Data & Analytics

amey-thakur Skill

Use ORMs for their productivity while avoiding N+1 queries and knowing when to drop to raw SQL. Use when working with an ORM or debugging the performance problems ORMs quietly cause.

amey-thakur Skill

Build spreadsheet models that are auditable and hard to break, separating inputs, calculations, and outputs. Use when modelling finances, forecasts, or scenarios.

amey-thakur Skill

Instrument search so queries, clicks, and abandonment tell you what to fix. Use when improving relevance without evidence, or when nobody can say whether search works.

amey-thakur Skill

Measure support with metrics that reflect customer outcomes rather than agent activity, and use them to reduce ticket volume. Use when support is measured by throughput and quality is drifting.

amey-thakur Skill

Partition datasets by pruning-friendly keys with healthy file sizes and scheduled compaction. Use when laying out lake or warehouse tables, or fixing slow scans and small-file explosions.

amey-thakur Skill

Constrain what can be entered into a spreadsheet so errors are prevented at input rather than found in analysis. Use when a spreadsheet is filled in by people.

amey-thakur Skill

Model warehouse tables with explicit grain, conformed dimensions, and deliberate SCD handling. Use when designing analytics schemas or fixing double-counted metrics and unjoinable tables.

amey-thakur Skill

Automate repetitive spreadsheet work with scripts, knowing when the task has outgrown a spreadsheet entirely. Use when the same manual steps are repeated on a schedule.

amey-thakur Skill

Diagnose and fix slow spreadsheets by reducing volatile formulas, whole-column references, and unnecessary recalculation. Use when a workbook takes seconds to respond to an edit.

prism-shadow Skill

Solve Atlas Commerce Operations analytical and controlled-correction tasks that provide a prompt, request payload, JSON answer contract, schema/data dictionary access, and SQL-style workplace data. Use for fulfillment, refund, carrier-scan, warehouse productivity, support health, or similar operational scorecards requiring exact JSON output, event-derived state at a cutoff, imported-row deduplication, FX conversion, risk classification, ranked exceptions, or approved canonical data corrections.

prism-shadow Skill

Use for Atlas Commerce Operations tasks that require producing exact JSON analytics or applying approved minimal data-quality corrections from workplace schema, dictionary, SQL data, and request payloads.

prism-shadow Bundle

Analyze the Atlas Commerce Operations workplace and produce one JSON answer object that exactly conforms to a provided JSON-Schema answer template, using the live authenticated SQL/transaction service. Use for fulfillment, refund, carrier-quality, warehouse-productivity, support-health, and similar operations scorecard requests that ship a prompt, a *_request.json (scope + business definitions + decision rules), and an answer_template.json.

prism-shadow Bundle

Produce JSON readouts (portfolio-mix, SLA-aging, or release-readiness) from a shared work-item portfolio environment exposed over REST + a restricted SQL endpoint. Use when a task points at a shared portfolio environment containing work items, mix targets, SLA policy, releases/milestones/blockers/dependencies and asks for a single JSON object matching a provided answer_template.json. Knows the environment's stale-field traps (mirror_status, legacy_category), primary-vs-duplicate-vs-cancelled record handling, the portfolio category classification convention, and the exact ordering/precision rules each template requires.

prism-shadow Bundle

Analyze an engineering work-item portfolio against the shared portfolio environment (HTTP API + SQL endpoint; base URL and token live in environment_access.md). Use for portfolio-mix gap reviews, SLA aging/breach audits, and release-readiness assessments. Encodes the authoritative-status-over-mirror, primary-vs-duplicate, cancelled/distractor exclusion, 4-category resolution, stable ordering, and exact rounding rules so the single JSON answer matches the provided answer_template.json schema.

prism-shadow Bundle

Answer Cedar Ridge Intake Coordination Portal tasks: read a task prompt plus its input/payloads/answer_template.json, query the read-only portal (REST + POST /query SQL) at the base URL in environment_access.md, apply the intake decision rules, and return ONE JSON object that exactly matches the template. Covers patient access verification, referral readiness audits, dialysis transfer reviews, program enrollment panels, and referral-to-chart activation. Use whenever a prompt points at the "Cedar Ridge Intake Coordination Portal" or a roster/batch/program id (e.g. NPI-*, ORTHO-*, PULM-*, DIAL-*, a program code) with an answer_template.json to fill.

