Data & Analytics

cslawyer1985 Bundle

乌鲁木齐工伤认定申请条件与材料清单。乌鲁木齐工伤认定申请条件+48小时内事故报告+申请材料清单+工伤认定书领取+不予受理的救济。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

长春工伤认定申请条件与材料清单。长春工伤认定申请条件+48小时内事故报告+申请材料清单+工伤认定书领取+不予受理的救济。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

最新劳动法规政策解读周刊。每周自动汇总全国及地方最新劳动法规政策变动+核心条款解读+企业影响分析。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

保密协议与知识产权归属指引。保密协议分级+职务发明归属+竞业与保密的区别+违约取证+赔偿标准。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

工伤预防与安全生产合规。安全生产培训要求+防护用品标准+事故报告义务+工伤保险费率浮动。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

批量工伤申报。批量工伤事故登记→材料收集→工伤认定申请→进度跟踪→待遇申领。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

海外招聘合规指引。跨国招聘→各国劳动法差异/签证要求/跨境薪酬支付/社保缴纳规则。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

合规制度归档虾 — 企业法律文件、规章制度的数字档案管理。用于归档新制度文件、更新版本、标记废止、全文检索、导出文件清单。 触发场景：用户说"归档制度"、"归档文件"、"查询制度"、"制度更新"、"标记废止"、"合规检查"、"导出文件清单"、"版本管理"等。 支持输入：Excel/CSV 文件清单、自然语言描述、文件上传（Word/PDF/Excel）。 核心能力：版本管理（自动标记旧版废止）、分类归档、全文检索索引、档案编号生成、归档通知推送。

cslawyer1985 Bundle

股权激励方案设计器。期权/限制性股票/虚拟股→授予节奏/行权条件/退出机制/税务优化方案。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

职级体系搭建工具。按行业参照→设计管理序列+专业序列+技术序列+操作序列的完整职级体系。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。

javimosch Skill

Meta Ads Analytics & Event Finder

wonsukchoi Bundle

Use when a task needs the judgment of a Logistics Engineer — evaluating the total-cost tradeoff of adding or consolidating distribution facilities, using a center-of-gravity model as a starting point for facility location, slotting a warehouse by pick velocity (ABC classification), or sizing facility throughput/capacity against peak rather than average demand.

wonsukchoi Bundle

Use when a task needs the judgment of a Validation Engineer — authoring or reviewing an IQ/OQ/PQ or process-performance-qualification (PPQ) protocol and justifying the batch/run count, computing a cleaning-validation acceptance limit (MACO from a toxicologically derived PDE/HBEL versus legacy 10 ppm or 1/1000-dose criteria), classifying a computerized system under GAMP 5 to scope CSV/CSA testing depth, auditing an existing validation package for regulatory compliance before batch release, or investigating an analytical-method validation failure against ICH Q2 acceptance criteria. Distinct from a manufacturing-engineer (owns making a process capable — fixturing, Cpk, PFMEA) — this role owns formally proving and documenting that a process, system, method, or piece of software meets its predefined requirements before it is allowed to run; the deliverable is an approved protocol or report, not a capability number.

haibarakiku Bundle

Warehouse Manager

wonsukchoi Bundle

Use when a task needs the judgment of a Self-Enrichment Instructor — pricing and setting the break-even enrollment for a hobby/craft/movement class, designing a session-1 lesson so a mixed-skill adult cohort re-books, deciding whether to run, combine, or cancel an under-enrolled section, writing a studio's cancellation/no-show policy, or drawing the line on liability and scope for a non-credentialed class.

wonsukchoi Bundle

Use when a task needs the judgment of a Data Warehousing Specialist — defining the grain of a fact table before modeling it, choosing a slowly changing dimension (SCD) type for a dimension attribute, designing an incremental ETL/ELT load strategy against a full-refresh alternative, resolving a conformed-dimension conflict across source systems, or diagnosing why a BI report's numbers don't reconcile to the source system.

