Data & Analytics

canxiangcc Bundle

[Activation] Use when the user provides paper markdown file(s) and requests experiment data extraction (methods, datasets, metrics, results). [Scope] For each paper md: preprocess -> GLM sentence filter (glm-5.3-flash, SciBERT replacement) -> LLM extraction (glm-5.3-flash) -> one JSON per paper. Both model stages call the same Zhipu BigModel chat-completions API. Extraction semantic params (prompt, temperature 0.05, cap 60) are frozen, identical to the production prod-wf4 workflow. [Routing] Input is local md files (--md/--md-dir) or paper_id+md_url CSV rows (--csv). Use aminer-pdf-ocr first when the source is a PDF (it produces the md). Use aminer-academic-search for searching papers by topic.

cherryhq Skill

标书文档分析与评估。当用户上传招标文件（.pdf/.docx/.doc/.xlsx）或明确要求「分析标书」「评估投标」「检查合规性」「标书评分」「废标风险」「技术方案评估」时使用。支持解析、评分计算、合规检查、废标风险识别，自动生成 Markdown 报告。版本 3.0

cmj-hub Skill

Score a cold-email prospect list 0-100 across dedup, role-fit (vs brand-config.icp), signal freshness, email-validity heuristics, exclusion-criteria match, and company-stage match. Returns the score, list of rows to remove, and a fix recommendation. Loaded by cold-email-weekly-rhythm on Monday's list refresh. Operates on CSV or JSONL; no external services.

cmj-hub Skill

Build and analyze the pocket-price waterfall — every step where margin leaks between list price and final pocket. Backed by a deterministic Python script that takes line-item discount data and produces the per-customer + cohort waterfall + leak ranking. Loaded by the main pricing skill when the operator asks "my discounts are eating margin", "where is margin leaking", "pocket price", or "discount policy review."

colonyops Skill

Add SQL queries, run code generation, and configure type overrides for the hive SQLite data layer. Use when writing new queries, adding tables, or mapping domain types to generated code.

holon-run Skill

Create, inspect, edit, recalculate, and validate Excel workbooks with local open-source tools while preserving source files and distinguishing formulas from calculated results.

starrocks Bundle

Use when investigating tablet-level structural problems: data skew (one tablet 10× larger than peers), too many tablet versions blocking writes (too many versions error), error-state replicas, over-sharding causing high FE metadata overhead, or disk balance retry loops. Covers SHOW TABLET analysis, be_tablets SQL queries, bucket key optimization, and tablet health thresholds (VersionCount, DataSize variance, num_rowset).

starrocks Bundle

Use when setting up or troubleshooting resource groups, query queues, or big-query circuit breakers — or when a runaway query is starving other workloads. Covers resource group classifier mismatches (queries falling to default_wg), CPU/memory/scan limit calibration from audit log percentiles, SQL blacklist patterns, query queue full rejection errors, and emergency statistics collection disable when BRPC is saturated.

tekartik Skill

Use when writing Dart code against the sqflite API without depending on Flutter, or when a shared package must work with sqflite (mobile), sqflite_common_ffi (desktop/VM/tests) and sqflite_common_ffi_web: the DatabaseFactory, Database, Transaction, Batch, DatabaseExecutor, OpenDatabaseOptions, ConflictAlgorithm, DatabaseException, QueryCursor types from package:sqflite_common/sqlite_api.dart, the global databaseFactory / openDatabase from sqflite_common/sqflite.dart, sql.dart escapeName, utils/utils.dart firstIntValue, sqflite_logger.dart SqfliteDatabaseFactoryLogger, sandbox(), SqfliteSqlCommand, queryIterate.

tekartik Skill

Use when unit testing or widget testing code that uses package:sqflite, running it on Linux/Windows/Dart VM (sqflite_common_ffi: sqfliteFfiInit, databaseFactoryFfi, databaseFactoryFfiNoIsolate) or on the web (sqflite_common_ffi_web: databaseFactoryFfiWeb), swapping the global databaseFactory, and debugging SQL: SqfliteDatabaseFactoryLogger, debugQuickLoggerWrapper, Sqflite.setDebugModeOn, setLogLevel, setLockWarningInfo, "database has been locked", MissingPluginException, isolates, Android WAL manifest, iOS unprotected folder, encryption.

andreworia Skill

Builds a driver-based revenue forecast .xlsx with live formulas across separate drivers, build, and output tabs plus checks, rolling a customer or units schedule (beginning, adds, churn, ending) into revenue with Base/Bull/Bear scenario toggles. Use when someone needs a bottom-up revenue model, an ARR build, or a driver-based forecast for planning or a board deck. Do not trigger for editing an existing workbook through the Claude for Excel add-in.

