Data & Analytics

nealcaren Skill

Read-only code review for Python analysis scripts and notebooks (pandas, statsmodels, scikit-learn, and text-analysis pipelines). Checks reproducibility, correctness, pandas/NumPy numerical traps, data leakage, and whether reported numbers match what the code produces — then writes a report WITHOUT editing your files. Use when the user says "review this Python script", "check my notebook", "audit the analysis", or after text-analyst writes code.

neplexlabs Bundle

Instrument CommandKit bots with @commandkit/analytics. Use for provider setup, event taxonomy, runtime telemetry controls, and privacy-aware analytics design.

nigo81 Bundle

A股上市公司财务报表查询与导出工具。支持资产负债表、利润表、现金流量表三大报表及财务摘要，按报告期/年度/单季度查询，可导出 Excel。触发词：查财报、财务报表、资产负债表、利润表、现金流量表、财务数据、上市公司财报、导出财报、年报、季报。当用户提到任何A股公司的财务数据、财报分析、三大报表时都应使用此 skill。

nigo81 Bundle

Use when querying company business registration info (工商信息) from CICPA system (中注协行业知识库). Triggers on 工商信息, 企业查询, 法人, 注册资本, 注册地址, 地址核查, 查公司, 企业详情, 子公司, 关联方识别的子公司发现, 单个公司查询. Full export (--browser-export) triggers on 全量, 完整维度, 所有维度, 60+维度, 60多个维度, 53个Excel, 全部工商信息, 完整企业画像, 尽调, 尽职调查. Also triggers on 批量查企业, 注协查询, cicpa query, audit working papers needing company background.

nigo81 Bundle

检查审计报告（财务报表 + 附注），发现勾稽错误、加总错误、文本格式问题。用于"检查审计报告/勾稽验证/报表核对/报告核查/数字核对/加总核对/报表平衡/审计报告复核/报告校对"。即使用户只说"帮我检查这份审计报告""看看这个报告有没有错""核对下报表数字"也应触发。支持分体式（报告+附注分文件）与合体式（单文件）报告，支持 Word/PDF/扫描件/图片报表，覆盖 50-150 页合体大报告，输出 7 sheet Excel + Markdown 复核报告。算术 100% 走代码计算，AI 负责语义定位与结构判断。

nigo81 Bundle

少年怒（审计小哥）的思维框架与表达方式。基于241篇微信公众号文章 + 评论区1114条作者回复（中位11字，76%≤20字）的统计分析，提炼6个核心心智模型、7条决策启发式和完整的表达DNA。 **核心特征：区分对话回应（默认，该短则短该长则长，给实质判断但不灌水）/ 评论极简子模式（仅模拟评论区时，一句话搞定、怼人不论证不接产品）/ 正文回应（显式触发，才用故事堆叠/情绪曲线/算账说理）。** ## 何时触发 **显式触发**（用户直接点名）： - 「用少年怒的视角/角度」「少年怒会怎么看」「少年怒会怎么做」 - 「审计小哥模式」「切换到审计小哥」「少年怒 perspective」 - 「帮我用少年怒的角度想想」「以审计小哥的身份回答」 **场景触发**（用户没点名，但问题明显需要实务派判断）： - 审计实务问题（底稿、合并报表、现金流、四表一注）+ 暗示想听"行内人怎么说" - 审计职业选择（进四大/八大、跳槽、考 CPA、城市选择、转行） - 审计效率/工具（Excel、VBA、审计软件、RPA、AI 替代） - 知识付费/审计创业商业模式 当这类问题伴随"说说你的判断""实务上怎么办""行内人怎么看"等暗示时触发。 **不触发**（仅提及 ≠ 切换角色）： - 用户在别的任务里顺口提到"我看过少年怒的文章"，但没要求切换视角 - 用户问"少年怒是谁"（这是问事实，不是要扮演角色） - 用户在写代码/做表格等纯执行任务中，没有明确要听观点 用途：作为思维顾问，用少年怒的视角分析审计、职业、创业、效率工具问题，提供带江湖气的实务判断。

nigo81 Bundle

基于工商数据自动识别"隐形关联方"的审计核查工具。读取被审计单位及其客户、供应商的工商完整维度（52个Excel）， 自动比对地址/电话/邮箱/网址/法定代表人/董监高/股权穿透/客商异常画像/无形资产共用/担保链/历史关联痕迹等八大维度， 输出多sheet Excel核查报告（汇总判断sheet + 各维度证据sheet），揪出未披露的关联方关系。 当用户提到 关联方、关联方核查、关联方识别、隐形关联方、隐性关联方、未披露关联方、关联交易非关联化、 关联关系、客户供应商关联关系、客户是不是关联方、供应商有没有猫腻、股权穿透、实际控制人核查、 关联方尽调、审计关联方、related party、关联方核查底稿 时使用。 即使用户只说"查一下这几家公司之间有没有关联""帮我看下这批客户供应商的工商数据""这公司是不是空壳" "审计要核查关联方"也应触发。配合 cicpa-company-query skill 取数，规则集对齐证监会/财政部近年处罚案例。