wonsukchoi Bundle

Use when a task needs the judgment of an Epidemiologist — investigating a disease outbreak and identifying its source, designing a case-control or cohort study to test an exposure hypothesis, calculating attack rates/odds ratios/relative risk from surveillance data, evaluating whether a surveillance system is sensitive and timely enough to catch a real signal, or judging whether an observed case cluster is a true outbreak or expected background variation.

prism-shadow Skill

Solve Atlas Commerce Operations database tasks that require cutoff-based operational analytics, source-stream reconciliation, or controlled canonical data corrections through the Atlas API. Use when prompts provide JSON request payloads and answer templates for fulfillment, refunds, carrier quality, warehouse productivity, support health, inventory, orders, payments, shipments, or similar Atlas Commerce workflows.

prism-shadow Skill

Analyze and, when explicitly approved, correct Atlas Commerce Operations workplace data through documented task-environment APIs. Use when Codex receives prompts with environment_access.md, input/payload JSON contracts, Atlas Commerce Operations schema/data-dictionary endpoints, SQL analysis endpoints, cutoff-based operational scorecards, refund settlement reconciliation, carrier or inventory canonical-field corrections with correction_audit records, warehouse productivity reviews, or support SLA health reviews that must be returned as strict answer.json JSON.

prism-shadow Skill

Analyze Atlas Commerce Operations workplace requests and produce exact JSON answers from prompt, request payload, schema, data dictionary, SQL query endpoints, and optional controlled correction endpoints. Use when a task asks Codex to compute operational scorecards, reconciliations, SLA/health reviews, cutoff-based state, ranked exceptions, or apply an approved minimal canonical data correction with audit evidence against the Atlas workplace service.

prism-shadow Skill

Complete Public Health Observatory portal statistical audit tasks that require strict release resolution, cohort construction, reproducible modeling modules, controlled decision gates, and JSON-only answers.

prism-shadow Skill

Complete Public Health Observatory portal audit tasks that provide a prompt, analysis_request.json, answer_template.json, and environment_access.md. Use this for state, county, and country publication audits requiring exact release resolution, cohort construction, deterministic statistical modules, controlled decision gates, and a contract-conforming JSON-only answer.

prism-shadow Bundle

Solve Northstar Health Plan payer-operations determination tasks against the shared read-only environment — UM prior-auth, pharmacy appeal + assistance, claim repricing, peer-to-peer, and therapy margin queue — and return one strict JSON object matching the task's answer template. Read BEFORE working any task whose prompt references Northstar, a TASK_ENV base URL, the /sql/query bearer token, or an input/payloads/answer_template.json.

prism-shadow Bundle

Produce a schema-validated JSON answer for portfolio-mix, SLA-aging/breach, or release-readiness tasks run against the shared work-item environment (work items, mix targets, SLA policy, releases, milestones, blockers, dependencies). Use when a task points at <TASK_ENV_BASE_URL> / environment_access.md and asks for a single JSON object matching an answer_template.json. Covers scope filtering, primary-vs-duplicate/cancelled/distractor separation, authoritative-field-only data quality, portfolio-category classification, derived metrics with fixed rounding, and stable ordering.

prism-shadow Bundle

Reconcile Asteria Fleet Data Quality Hub audit and certification tasks. Use when Codex must answer JSON-only Asteria data-quality cases from prompt.txt, case_scope.json, answer_template.json, and environment_access.md for contact-master readiness, fuel ledger normalization, freight accrual close, or maintenance-history integrity using the hub catalog, schema, source snapshots, reference aliases, conversions, FX, and authenticated SQL query endpoint.

prism-shadow Skill

Use when solving Atlas Commerce Operations workplace tasks that provide a prompt, request payload JSON, and answer_template.json, and require authenticated schema/data-dictionary/SQL API use to produce exact answer.json metrics, reconciliations, support/warehouse/fulfillment scorecards, or approved canonical corrections with correction_audit records.

prism-shadow Skill

Analyze Atlas Commerce Operations workplace tasks that provide request payloads, answer templates, and an authenticated Atlas service. Use for cutoff-consistent fulfillment scorecards, refund reconciliation, carrier scan quality corrections, warehouse productivity reviews, support health reviews, and similar operational analytics requiring exact answer.json output through the schema, data dictionary, SQL, transaction, and correction-audit APIs.