prism-shadow Bundle

Produce structured JSON decisions for state licensing review tasks backed by the shared licensing data service (contractor application batches, restricted liquor license staff packages, and alcohol renewal manual-review queues). Use when a prompt asks you to review licensing records over a network environment and return JSON that must conform to an answer_template.json, especially when the prompt names contractor applications (C-*), liquor applications/locations (L-*/LOC-*), or alcohol licenses (AL-*), and lists /api/... endpoints plus POST /api/sql.

prism-shadow Skill

Solve Atlas Commerce Operations cutoff-based analytical review tasks (fulfillment, refund, carrier, warehouse, support). Read request + template contracts literally, replay event history at a cutoff, dedup imported rows, and produce a JSON object that conforms exactly to the answer template.

prism-shadow Bundle

Solve Atlas Commerce Operations analytical scorecard, reconciliation, and data-correction requests against the authenticated workplace SQL service. Use when a task gives a business request JSON + an answer-template JSON and asks you to compute fulfillment, refund, carrier-quality, warehouse-productivity, or support-health metrics from the Atlas Operations database. Covers cohort scoping, snapshot-vs-event-history authority, raw/canonical fields, minor-unit money + FX, the controlled correction transaction, and the support active-time clock.

prism-shadow Bundle

Solve Public Health Observatory (PHO) reproducibility/transportability algorithmic-audit tasks. These tasks fetch surveillance + socioeconomic records from a read-only PHO data portal, resolve publication releases/cohorts under a strict evidence specification, run a set of registered statistical audit modules with exact reproducibility checkpoints (fixed seeds, PRNG streams, replicate counts, ordered arrays), apply controlled decision gates, and return one JSON object conforming to a per-task answer template. Invoke when a task references the PHO portal / a "six-module audit" / "transportability" / "publication cohort" / "robustness gates" / analysis_request.json + answer_template.json, or asks to audit whether an exposure-outcome signal survives controlled statistical gates.

prism-shadow Bundle

Produce the required normalized JSON audit for a Cedar Ridge Intake Coordination Portal task — patient access verification, referral readiness / referral-to-chart activation, dialysis transfer review, or program enrollment panel. Use when a task points at an intake-coordination portal base URL plus an answer_template.json and asks for a batch/roster/program-level JSON report of statuses, blockers, reason codes, and cohort counts. Covers how to discover the data, apply the classification rules, and emit template-conformant JSON.

prism-shadow Bundle

Produce the required JSON for a Cedar Ridge Intake Coordination Portal structured-audit task — new-patient access verification, referral readiness audits, dialysis/transfer packet reviews, chronic-care program enrollment panels, and referral-to-chart activation. Use whenever a task gives a portal base URL plus an answer template (input/payloads/answer_template.json) and asks for a single JSON object of per-record findings and cohort/summary counts drawn from patients, coverage, PBM, pharmacies, referrals, transfers, documents, ICD codes, chart artifacts, program candidates, and facility capacity.

prism-shadow Bundle

Produce a structured JSON determination for a Northstar-style health-plan "payer operations" case by reading the case's records out of the shared operations data environment and reasoning over policy criteria, evidence, and business rules. Use when a task asks for a JSON determination / disposition / repricing packet / summary for a prior-authorization, coverage-appeal, claim-payment-integrity, peer-to-peer, or finance/margin-queue work item, and gives you (a) a target business id, (b) access to a SQL-queryable operations environment, and (c) an answer_template that fixes the required output shape.

prism-shadow Bundle

Produce the exact structured JSON deliverable for a Northstar-style payer-operations task by reading a shared read-only case environment. Use this when a task hands you a target business ID (a case, appeal, claim, peer-to-peer event, or finance queue), a read-only operations environment (a SQL query endpoint plus business GET endpoints), and a JSON answer template to fill. Covers prior-authorization / UM nurse determinations, coverage-exception appeals with manufacturer-assistance intake, claim repricing against rate benchmarks, peer-to-peer closures, and margin-queue analysis.

prism-shadow Bundle

Solve State Licensing Board / regulatory "structured decision" tasks that ask for a JSON answer conforming to a provided input/payloads/answer_template.json, built by reading a licensing data service (policies/rules plus contractor, liquor, or alcohol-renewal datasets, usually with a read-only SQL endpoint). Use for contractor batch eligibility reviews, restricted liquor-license staff packages, and alcohol renewal manual-review queues. Triggers: a prompt that assigns a licensing-examiner / staff-review role, lists GET endpoints under /api/... plus an answer template, and asks for determinations, deficiency/risk codes, control/obligation codes, verification gaps, monitoring plans, or a ranked review queue.

