Data & Analytics
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
-
paulasilvatech Bundle Security Review 3Scan codebases and files for exploitable security vulnerabilities by tracing data flows, dependencies, secrets, authentication, authorization, injection, cryptography, and business logic issues. Use when asked to scan code, review for security issues, audit a codebase, check vulnerabilities, find SQL injection, XSS, command injection, exposed API keys, hardcoded secrets, insecure dependencies, or run /security-review.
-
paulasilvatech Skill Cobol Db2 Analysis 3Analyze COBOL programs, copybooks, PERFORM and CALL structure, file and VSAM access, embedded EXEC SQL and EXEC CICS, DB2 DDL, DCLGEN structures, cursors, and JCL job steps with source citations. Use when reading or inventorying a COBOL/DB2 legacy system before modernization.
-
paulasilvatech Skill SQL Code Review 3Review SQL code across PostgreSQL, MySQL, SQL Server, and Oracle for injection risks, access control, data protection, performance, schema quality, and maintainability. Use when asked to "review SQL", "find SQL injection", "audit database code", "check stored procedures", or "perform SQL security analysis".
-
paulasilvatech Skill Migrating Oracle To Postgres Data Access Code 2Migrate .NET/C# data access code from Oracle.ManagedDataAccess or Oracle.EntityFrameworkCore to PostgreSQL with Npgsql. Use when replacing OracleConnection, OracleCommand, OracleDataReader, OracleDbType mappings, stored procedure calls, connection strings, inline SQL, and EF Core provider configuration during an Oracle-to-PostgreSQL migration.
-
paulasilvatech Skill SQL Optimization 3Universal SQL performance optimization assistant for query tuning, execution-plan review, index strategy, pagination, batching, aggregation, and monitoring across MySQL, PostgreSQL, SQL Server, Oracle, and other SQL databases. Use this skill when the user asks to optimize slow SQL, review query plans, improve indexes, fix SELECT performance, reduce N+1 queries, tune pagination, or analyze database performance.
-
paulasilvatech Skill Migrating Oracle To Postgres Stored Procedures 2Migrate Oracle PL/SQL stored procedures and functions to PostgreSQL PL/pgSQL while preserving behavior, signatures, type-anchored inputs, exception handling, rollback logic, collation semantics, and orafce compatibility. Use when converting Oracle Procedures and Functions into PostgreSQL equivalents during an Oracle-to-PostgreSQL migration.
-
undermybelt Bundle Second Order SQL InjctnDetect and exploit second-order SQL injection vulnerabilities where malicious input is stored in a database and later executed in an unsafe SQL query during a different application operation.
-
undermybelt Bundle Web App Firewall BypassBypass Web Application Firewall protections using encoding techniques, HTTP method manipulation, parameter pollution, and payload obfuscation to deliver SQL injection, XSS, and other attack payloads past WAF detection rules.
Audited -
undermybelt Bundle Red Team Phishing GophisAutomate GoPhish phishing simulation campaigns using the Python gophish library. Creates email templates with tracking pixels, configures SMTP sending profiles, builds target groups from CSV, launches campaigns, and analyzes results including open rates, click rates, and credential submission statistics for security awareness assessment.
-
prism-shadow Skill Northwind Erp Control Desk 2Use this skill for Northwind Components ERP evaluation tasks that ask for strict JSON decisions using the shared ERP API, especially dispatch expedite queues, mixed-warehouse allocation, kit replenishment, supplier incident scorecards, procurement quality holds, inventory coverage, purchase orders, BOMs, shipping quotes, customers, suppliers, and products. It gives SOPs for API usage, field conventions, stock math, decision precedence, ordering, rounding, and common pitfalls.
-
cslawyer1985 Bundle Skill 19对比两个版本的合同或协议文本,生成逐条新增、删除、修改清单和原始差异文件,并重点标记付款、违约责任、赔偿、终止、知识产权、保密、数据和管辖条款的变化。 适用于:合同对比、协议版本差异、条款变更、红线审查、付款条款、违约责任、合同风险。包含本地 Python 脚本,生成 Markdown、JSON、CSV 等结构化交付物,不依赖外部 API。
-
cslawyer1985 Bundle Litigation Docs Generator 2民商事诉讼文书成套生成技能(诉状文本生成)。当用户要求起草民事起诉状、生成诉讼文书材料、准备立案材料时触发。自动生成8份配套文书:民事起诉状、诉讼保全申请书、担保书、授权委托书、法定代表人身份证明(仅原告为公司时)、律师接待笔录、利息损失计算表(Excel)、委托代理合同。核心流程:收集信息→法律检索(元典/北大法宝)→强制加载全部模板→逐份按模板生成。所有文书严格由 references/ 下的模板驱动,禁止自由发挥。支持华宇元典、北大法宝等专业法律数据库进行法规和类案检索;当事人任一方为企业时自动检索补全公司信息。推荐使用 DeepSeek 模型以获得最佳法律文书撰写效果。
-
prism-shadow Skill Self Attempt 02 11ApexCloud Retention Operations — CRM Retention Analytics Skill
-
prism-shadow Skill Self Attempt 03 8ApexCloud Retention Operations — CRM Retention Analytics Skill
-
prism-shadow Bundle Cedar Ridge Intake Audit 2Audit and reconcile a batch, roster, or program against the Cedar Ridge Intake Coordination Portal (REST + read-only SQL), then emit one template-conformant JSON object. Use when a task points at the Cedar Ridge portal and supplies an answer_template.json describing the required output shape.