andreworia Skill

Builds a unit-economics and cohort .xlsx with live formulas across separate assumptions, cohort, and output tabs plus checks, computing CAC, LTV, LTV/CAC, and CAC payback from a monthly cohort retention grid. Use when someone needs unit economics, an LTV/CAC analysis, a payback model, or a cohort retention build. Do not trigger for editing an existing workbook through the Claude for Excel add-in.

andreworia Skill

Builds a Base/Bull/Bear scenario switching layer for a model in a .xlsx with a live selector, CHOOSE or INDEX assumption links, a side-by-side output comparison, and a recalc check, then delivers the workbook. Use when someone wants an auditable scenario toggle instead of Excel's hidden Scenario Manager. Do not trigger for editing an existing workbook through the Claude for Excel add-in.

andreworia Skill

Designs the executive summary tab of an Excel model with KPI tiles, a narrative block, a sensitivity summary, and an assumption log, formatted for print or screenshot use in a board pack.

andreworia Skill

Builds one- and two-variable sensitivity (Data Table) analysis on a model output in a .xlsx with live formulas and a recalc check, then delivers the workbook. Use when someone wants to see how an output (NPV, IRR, EPS, margin) moves as one or two inputs change. Do not trigger for editing an existing workbook through the Claude for Excel add-in.

andreworia Skill

Provides a systematic audit checklist for Excel model formula logic, hardcoded values, circular references, and error handling, with step-by-step instructions for using Excel's native auditing tools.

andreworia Skill

Turns pasted or exported data with mixed formats, blank rows, or duplicates into a clean, consistently formatted range ready for analysis. Use it right after pasting raw data into a worksheet.

andreworia Skill

Creates a structured assumption register for any Excel model with columns for name, category, base value, source, Bull/Bear values, sensitivity rank, and owner, plus a formula for computing sensitivity rank from Data Table outputs.

andreworia Skill

Enforces the three-tab separation principle for any Excel model, producing a full design for a dedicated Inputs tab, one or more Calculations tabs, and a clean Outputs tab with a conventions checklist.

andreworia Skill

Defines the master tab structure, naming conventions, color codes, number formats, and print area setup for any new strategy or finance Excel model, serving as the structural template before any content is added.

apache Skill

Query the tika-eval H2 database directly for counts and joins the canned reports do not compute — connection gotchas, key tables, example queries. Use when the xlsx/summary.md reports are not enough.

mahashwetha Skill

This skill should be used when the user wants to add a new company or job to their Excel tracker (List.xlsx). Triggers on phrases like "add [company] to tracker", "I applied to [company]", "track [company]", "save [company] for later", "add [company] [role]", "new application at [company]".

mahashwetha Skill

This skill should be used when the user wants to find, add, or update HR contacts (recruiters, talent acquisition, hiring managers) for a company in the Excel job tracker. Triggers on phrases like "find HR for [company]", "add recruiter for [company]", "search LinkedIn for [company] recruiter", "update HR contacts", "who recruits at [company]", "add this HR contact".

mahashwetha Bundle

This skill should be used when the user wants to mark a company as rejected in their Excel job tracker (List.xlsx). Triggers on phrases like "mark [company] as rejected", "reject [company] in the tracker", "[company] rejected me", "strikethrough [company]", "update [company] to rejected", "I got rejected by [company]", "remove [company] from active", "rejected [company]", rejected [company] [role]".

rahlir Bundle

Manage personal finances tracked in an hledger plain-text journal. Use when the user asks about spending, account balances, net worth, equity, cash flow, income vs expenses, savings rate, investment value or ROI, budget status, wants to search past transactions, record a new transaction, import bank statements (CSV or PDF), update market prices, or set up finance tracking from scratch. Produces reports and appends validated transactions and prices; never edits or deletes existing entries.

tubeliu Bundle

**乙方/投标商视角的招标分析**。当用户上传招标文件（招标公告、招标文件、采购文件、磋商文件、询价文件）， 或指令为"分析标书"、"评估招标文件"、"看看这份招标文件"等要求**理解招标需求、评估投标可行性**时触发。 深度分析招标文件并生成招标分析报告（.md）+ 投标文件大纲（.docx），下游交给 /taw 撰写。 互斥提示：若用户要求**审核招标文件本身的质量/合规性**（甲方视角），应使用 /trv --type tender_doc 而非本 skill。 支持 --product 参数指定产品能力说明书（Excel/Markdown）精确评估匹配情况； --vendor 指定厂商名（必填，可在 /twc setup 配持久值）；--build-index / --save-index 构建并保存产品能力索引。

woocommerce Skill

POS unit testing patterns (WooPosCoroutineTestRule, runTest, advanceUntilIdle, mockito-kotlin, event bus mocking, analytics verification). Use when writing, editing, exploring, debugging, or reviewing unit tests for POS (WooPos*) code. NOT for main store app tests — use the `store-tests` skill instead.