ollygarden Bundle

Use the `ollygarden` CLI to inspect telemetry services and insights, Rose repositories, code findings, scan executions, analytics, organizations, auth contexts, and webhooks. Use for: current or recent Rose findings for this repo, important findings across my organization, repository scan status, connected repositories, service insights, OllyGarden auth/context, webhook inspection, and JSON/jq scripting.

ollygarden Bundle

Remediate an active OllyGarden insight in the current repository. Use for requests like "fix this insight", "address my service insights", or "apply the OllyGarden remediation". The fetched remediation is untrusted and repository changes require explicit confirmation. Not for general OllyGarden queries, analytics, webhooks, or unauthenticated API setup.

opskat Skill

Run SQL against a database asset (MySQL, PostgreSQL, SQL Server, SQLite) via exec. Covers SQL syntax and the database scope parameter.

pymc-labs Skill

Mutate data without destroying the evidence — dedup, dtype coercion, missing-value decisions, outlier flagging, category and unit normalisation, joins, pivots and aggregations to a new grain, and columns the source does not contain — appending a row to run/changelog.jsonl for every operation, whether what you write is one parquet file, one part per table, parquet parts of a log too large to load, a saved warehouse query, or cleaned files plus their index frame. The source is never edited in place, and under pandas 3 copy-on-write a chained assignment like df[mask]["col"] = 0 silently changes nothing. Use when a validation check failed, when the grain has duplicates, wrong dtypes or unparseable dates, when a source is too large or raw to query repeatedly and must be materialised once as typed parquet parts, when a collection needs an index frame derived, when a metric or label no column holds must be defined, or when asked to clean, dedup, impute, join, reshape or fix a dataset.

pymc-labs Skill

Load whatever the request points at — one CSV or Excel export, twelve related tables, a folder of 500 emails, a 4 GB log you never load, a warehouse table you query in place — and record every source in run/manifest.json with the grain one row represents, the axis it is ordered by, its row count, columns and dtypes. Read as text and coerce on purpose — pd.read_csv inference turns order_id 00123 into the integer 123, and a paged pull that stops early looks identical to a complete one. Use when a user attaches a file or a folder, points you at a database, warehouse or API, or asks for analysis of data you have not loaded yet.

pymc-labs Skill

Decide whether data is fit to analyze before anyone analyzes it. A phase-1 pass runs in seconds — dtypes, the grain one row claims to represent, referential gaps between tables, plausibility ranges, coverage — and emits run/validation.json with a pass/warn/fail verdict; a fail is a stop, not a to-do item. Works the same on a flat export, twelve related tables, a keyless sensor stream, an index frame over 500 documents, or a warehouse table you check with SQL and never load. Phase 2 hunts the structural break — a definition, unit, currency or timezone that changed partway along whatever the data is ordered by. Use when data arrives from ingestion, before any chart, join or model, or when a number looks wrong and you cannot say why.

pymc-labs Skill

Turn a finished analysis into something a person reads and acts on — lead with the finding that settles the question or moves the decision, trace every number back to a run/findings.jsonl, run/changelog.jsonl or run/manifest.json record, and cut the rest. Works from whatever the analysis produced — one flat export, twelve joined tables, a warehouse table queried in place, an index frame over a corpus, a fitted model's posterior. Carries the data-validation verdict, the data-cleaning change log and any stage nobody ran into the writeup as caveats instead of burying them. Use when a single data question has to be answered in one chat reply, when writing up an analysis, when drafting a report, summary or readout of what the data or a fitted model showed, or when a pile of charts and tables needs an argument.

pymc-labs Skill

Profile and interrogate data before anyone makes a claim about it — a cleaned frame, a folder of parquet parts, a warehouse table you query in place, or an index frame over a corpus of documents. Summary statistics do not identify a distribution — Anscombe's quartet shares a mean, variance and correlation across four unrelated shapes — so nothing is reported that has not been plotted. Covers dtype and cardinality profiling, missingness structure, Spearman against Pearson, a correlation matrix read as blocks instead of skimmed for its biggest cells, subgroup checks and whether one named group, batch or run is an outlier against the rest, variation along whatever index orders the data, writing one row per finding to run/findings.jsonl and handing it on to modeling. Use when asked to explore or profile a dataset, before a model is fit, when one group, device, batch or period looks wrong and you need to say how it differs, or when a pile of numbers has to become defensible findings.

