TrueGradient Planning Analysis — nine skills that make Claude answer demand, supply and inventory questions from final, approved TrueGradient data only: forecast lookup with uncertainty intervals, accuracy and bias measurement, forecast-risk ranking, forecast-family change comparison, consensus versus TrueGradient forecast value add, disaggregation of top SKUs to series, components and warehouses, comparison of two runs of a planning pipeline, year-on-year comparison of actuals and forecasts, and supply/inventory analysis covering stock position, coverage, stockout timing, reorder plans and excess. Requires the TrueGradient connector, published in Claude's connector directory.
Plugin truegradient-forecast-plugin from marketplace truegradient in truegradient/tg-claude-connector-plugin. Commands read from the repo's manifest — 22 days ago.
consensus-comparisonCompare the planners' consensus forecast with TrueGradient's own forecast. Answers whether consensus added or removed accuracy against actual sales on past months (forecast value add), and how far apart the two are for the coming months, at any grain. Use this for "did consensus improve on the TG fo
forecast-accuracyMeasure TrueGradient forecast accuracy, bias, or error trend over past months — accuracy percentages computed as 1 − WMAPE, whether the forecast systematically over- or under-forecasts, and which products, categories, channels or regions are improving or worsening. Use this for "how accurate is our
forecast-changeCompare two TrueGradient forecast families within one experiment and report exactly what changed — for example the frozen baseline versus the current operational forecast, the model output versus a planner-reviewed view, or the operational versus the consensus forecast. Use this for "what changed si
forecast-disaggregationBreak a TrueGradient forecast down below the SKU. Split the top SKUs' forecast across their individual time series (ts_ids — each site, channel, region, city or platform the SKU is planned at) with each series' share, or down to component SKU and warehouse from the Disaggregated Forecast dataset whe
forecast-lookupLook up the final forecast, actual sales, or forecast uncertainty interval for a specific product, SKU, variant, category, brand, channel, customer, region, or time period from TrueGradient demand planning data. Use this when the user asks what the forecast or actual IS for something specific — "wha
forecast-riskRank which products, SKUs, variants, categories, brands, channels or regions carry the most forecast risk in TrueGradient, combining the stored accuracy, bias, volume-contribution and trust_zone columns so that material items rank above trivial ones and systematic error is told apart from volatility
snapshot-comparisonCompare two runs (snapshots) of the same TrueGradient planning pipeline and report what moved between them — the forecast for the same target months, the largest movers, items new or dropped, and actuals that were restated — by month, product, category, channel or region. Use this for "compare the l
supply-inventoryAnswer supply and inventory questions from TrueGradient inventory-optimization data — stock on hand, total inventory, days of cover, stockout timing, reorder plans, points and quantities, safety stock, in-transit, open POs and inbound supply, excess and dead stock, sales-loss exposure, working capit
year-on-yearCompare TrueGradient demand with the same months a year earlier — actual sales against last year's sales, and any forecast family (operational, ML, consensus, the locked plan) against last year's sales — by month, year to date, last twelve months or full-year outlook, in units or value. Use this for
truegradientconnects to: https://mcp-server.truegradient.ai/mcp
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Install the "AAS Data Analytics & Business Intelligence" editorial skill bundle for Claude Code.
16 skills
Databricks skills for the CLI, Apps, Lakebase, Model Serving, Lakeflow Jobs, Spark Declarative Pipelines, Declarative Automation Bundles (DABs), and classic-to-serverless migration.
37 skills · 2 commands · hooks
The official CCXT MCP server plus the ccxt-mcp usage skill — market data, balances and opt-in trading across 100+ crypto exchanges and prediction markets, with keys kept local.
1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.