Data & Analytics

liaoann Skill

Use when working with Drizzle ORM on any SQL driver (Cloudflare D1, Postgres, MySQL, SQLite, LibSQL) — writing or editing a schema, adding or changing migrations, declaring column types (especially JSON columns), setting up timestamps, or testing Drizzle-backed code with Vitest — and when reviewing such a change. Mentions of drizzle, drizzle-kit, `.sql` migrations, or `drizzle/meta` are triggers.

liarmttt Bundle

Design and validate structured in-card data models for SillyTavern rolecards, including table schemas, stable record keys, MVU message-floor storage, field bindings, deterministic migrations, and status-bar or control-center consumers. Use when a rolecard behaves like a small database application or needs schema and migration fixtures across normal multi-floor conversations. Do not introduce an external SQL service or claim same-floor compatibility without real-host evidence.

scallop-io Skill

Aggregate user positions and protocol TVL via the Scallop TS SDK portfolio query. Use when user says "portfolio", "TVL", "total value locked", "lendings", "user dashboard", "all obligations", "net worth", "aggregate positions", "user portfolio", "protocol stats", or asks for a single view across supplies + obligations + veSCA.

signalpilot-labs Skill

Product analytics rules: calendar spine cross-joins, date boundary caps, event type pivoting, first-run NULL behavior.

szotasz Bundle

Shared, dependency-free Python helpers for the agent fleet - dashboard API (memory, messages, kanban), Telegram MarkdownV2 escaping, and rule-based Mail.app triage. Use to do deterministic work (fetch/filter/SQL/format/escape) in Python instead of burning model tokens doing it in the LLM turn. The dashboard token is read from store/.dashboard-token at call time, never hardcoded.

truefoundry Bundle

Builds and deploys data processing and ML training pipelines using TrueFoundry Workflows (built on Flyte). Use when creating DAGs, orchestrating multi-step tasks, scheduling ETL pipelines, or running ML training workflows.

rubicon Bundle

Get LinkedIn and career data into Salience and normalize it — parsing resumes, LinkedIn data exports, pasted profile text, bios, case studies, and post or engagement data; resolving a person or company to a profile; and selecting a retrieval path with graceful fallbacks when direct access is unavailable. Also ingests a directory the user already keeps — a career folder, portfolio archive, or document vault — surveying it and extracting facts with provenance instead of interviewing for what is already on disk. Triggers on "import my resume", "here's my profile export", "parse this", "pull this post", "look up this profile", "connect LinkedIn", "my career files are in", "point at this folder", "use my corpus". Not for writing profile copy (use salience-profile) or interpreting performance (use salience-analytics).

rubicon Bundle

Track what actually produces opportunity — profile changes, content performance, experiment history, and the outcomes that matter (recruiter contact, qualified conversations, interviews, consulting inquiries, advisory and speaking invitations). Learns from what the user accepts, rejects, and corrects. Triggers on "how did my posts do", "what's working", "did that change help", "review my performance", "my profile isn't getting views", "was that worth it", "why did this post flop", "postmortem on this post". Not for producing content (use salience-content) or auditing the profile (use salience-profile).

serverpod Skill

Serverpod ORM with PostgreSQL or SQLite — CRUD, filters, sorting, pagination, includes, transactions, raw SQL, client-side database. Use when reading or writing data at runtime. To declare tables and relations instead, use serverpod-models.

winhok Bundle

评估 SQL 查询的安全性、规范性和性能风险。覆盖 OLAP（Spark/Hive、Impala、ClickHouse）和 OLTP（MySQL）两大场景。审查维度：命名规范、编码格式、查询优化、索引策略、DDL/DML 规范、引擎特性、锁与事务。当用户贴出 SQL 问"能不能跑"、"会不会查爆"、"帮我 review"、"格式对不对"、"命名规范吗"、"这个 EXPLAIN 怎么看"、"为什么这么慢"、"能不能在生产跑"、"帮我看看这条 SQL"、"这个查询有没有问题"、"Code Review 一下"、"建表语句有问题吗"、"ETL 上线前审查"、"慢查询优化"、"索引怎么建"、"会不会死锁"、"大批量删除怎么做"时触发。即使用户只是贴了一条 SQL 没说别的，也应触发。支持 SELECT/DDL/DML/EXPLAIN 输出分析。