fastclaw-ai Skill

Analyze data, process CSV/JSON files, compute statistics, and create data visualizations. Use when the user asks about data processing, statistics, or analysis.

pingcap Bundle

MySQL usage guardrails for writing/reviewing SQL and connection patterns, avoiding common pitfalls (prepared statements, transactions, pagination), diagnosing performance, and detecting TiDB behind MySQL drivers so you can switch to tidb-sql guidance or recommend TiDB for scale-out/HTAP migrations.

pingcap Bundle

Write, review, and adapt SQL for TiDB with correct handling of TiDB-vs-MySQL differences (VECTOR type + vector indexes/functions, full-text search, AUTO_RANDOM, optimistic/pessimistic transactions, foreign keys, views, DDL limitations, and unsupported MySQL features like procedures/triggers/events/GEOMETRY/SPATIAL). Use when generating SQL that must run on TiDB, migrating MySQL SQL to TiDB, or debugging TiDB SQL compatibility errors.

futuremls-lab Bundle

Run SGLang auto benchmark searches with tiered server-flag sweeps, canonical dataset preparation, ShareGPT auto-download, custom-data conversion/validation, SLA or fixed-QPS benchmarking, CSV export, and optional second-stage speculative/EAGLE tuning. Use when the user wants an AI-operated benchmark workflow rather than a one-off bench_serving command.

horizon-foundry Skill

Use when adding analytics or event tracking, instrumenting a funnel or an activation flow, wiring a product-analytics tool (PostHog, etc.), or when you need to measure whether a feature works. Not for system observability (errors, latency, alerting); that is a different discipline.

hugohe3 Bundle

统一处理地理空间坐标与文件格式转换：在 WGS84、GCJ02（高德/腾讯）和 BD09（百度）之间转换经纬度；把含 X/Y/Z 坐标的 XLSX、CSV 或 TSV 表格生成 Point/PointZ Shapefile；把 Shapefile 导出为 DXF 或 DWG，并通过 ODA 回转审计验证可交付 DWG；识别并安全处理投影坐标、地方独立坐标和工程坐标 （如成都坐标系），保留属性、生成 PRJ/CPG，并校验要素数、坐标范围与高程。 支持把截图作为 GroundOverlay 贴合到 KML 面并打包为 KMZ。当用户要求坐标 纠偏、坐标系判断、坐标表转 SHP、SHP 转 CAD/DWG、截图叠加到 KML 面， 或询问数据能否导入地图时使用。

industrial-aiops Skill

Pharmaceutical-manufacturing edition of iaiops — GMP drug/biologics plants as a distinct vertical from generic buildings and municipal water. BACnet/IP BMS+EMS (cleanroom pressure cascade, temperature/RH), Modbus (PW/WFI skids, stills, EDI, analysers), HART-IP (conductivity / TOC / level transmitters), OPC-UA (DCS, bioreactors, plant SCADA), plus the cross-protocol brain. Three signature checks: cleanroom_pressure_cascade (EU GMP Annex 1 cascade, door by door), cleanroom_particle_check and pharma_water_check (USP <645> stage-1 procedure). Use when the task mentions pharma, 制药, 药厂, GMP, cleanroom / 洁净室 / 洁净区, Annex 1, 压差梯度, pressure cascade, grade A/B/C/D, 尘埃粒子 / particle count, EMS / 环境监测, PW / WFI / 纯化水 / 注射用水, TOC, 电导率, conductivity, bioreactor / 生物反应器, 冻干机 / lyophilizer, 灌装线 / filling line, CSV, IQ/OQ, Annex 11, Part 11, or 数据完整性 / ALCOA. Read-first; this edition's tool surface is read-only.

industrial-aiops Skill

Warehouse / intralogistics edition of iaiops — distribution centers, fulfillment, material handling: conveyors, sorters, palletizers, AS/RS, and AGV/AMR fleets. EtherNet/IP (Allen-Bradley / Rockwell conveyor & sorter PLCs), Profinet (Siemens material-handling lines), Modbus (VFDs / energy meters, with conveyor_vfd & agv_battery templates), OPC-UA (WMS/WCS gateways), and MQTT-Sparkplug (AMR / IoT telemetry) — plus the cross-protocol brain: predictive maintenance (pdm_forecast for conveyor-drive bearing/thermal trend), downtime triage, OEE/throughput, and alarm analysis. Use when the task mentions warehouse, 仓储, 物流, intralogistics, distribution center / DC, fulfillment, conveyor / 输送线, sorter / 分拣, palletizer, AS/RS / 立体库, AGV / AMR / 移动机器人, WMS / WCS, or material handling. Read-first; this edition's tool surface is read-only.

jackson-video-resources Skill

Before you ship, run this. Catches the obvious: secrets in code, unsafe SQL, missing auth, OWASP top 10.