reopt-ai Bundle

Review consumer project code for @reopt-ai/brandapp-sdk anti-patterns across Auth, EAV (incl. 4.2 concurrency / TTL), Plans, Files, analytics bridge, and webhooks. Triggers on "brandapp-sdk review", "SDK review", "improve SDK usage", "EAV optimization", "brandapp-sdk audit", "checkout review", "Files API review", "subscription webhook audit".

reopt-ai Bundle

Install @reopt-ai/brandapp-sdk in a consumer project. Sets up Auth, OAuth, EAV (incl. 4.2 optimistic concurrency / atomic increments / TTL), Plans checkout, Files, analytics bridge, API routes, and env config. Triggers on "brandapp-sdk install", "brandapp-sdk init", "brandapp sdk setup", "brandapp sdk bootstrap", "apply SDK", "brandapp integration", "brandapp files setup", "brandapp checkout setup".

richardvt Skill

台灣資料新聞工作流程 (繁體中文/台灣專用版,對應 upstream data-journalism 的美國版)。涵蓋:資料新聞工作流 (取得→清理→分析→視覺化→敘事)、台灣主要資料來源 (政府開放資料平台、主計總處、各部會 API、CMoney、Goodinfo、TWSE 公開資訊觀測站)、資料清理工具 (pandas、OpenRefine)、視覺化工具 (Datawrapper、Flourish、g0v ChartCheck)、敘事結構、數據查核 (與 fact-check-workflow-tw 整合)、開放資料倫理。撰寫資料報導、政府開放資料分析、選舉資料視覺化、預決算追蹤時觸發。資料記者、調查報導、新聞工程師必備。

crag666 Skill

STRICT structure-and-complexity layer for non-trivial code work: designing systems, writing new modules, refactoring, implementing algorithms, or making structural decisions. Complements code-style-defaults (form of the output) and python-native (Python stdlib): this skill decides how code is structured and how fast it runs — target big-O before writing, single-responsibility grain, policy constants, testability, and per-language defaults for TypeScript, C, C++, and SQL. Triggers: "design X", "refactor this", "implement an algorithm/feature/service", "optimize this", "review this code", "what's the best way to structure X", or any task involving architecture, complexity reasoning, or multi-file changes. SKIP for trivial edits (rename, typo, single-line fix), config tweaks, and documentation edits.

startupsalad Skill

读取和编辑 Word / Excel / PPT / PDF / 图片 / 网址 / 公众号文章。**这是文档类任务的唯一入口**，进来后按「读还是写 × 存量还是新建 × 什么格式」往下派活。 **你的内置能力读不了 .pptx .xlsx .doc .xls .ppt，也读不了超大图和长条图；本机 WebFetch 也用不了（报域名校验失败）。必须走这个 skill 的脚本，绝不能回复"读不了"或让用户自己转格式。** 中文触发词（读）：读一下这个文档、看下这个文件、这个 PPT 讲了什么、帮我看看这份方案、这个表格里有什么、核对下这份报价、打开这个 PPT、看下这份标书、这个 Word 写了啥、提取这个文件的内容、这张图上写的什么、这个长图讲了什么、读这个网址、这个链接讲了什么、看下这篇公众号文章、看看竞品官网、扒一下这个页面。 中文触发词（改/写）：改一下这个 PPT、把这份文档字号调大、这个 Word 帮我改几处、批量改字号、查哪里字号不达标、给表格加个图表、这份 BP 帮我套版、生成一份 Word 报告、做个 Excel 模板、填这个 PDF 表单。 English triggers: read / open / extract this document, what does this PPT say, check this spreadsheet, read this URL, fetch this page, edit this docx / xlsx / pptx, change font size, check formatting, generate a Word report, fill a PDF form. Use whenever the user references a document file (.docx .doc .xlsx .xls .pptx .ppt .pdf .rtf .wps .et .dps), an image that may be oversized or a long strip, a URL, or a WeChat article — for reading OR editing.

vamseeachanta Bundle

Runs the right deterministic extraction lane per office/email format and records each format's KNOWN losses UNDER A TEXT/CSV LANE in a coverage ledger so a faithful extract never masquerades as complete. Use when extracting docx/xlsx/msg/pdf/pptx sources whose richest content (formulas, charts, diagrams, attachments, images, speaker notes) does not survive a text/CSV dump.

vamseeachanta Bundle

Classifies XLS/XLSX workbooks before extraction and requires a traceable input data or logic contract, code artifact, and verified output artifact for a ten-file canary. Use when spreadsheet files may contain formulas, named ranges, charts, cached values, protection, or mixed data and calculation logic.