-
prism-shadow Bundle Northstar Payer Ops 3Produce template-exact JSON determinations for Northstar Health Plan payer-operations tasks against the shared read-only environment at <TASK_ENV_BASE_URL> (POST /sql/query with bearer pa-review-token-014; open GET /api/... business endpoints). Covers UM nurse authorization summaries, pharmacy appeal + manufacturer-assistance dispositions, payment-integrity claim repricing, peer-to-peer final summaries, and therapy margin-queue analysis. Use whenever a prompt names Northstar Health Plan, the task-env base URL, the pa-review-token-014 SQL endpoint, an answer_template.json contract, or a basis_audit object with source_precedence. Read BEFORE writing the JSON answer.
-
prism-shadow Bundle Northstar Payer Ops 4Northstar Health Plan payer-operations structured determinations. Use when a task asks for a JSON determination, disposition, correction packet, P2P summary, or margin-queue summary for a Northstar case/appeal/claim/P2P/queue against a shared read-only payer environment (base URL http://task-env:9014/, SQL POST /sql/query with bearer pa-review-token-014, open GET business endpoints). Covers five archetypes — UM nurse prior-auth determination (physical therapy), pharmacy coverage appeal + manufacturer assistance intake, payment-integrity claim repricing (cardiac imaging), peer-to-peer final summary (PET MPI), and UM-finance therapy margin queue. Reads prompt.txt + task_context.json + answer_template.json, gathers evidence via allowed endpoints only, and emits exactly one JSON object matching the template's required keys, enums, ordering, precision, and basis_audit rules. Do not inspect environment DB/setup files directly; do not call any judge endpoint.
-
prism-shadow Bundle Self Attempt 02 22Portfolio Environment Analytics
-
prism-shadow Skill Cedar Ridge Intake Reconciliation 3Reconcile Cedar Ridge Intake Coordination Portal tasks and produce schema-valid JSON for patient access verification, referral readiness or activation audits, dialysis transfer packet reviews, and chronic-care enrollment panels. Use when a task references the Cedar Ridge portal, an environment_access.md base URL, intake rosters, referral batches, transfer batches, program candidates, chart artifacts, ICD metadata, documents, pharmacies, or read-only SQL reconciliation.
-
prism-shadow Bundle Licensing Review 2Structured licensing review for contractor application batches, restricted liquor-license staff packages, and alcohol renewal manual-review queues using a task environment API, policy JSON, record endpoints or SQL, and JSON answer templates. Use when Codex must evaluate licensing eligibility, deficiencies, postures, verification gaps, renewal review ranking, or produce schema-conformant JSON from licensing environment records.
-
prism-shadow Skill Self Attempt 01 23SKILL: ApexCloud Retention Operations — CRM Analytics SOP
-
prism-shadow Skill Self Attempt 02 25SKILL: ApexCloud Retention Operations — CRM Analytics SOP
-
prism-shadow Skill Self Attempt 03 22SKILL: ApexCloud Retention Operations — CRM Analytics SOP
-
prism-shadow Bundle Cedar Ridge Intake Coordination 3Produce the strict-JSON deliverable for any Cedar Ridge Intake Coordination Portal task — primary-care access verification, referral readiness/activation audits, dialysis transfer packet review, and chronic-care program enrollment panels. Use whenever a prompt points at the Cedar Ridge Intake Coordination Portal (a base URL) plus an input/payloads/answer_template.json and asks for a single JSON object keyed by a roster_id, batch_id, or program_code. Covers how to reach the read-only REST + SQL endpoints, the shared data model, per-item classification rules, cohort/summary rollups, and the output contract.
-
prism-shadow Bundle Cedar Ridge Intake Coordination 4Complete a Cedar Ridge Intake Coordination Portal reconciliation task and return a single JSON object that conforms to a provided answer_template.json. Use whenever a prompt points at the "Cedar Ridge Intake Coordination Portal" (a read-only HTTP + SQL portal reached via <TASK_ENV_BASE_URL>) and asks you to audit / verify / review a named roster, referral batch, transfer batch, or program candidate list and emit structured JSON (patient-access verification, referral readiness audit, dialysis transfer review, chronic-care enrollment panel, or referral-to-chart activation). Covers how to reach the portal, which data source feeds each output field, the decision rules per task family, and the strict output contract (controlled vocab, ordering, summary counts).
-
prism-shadow Bundle Northstar Payer Ops 7Produce a structured JSON deliverable for a Northstar Health Plan payer-operations work item (UM prior-auth determination, pharmacy coverage appeal + manufacturer assistance intake, claim repricing/payment-integrity correction, peer-to-peer closure, or therapy-margin queue analysis) by reading the shared read-only payer operations environment over its SQL and REST endpoints and returning exactly the JSON shape the task's answer_template.json defines. Use whenever a task gives a Northstar business ID (CASE-*, APPEAL-*/APL-*, CLAIM-*, P2P-*, QUEUE-*), a `<TASK_ENV_BASE_URL>` with a `POST /sql/query` bearer token, and an answer_template.json to conform to.
