes dbt fixing.

snowflake-labs Skill

Preview. Validate a completed SAS to Snowflake conversion by comparing expected SAS output against actual converted SQL output using synthetic test data. Performs dual-execution comparison: LLM traces original SAS logic to produce baseline, then runs converted SQL on Snowflake and compares outputs cell-by-cell. Triggers: validate conversion, verify sas migration, test conversion, compare sas output.

snowflake-labs Skill

Generate dbt tests (seeds, schema tests, singular assertions) for ETL-to-Snowflake ETL dbt sub-projects. Scoped to dbt projects assigned to the current phase. Use when the stabilization skill invokes dbt test generation.

snowflake-labs Bundle

Derive source-of-truth functional-equivalence assertions for ONE converted Informatica-to-Snowflake-Scripting mapping procedure (data-flow), independent of the converted SQL. Seeds input, deploys+CALLs the proc in an isolated test schema, and grades its target table against expected contents computed from the source mapping. Use when the stabilization skill invokes test generation for a scripting-flavor mapping proc.

snowflake-labs Skill

Fix orchestration elements with EWI issues using test-file workbench. Scoped to elements assigned to the current phase. Use when the stabilization skill invokes fixing for an orchestration phase.

timdevai Bundle

Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B customer-data-as-asset valuation and M&A readiness, data team org evolution. Use when deciding whether to train models on customer data, choosing data architecture, valuing data for fundraising or M&A, sequencing data hires, or when user mentions CDO, chief data officer, data strategy, data mesh, lakehouse, training data, data product, data monetization, or customer data asset. NOT a tactical data engineering skill — strategic decisions only.

jaechang-hits Skill

Query and download NCI Imaging Data Commons (IDC) cancer radiology and pathology datasets via the idc-index Python client. No authentication required: the parquet index ships inside the pip wheel, SQL runs locally via DuckDB, and DICOM downloads stream from public S3/GCS buckets through s5cmd. Use sql_query() for DuckDB cohort selection, get_collections/get_patients/get_dicom_studies/get_dicom_series for hierarchical browsing, download_from_selection() for downloads, and get_viewer_URL() for OHIF/Slim links. Use pydicom-medical-imaging for local DICOM reading; histolab for whole-slide pathology preprocessing.