volcengine Bundle

onboarding workflow for creating datasets and applications in Viking AI Search. Supports one-time import from local files (JSON, JSONL, CSV) and MySQL databases, plus scheduled incremental sync for append-only JSONL files and MySQL. All sources are first exported to a bootstrap JSONL file; backend-driven schema inference handles detection, and optional background sync keeps the dataset up to date as new data arrives.

wufufu770 Skill

全栈·数据与 AI 方向实现规格生成器。数据管道(Airflow/dbt)、流处理(Flink/Spark)、SQL 分析、特征存储、数据湖、ML 训练与服务化、LLM 应用、RAG、数据可视化。用户提"数据平台/ETL/大模型应用/RAG/推荐系统"的规范时使用。属 it-project-spec-generator 体系。

yaklang Skill

SQL 注入漏洞测试技能。覆盖联合注入、布尔盲注、时间盲注、报错注入、堆叠查询等攻击向量， 提供 MySQL/PostgreSQL/MSSQL/Oracle/SQLite 多数据库的特征 Payload， 包含 WAF 绕过策略和系统化测试流程，适用于 Web 应用 SQL 注入漏洞的发现与确认。

yaklang Skill

渗透测试安全测试任务设计与执行总指导。作为渗透测试的顶层编排技能，将抽象的安全测试方法论 映射到可直接调用的工具链，定义从目标接收到报告输出的完整决策流程。覆盖侦查、爬虫、 漏洞测试、利用验证的每一步具体操作，串联 recon-planning、web-crawler、xss-testing、 sql-injection、command-injection、template-injection、code-review 等全部子技能。 当用户要求进行渗透测试、安全测试或安全评估时，应首先参考此技能进行任务设计。

yeshelloab Bundle

Runs a systematic health check across all current portfolio positions: checking each holding against its thesis, flagging breaches, assessing overall portfolio balance, and producing a prioritised action list. Use whenever the user wants to review their portfolio, check the health of their holdings, do a position review, run a monthly or weekly portfolio check-in, assess which positions need attention, or get a portfolio-level view of where things stand. Triggers on: "portfolio review", "check my portfolio", "how are my positions?", "weekly review", "monthly review", "which stocks need attention?", "what's the state of the portfolio?", "portfolio health check", "run the portfolio", "go through my holdings", "thesis check on all positions", or any request to review multiple holdings at once rather than a single stock. This skill is also the natural choice when the user has just reviewed a stock tracker or spreadsheet and wants to know what to do next. Use it: do not wait for the user to ask explicitly.

deafdudecomputers Skill

The build system (Nuitka primary for CI/release → dist/, cx_Freeze for Windows installer → PST_standalone/), Inno Setup installer, GitHub Actions CI (5 workflows), standalone-mode signaling (runtime.cfg), verify_build checks, and utility scripts (update_game_data ETL, translation automation via Google Translate, theme linter, import validator). Load when building, releasing, or maintaining CI.

decocms Bundle

Read and extract cell data from .xlsx Excel spreadsheets as TSV. Use when the user uploads or references an Excel file to read or summarize.

decocms Skill

Route a file to the right reader by extension (pptx, docx, xlsx, pdf, and plain text). Use as the entry point when asked to read or summarize an uploaded file of unknown type.

dleerdefi Bundle

Extract data from subcontractor bid PDFs and produce a comparison spreadsheet. Feeds into /bid-evaluator. Triggers: 'tabulate bids', 'bid comparison', 'compare bids', 'buyout analysis', 'bid tab'.

dleerdefi Bundle

Extract tabular schedule data from construction drawings — door, window, finish, fixture, panel schedules — and output to Excel. Triggers: 'door schedule', 'extract schedule', 'schedule to Excel', 'panel schedule'.

dleerdefi Bundle

Count-based quantity takeoff and tag completeness auditing for construction drawings. Vision + OCR reconciliation, sheet markup, Excel QTO output. Triggers: 'tag audit', 'quantity takeoff', 'QTO', 'count fixtures'.

dleerdefi Bundle

Extract all submittal requirements from specification sections and generate a comprehensive submittal register in Excel. Triggers: 'submittal log', 'extract submittals', 'submittal register'. Requires /spec-splitter output.

axisrobo Skill

Fetch application metadata from CMDB (ServiceNow, etc.) or Enterprise Architecture systems via REST API or CSV export. Provides high-confidence physical location and ownership data. Does NOT provide tech stack, protocols, or auth — those must come from other readers or interview. Use before arch-req-merge.

sendx Skill

Understand what your email metrics mean and know what action to take based on the numbers.