prism-shadow Skill

Use for engineering portfolio environment tasks that require JSON answers from work items, mix targets, SLA policy, releases, milestones, blockers, dependencies, or the restricted SQL query endpoint. Covers portfolio mix reviews, SLA aging/breach audits, and release-readiness assessments.

prism-shadow Skill

Use when answering engineering portfolio environment tasks that require JSON-only portfolio mix, SLA aging, or release readiness analysis from work item, mix target, SLA, release, milestone, blocker, dependency, and restricted SQL endpoints.

prism-shadow Bundle

Produce a structured JSON disposition for a Northstar Health Plan payer-operations task (prior-authorization / UM-nurse determination, coverage-exception appeal + drug assistance intake, claim repricing, peer-to-peer summary, or margin/finance queue analysis). Use when a task hands you a prompt.txt + task_context.json + answer_template.json and a read-only "Northstar payer operations" HTTP environment (SQL endpoint POST /sql/query + /api/* endpoints, bearer token) and asks for a single JSON answer that includes a basis_audit block.

prism-shadow Bundle

Operating procedure for Atlas Commerce Operations reporting tasks — producing an exact answer.json for a request payload + JSON-Schema answer_template. Use whenever a task ships an input/payloads/ folder containing a *_request.json (business definitions, cohort, cutoffs, thresholds) plus an answer_template.json, and points at an authenticated Atlas workplace service (GET /api/schema, GET /api/data-dictionary, POST /api/sql, and optionally POST /api/sql/transaction, GET /api/correction-audit). Covers both read-only analytical scorecards and controlled single-field canonical corrections.

prism-shadow Bundle

Answer analytics questions against the shared read-only "portfolio" HTTP environment (work items, mix targets, SLA policy, releases, milestones, blockers, dependencies) and return a single strict-JSON answer matching a provided answer_template.json. Use for the three recurring task families: (1) quarterly portfolio-mix reviews/readouts (category mix vs a mix_targets row), (2) SLA aging/breach audits for reliability & security work, and (3) release-readiness assessments. Triggers whenever a task references <TASK_ENV_BASE_URL> / environment_access.md plus /api/work-items and asks for category mix, SLA/overdue/breach, or ship-readiness, with a payloads/ answer_template.json to conform to.

wonsukchoi Bundle

Use when a task needs the judgment of an RFID Device Specialist — running a site RF survey before a warehouse or retail RFID deployment, diagnosing a degraded read rate or dead zone on an installed portal, selecting tag/reader/antenna configurations against FCC/ETSI power limits, or bridging RFID event data into a legacy WMS/ERP that can't ingest it natively.

wonsukchoi Bundle

Use when a task needs the judgment of a Stocker or Order Filler — reading a pick list against warehouse slotting logic, sequencing a multi-line batch pick, applying FIFO/FEFO rotation on dated inventory, checking a lift against ergonomic lifting-index thresholds, or deciding whether a pace-vs-accuracy tradeoff should be flagged before it ships as a customer-facing error.

wonsukchoi Bundle

Use when a task needs the judgment of a Health Sciences Professor teaching in an accredited health-professions program (nursing, allied health, pharmacy, dental hygiene, veterinary technology, or medical-school basic sciences) — diagnosing a licensure/board pass-rate drop, sizing a clinical-hours-to-simulation substitution, negotiating clinical placement capacity against cohort size, responding to a specialized-accreditor citation, or resolving a clinician-educator's teaching-vs-clinical effort conflict.

wonsukchoi Bundle

Use when a task needs the judgment of an Industrial Truck and Tractor Operator — checking a load against a forklift's rated capacity and load center, judging stability-triangle tip-over risk before raising or tilting a load, verifying rack beam load-capacity before stacking a pallet, managing pedestrian-forklift traffic in a shared warehouse aisle, or deciding whether an operator needs recertification after an incident.