-
prism-shadow Bundle Northstar Payer Ops Determination 2Produce a structured JSON determination for a Northstar Health Plan payer-operations work item (prior-authorization / UM nurse review, pharmacy coverage appeal + manufacturer assistance intake, payment-integrity claim repricing, peer-to-peer close-out, or UM-finance margin-queue summary). Use when a task ships an input/payloads/task_context.json plus an input/payloads/answer_template.json, points at a shared "Northstar" / "payer operations" environment reachable via POST /sql/query (bearer token) and GET /api/* endpoints, and asks for JSON conforming to the answer template. Triggers: "UM nurse determination", "prior authorization", "coverage appeal", "manufacturer assistance", "claim repricing / payment integrity", "peer-to-peer summary", "margin queue", "basis_audit", "source_precedence", "pa-review-token".
-
prism-shadow Bundle Licensing Review 3Produce structured JSON licensing-review decisions against a shared state licensing data service. Covers three recurring task families: (A) contractor application batch eligibility reviews, (B) restricted liquor-license staff packages, and (C) alcohol renewal manual-review queues. Use this whenever a prompt asks you to act as a licensing examiner / renewal-unit staffer, points you at the licensing environment endpoints (/api/policies, /api/contractor/*, /api/liquor/*, /api/alcohol/*, /api/renewal/rules, /api/sql), and asks for a JSON answer that must conform to an input/payloads/answer_template.json.
-
prism-shadow Bundle Licensing Review Decisions 2Produce structured regulatory decisions (contractor eligibility batches, restricted liquor-license staff packages, alcohol renewal manual-review queues) by reading records from a shared licensing data service and emitting ONLY JSON that conforms exactly to the task's answer_template.json. Use whenever a prompt casts you as a licensing examiner/reviewer, points at a task environment (<TASK_ENV_BASE_URL> + /api/... endpoints, optional POST /api/sql), and asks for an answer matching input/payloads/answer_template.json.
-
prism-shadow Bundle Ma Deal Workbench JSON 3Produce schema-conformant JSON deliverables (issue registers, deviation matrices, closing-readiness packages, committee escalation memos, transition reviews) from the M&A deal workbench HTTP/SQL API. Use whenever a prompt names a deal ID like PRJ_XXXX, points at a deal workbench base URL, references a playbook (PB_*) or policy (POL_*), and requires output conforming to an answer_template.json with no prose.
-
prism-shadow Bundle Pho Registered Algorithmic Audit 2Operating procedure for Public Health Observatory (PHO) "registered algorithmic audit" tasks: a prompt.txt plus payloads/analysis_request.json (the registered protocol) and payloads/answer_template.json (the strict output contract), to be answered ONLY from a read-only web data portal whose base URL is given in environment_access.md. Use whenever the input pairs an analysis_request.json spec with an answer_template.json contract and points at a "<TASK_ENV_BASE_URL>" portal for state / county / country health, socioeconomic, geography, revision, or methodology evidence, and asks for one JSON object of cohort + multi-module robustness diagnostics (jackknife/fixed-effects/GMM, nested penalized CV, wild-cluster bootstrap-t, grouped conformal, trajectory PCA + k-means, source perturbation) leading to a gated classification.
-
prism-shadow Bundle Portfolio Environment Analysis 2Answer engineering-portfolio review tasks that query a shared read-only work-items API/SQL environment and must return one strict JSON object matching a supplied answer_template.json. Covers the recurring task families: portfolio-mix reviews (count-based category mix vs. a target, gaps, rebalance), SLA-aging audits (primary vs. duplicate work, overdue/aging buckets, breach rate, hotspots), and release-readiness assessments (milestone completion, gating items, blockers, dependency chains, ship decision). Use whenever a task references work items, mix targets, SLA policy, releases, milestones, blockers, or dependencies, an X-Env-Token query token, and stale "mirror" or "legacy" fields to ignore.
-
prism-shadow Skill Self Attempt 01 31CRM Retention Analytics Skill
-
prism-shadow Skill Self Attempt 02 33CRM Retention Analytics Board — Solver Skill
-
prism-shadow Skill Atlas Ops Analytics 2Analyze Atlas Commerce Operations workplace tasks that require strict JSON answers from operational database records, including cutoff-based fulfillment, refunds, carrier corrections with audit records, warehouse productivity, and support-health reviews. Use when a task provides a prompt, JSON request payload, answer template, and environment access for Atlas-style schema/data-dictionary/query services or controlled correction transactions.
-
prism-shadow Skill Fewshot Attempt 01 5ApexCloud Retention Operations — Analytics Convention Skill
Frequently asked questions
What are Data & Analytics agent skills?
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
Which Data & Analytics skills are most installed?
Popular Data & Analytics skills on SkillMD right now include litigation-docs-generator, licensing-review, security-review. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Data & Analytics skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.