prism-shadow Bundle

Use when a task provides an operations "request" JSON (business scope, metric and classification definitions) plus a strict answer_template JSON Schema and asks you to compute exact figures from an authenticated operations database and write them to answer.json. Covers cutoff/window-based scorecards, refund and money reconciliations, warehouse/support productivity and SLA reviews, and minimal canonical data-correction tasks. Turns a prose business spec into precise, schema-exact numeric answers derived from the live records.

prism-shadow Bundle

Solve Northwind Components ERP operations tasks against the shared read-only ERP HTTP API: expedite/dispatch-control decisions, mixed-warehouse allocation and transfer decisions, kit/BOM replenishment packages (transfers + purchase requisitions), supplier incident scorecards, and supplier quality-hold / replenishment-control reviews. Use this skill whenever a task references the Northwind ERP, a wave (e.g. TRAIN_*), an allocation or expedite "desk", a "memo"/"scorecard request"/"review memo" plus an answer_template.json, BOM/kit builds, supplier incidents or RMAs, shipping quotes, or asks for a structured JSON decision file driven by live ERP records. Apply it even when the task only hints at these (e.g. "classify these orders", "which POs to hold", "Q1 supplier scorecard") because the business rules, effective-stock formula, API usage, and output conventions are shared and non-obvious.

prism-shadow Skill

Use for Northwind Components ERP tasks that require JSON answers for dispatch expedite queues, warehouse allocation and transfer waves, kit replenishment planning, supplier incident scorecards, or procurement quality-hold reviews using the local ERP API.

komunite Skill

Create a analytics implementation with structured process, quality checks, and system integration

amey-thakur Skill

Turn business data into answered questions with agents that define the metric, pull it consistently, check it against a second source, and state what it does not prove. Use when numbers are quoted in meetings that nobody can reproduce.

amey-thakur Skill

Share workbooks so several people can work without overwriting each other or creating competing versions. Use when more than one person edits the same spreadsheet.

amey-thakur Skill

Turn messy imported data into a clean flat table, fixing types, whitespace, duplicates, and inconsistent categories. Use before any analysis on data that came from elsewhere.

cslawyer1985 Bundle

珠海工伤认定与待遇申领指引。珠海工伤认定申请流程+劳动能力鉴定+伤残补助金/津贴/工亡待遇计算+材料模板+时限要求。当HR、管理者或员工需要完成该项工作时使用；支持自然语言和直接上传CSV/XLSX/Word/PDF，不依赖蚂蚁HR后台数据。

cslawyer1985 Bundle

温州工伤认定与待遇申领指引。温州工伤认定申请流程+劳动能力鉴定+伤残补助金/津贴/工亡待遇计算+材料模板+时限要求。当HR、管理者或员工需要完成该项工作时使用；支持自然语言和直接上传CSV/XLSX/Word/PDF，不依赖蚂蚁HR后台数据。

cslawyer1985 Bundle

泉州工伤认定与待遇申领指引。泉州工伤认定申请流程+劳动能力鉴定+伤残补助金/津贴/工亡待遇计算+材料模板+时限要求。当HR、管理者或员工需要完成该项工作时使用；支持自然语言和直接上传CSV/XLSX/Word/PDF，不依赖蚂蚁HR后台数据。

cslawyer1985 Bundle

石家庄工伤认定与待遇申领指引。石家庄工伤认定申请流程+劳动能力鉴定+伤残补助金/津贴/工亡待遇计算+材料模板+时限要求。当HR、管理者或员工需要完成该项工作时使用；支持自然语言和直接上传CSV/XLSX/Word/PDF，不依赖蚂蚁HR后台数据。

cslawyer1985 Bundle

太原工伤认定与待遇申领指引。太原工伤认定申请流程+劳动能力鉴定+伤残补助金/津贴/工亡待遇计算+材料模板+时限要求。当HR、管理者或员工需要完成该项工作时使用；支持自然语言和直接上传CSV/XLSX/Word/PDF，不依赖蚂蚁HR后台数据。