Data & Analytics

daemon-blockint-tech Bundle

Builds location-aware systems—CRS/projections; GeoJSON, Shapefile, GeoTIFF, MVT; PostGIS spatial SQL; indexes and tiling; OGC WMS/WFS/WMTS integration; map matching, trajectories, geofencing; fleet telematics (GPS/GNSS, NMEA, timestamps, CAN metadata); streams and batch ETL; location privacy/accuracy. Use for geospatial developer, telematics, PostGIS, GeoJSON, geofencing, fleet tracking, GPS trajectory, map matching, NMEA, spatial query, tile server, OGC, coordinate projection, vehicle telematics—not pure OR routing without geo (operations-research-algorithm-developer), autonomy fusion (sensor-fusion-engineer), WMS workflows (wms-developer), warehouse marts without geo (data-warehouse-engineer), generic backend (senior-software-engineer), simulation platforms (simulation-software-engineer), robotics without fleet geo (robotics-automation-integration-engineer).

unboundcompute Skill

Hunt formula injection, also called CSV injection, where an untrusted field stored by the application is later written into an exported CSV, TSV, or spreadsheet and a spreadsheet program evaluates it as a formula when a victim opens the file. A cell whose first character is an equals, plus, minus, or at sign, or a tab or carriage-return prefix, is treated as a formula, so a stored value can call a data connection or hyperlink to exfiltrate other cells, trigger a legacy dynamic-data command that runs a program, or spoof content the recipient trusts. The vulnerable step is the export, not the page that stored the value, and the victim is whoever opens the download. Use when the app exports user-controlled data to a spreadsheet format. The stored untrusted field is the source, the exported cell a spreadsheet evaluates is the sink, and formula execution in the recipient's client is the bug.

unboundcompute Skill

Test what happens after the model speaks: whether an application trusts model output and passes it, unescaped, into a browser, a terminal, a shell, a database, or another system. Covers model-driven XSS and markup injection, data exfiltration through rendered markdown images and links, terminal and ANSI escape injection, invisible-unicode and ascii smuggling in output, and output used to build code, SQL, or shell commands. Use when reviewing any app that renders, executes, or forwards LLM output. The model's output is an untrusted string.

unboundcompute Skill

Hunt Python deserialization that executes attacker code: untrusted input reaching pickle.loads, an unsafe YAML load, marshal, jsonpickle, dill, or a numpy or pandas loader that unpickles, where the format supports arbitrary object construction through __reduce__ or a tag. Covers pickled data in requests, cookies, caches, message queues, and model or dataframe files, and YAML documents that instantiate arbitrary Python objects. Use when a service loads serialized Python objects it did not produce with a loader that reconstructs arbitrary types rather than parsing data only. The untrusted serialized blob is the source, the reconstructing loader is the sink, and the __reduce__ or object tag that runs a callable during load is the bug.

unboundcompute Skill

Hunt PHP object injection where untrusted input reaches unserialize or a framework unserializer and a reachable class carries a magic method that fires during or after reconstruction. Covers native unserialize on request data, cookies, or cache entries, phar deserialization triggered by filesystem functions on an attacker-controlled path, and property-oriented programming chains through __wakeup, __destruct, __toString, and __call that reach a file write, a command, or an SQL sink. Use when a PHP app deserializes data it did not produce and application or library classes define magic methods with side effects. The untrusted serialized string is the source, the unserialize or phar trigger is the sink, and the magic-method chain to a dangerous call is the bug.

unboundcompute Skill

Hunt the SQL injection that first-order testing misses: blind injection where the response carries no error or data and the signal is a boolean difference or a timing delay, and second-order injection where input is stored safely on one request and later concatenated into a query on a different code path. Covers values that reach a query only after being read back from the database, a cache, or a log, and sinks that reveal nothing directly so confirmation depends on an inferential channel. Use when a value is stored now and used in a query later, or when a parameter reaches a query whose response shows no direct output. The untrusted value that becomes query structure at the later or blind sink is the source, that query is the sink, and the unparameterized use on the second path is the bug.

quantumquirkxyz Skill

Design streaming data pipelines — Kafka, Kinesis, Pub/Sub, Flink — with event schemas, stream processing, and real-time analytics.

inbharatai Skill

Build cohort analyses — retention curves, LTV by cohort, churn funnels, and behavioral segmentation.

inbharatai Skill

Create Anki-compatible flashcard decks — spaced repetition, cloze deletions, images, and export to CSV/APKG.

m2ai-portfolio Skill

Run the Gemini file processor on any folder — extracts content from PDF, PPTX, XLSX, DOCX, CSV, JSON, and any text format, then generates Obsidian-ready summaries. Use when asked to "summarise this folder", "run file intel", "process these files", or a folder path is provided and summaries are needed.

m2ai-portfolio Bundle

Score any AI-generated document, spreadsheet, or deck on a 0–100 trust scale across five verifiable dimensions. Outputs a per-dimension scorecard and a composite score. Use as a final gate before sharing any AI-generated artifact.

mariourquia Bundle

Operationalize the first 12-18 months post-delivery of a new-construction or gut-renovation asset: monthly tracker of lease-up velocity vs underwriting, concession depth vs market, approval-rate posture, traffic-source mix, broker-assist rate, model-unit performance, first-renewal retention readiness, stabilization pace, NOI ramp vs underwriting, lender-reporting compliance, and equity-call scheduling for any unfunded reserves. Distinguishes from the steady-state `workflows/monthly_property_operating_review` by adding ramp-tracking metrics and by wiring the cross-system posture between AppFolio (leasing funnel + lease execution) and Excel (rent comp + concession benchmark) into a single lease-up narrative. Hands off to `workflows/monthly_property_operating_review` once the property crosses the lifecycle stabilization threshold. Narrative-first with a KPI dashboard. Informational to recommendation severity: this pack does not authorize concession policy exceptions, pricing shifts, or equity-call initiations —

evolution-foundation Bundle

Query MongoDB databases configured in .env (DB_MONGO_N_*). Use when the user asks to query, explore, or audit data in a MongoDB database. Picks connection by label (e.g. 'orders-dev', 'analytics-prod') or numeric index. Read-only by default — writes refused unless DB_MONGO_N_ALLOW_WRITE=true on that block.

evolution-foundation Bundle

Query MySQL / MariaDB databases configured in .env (DB_MYSQL_N_*). Use when the user asks to query, explore, or audit data in a MySQL database. Picks connection by label (e.g. 'orders-dev', 'analytics-prod') or numeric index. Read-only by default — writes refused unless DB_MYSQL_N_ALLOW_WRITE=true on that block.

evolution-foundation Bundle

Query YouTube Data API v3 — channel stats, recent videos, top videos, comments. Supports multi-account (OAuth or API Key). Use when user asks about YouTube metrics, YouTube channel, subscribers, views, videos, engagement, or any reference to YouTube analytics.

evolution-foundation Skill

Perfila e explora um dataset para entender sua forma, qualidade e padrões. Use ao encontrar uma nova tabela ou arquivo, verificar taxas de nulo e distribuições de colunas, identificar problemas de qualidade como duplicatas ou valores suspeitos, ou decidir quais dimensões e métricas analisar. Funciona com tabelas PostgreSQL do stack Evolution (Evo CRM, Evo AI), dados do Stripe, Omie, Licensing, ou arquivos CSV/Excel carregados.

evolution-foundation Bundle

Query LinkedIn API — profile info, posts (when approved), org stats. Supports multi-account via OAuth. Use when user asks about LinkedIn metrics, LinkedIn profile, LinkedIn posts, or any reference to LinkedIn analytics.

evolution-foundation Skill

Valida uma análise antes de compartilhar — metodologia, precisão e verificações de viés. Use quando revisar uma análise antes de uma apresentação para stakeholders, verificar cálculos e lógica de agregação, conferir se os resultados de uma query SQL parecem corretos, ou avaliar se as conclusões são de fato suportadas pelos dados. Sempre rodar esta skill antes de compartilhar análises baseadas em Stripe, Omie, Licensing ou Evo CRM.

evolution-foundation Bundle

Query Instagram Graph API — profile stats, recent posts, engagement, insights. Supports multi-account (OAuth via Social Auth App). Use when user asks about Instagram metrics, followers, posts, engagement, or any reference to Instagram analytics.

evolution-foundation Skill

data-write-query — Escrever SQL Otimizado

evolution-foundation Skill

Uninstall an EvoNexus plugin, reverting the files it copied and running its uninstall.sql. Use when the user asks to remove, uninstall, or delete a plugin. Triggers on "desinstala plugin X", "remove plugin X", "uninstall plugin X", "tira o plugin Y".

euwebertdefreitas Bundle

Expert in Spreadsheets (.xls, .xlsx, .csv, .xlsm)

euwebertdefreitas Bundle

Expert in T-SQL and PL/SQL

euwebertdefreitas Bundle

Expert in Analytics-Driven Management

sam6dvpte34 Skill

---

sam6dvpte34 Skill

---

sam6dvpte34 Skill

---

tractorjuice Bundle

[COMMUNITY] Assess a US federal civilian system against the CISA Zero Trust Maturity Model v2.0 — scoring 5 pillars (Identity, Devices, Networks, Apps & Workloads, Data) and 3 cross-cuts (Visibility & Analytics, Automation & Orchestration, Governance) across 4 maturity stages.

evolution-foundation Skill

LinkedIn analytics report — profile data, posts (when available), org stats. Use when user says 'linkedin report', 'linkedin analytics', or any reference to LinkedIn performance.

lovstudio Bundle

万能微信秘钥：先为本地微信准备密钥，再查询聊天、联系人、朋友圈和任意只读 SQL。Use when the user mentions“万能微信秘钥”“查微信记录”“读取朋友圈”。

morning-start Skill

数据看板技能库，使用 Python + Streamlit + ECharts + Pandas 快速构建数据分析和可视化应用，掌握从数据处理到界面展示的完整技能体系

morning-start Skill

Use when the user needs a data analysis skill entry point, a recommended analytics sub-skill, or a guided overview of the analysis workflow.

morning-start Skill

Pandas 数据处理技能，掌握数据读取、清洗、转换和聚合，为数据看板提供高质量的数据源

morning-start Skill

Use when the user needs a standard data analysis workflow, goal definition guidance, value realization steps, or analysis taxonomy.

morning-start Skill

Use when the user needs a structured data analysis report, audience-specific reporting, or delivery templates.

morning-start Skill

Use when the user needs multi-dimensional data visualization, chart selection guidance, or interactive presentation patterns.