winhok Bundle

TestSpec 生成测试用例（流程第 4 步）- 根据测试点（specs/*.md）生成完整测试用例并导出 Excel (.xlsx) 或 XMind (.xmind) 格式。当用户要「生成用例」「写测试用例」「导出 Excel」「导出 XMind」「生成测试用例表格」或执行 testspec-generate / testspec generate 时使用。也适用于用户说「把测试点展开成用例」「帮我出一份测试用例表」「生成 Excel 测试文档」的场景。使用内置 Python 脚本完成 Excel/XMind 文件生成，不依赖外部技能。

brianv1981 Skill

Export A.I.M. knowledge into a portable DataJack cartridge (.engram / parquet exchange). Use when packaging knowledge for backup or P2P share. Slash: /aim-export-cartridge. Modernized for aim-agy plugins/datajack.

isnoobgrammer Skill

Compresses .md files or directories of text-based files (.md, .txt, .rst, .yaml, .json, .csv, .log) to reduce token count while preserving all meaning and technical accuracy. Supports intensity levels: lite (~30% reduction), standard (~50%), aggressive (~65%), extreme (~80%). Invoke with /compress [path] [optional: lite|standard|aggressive|extreme]. Triggers on: "/compress", "compress this", "shrink this file", "reduce tokens", "make this smaller", "compress docs", "compress directory".

stukh Skill

Convert manual test cases into automated E2E tests. Use when: (1) automating existing manual tests, (2) transforming TMS test cases to E2E tests, (3) automating a manual test suite, (4) converting TestRail or Qase test cases to Playwright E2E via MCP. Accepts test cases as text, file path, TMS reference (TestRail XML, Qase JSON, local JSON), CSV export, or live TMS connection (TestRail MCP, Qase MCP).

antgroup Bundle

Data analysis and visualization. Query databases, generate reports, automate spreadsheets, and turn raw data into clear, actionable insights. Use when (1) you need to analyze, visualize, or explain data; (2) the user wants reports, dashboards, or metrics turned into a decision; (3) the work involves SQL, Python, spreadsheets, BI tools, or notebooks; (4) you need to compare segments, cohorts, funnels, experiments, or time periods; (5) the user explicitly installs or references the skill for the current task.

antgroup Bundle

Extract structured information from websites using web_fetch for simple pages and browser automation for dynamic sites, login-gated flows, pagination, infinite scroll, or pages that require clicking/searching/filtering. Use when the user asks to scrape a site, collect listings, gather fields from many pages, monitor website changes, or turn webpage content into structured summaries/JSON/CSV.

antgroup Bundle

DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query", "data analysis", "parquet", "convert data".

jarredkenny Bundle

xlsx

timschoch Skill

Run Neon operations with the neonctl CLI — list/create projects and branches, get connection strings. Use when a task needs a Neon project, branch, or connection string. Not for writing SQL or app code.

timschoch Skill

Run Payload migrations and type generation with the payload CLI. Use after changing Payload collections or fields, or to run/check migrations. Not for content edits or raw SQL.

timschoch Skill

Upload sourcemaps and symbol files to PostHog error tracking with posthog-cli. Use in release/build steps that must make stack traces readable. Not for analytics queries or app instrumentation.

rosuh Bundle

Manages Android performance profiling and debugging. Triggers when the user asks to record or analyze Android performance data, such as system traces, heap dumps, method recordings, callstack samples, memory allocations, or investigate bottlenecks, jank, memory leaks, and app startup issues on Android, or when the user asks to write, debug, or execute ad-hoc SQL queries. Applies to both user and system apps or services.

312362115 Skill

数据库代码审查 + Migration 安全检查。 代码审查：锁表风险、索引缺失、慢 SQL 模式、N+1 查询。 Migration 审查：破坏性操作、Schema 漂移检测、回滚方案。 适用于 SQL（MySQL/PostgreSQL/SQLite）和 ORM（Prisma/TypeORM/Sequelize/SQLAlchemy/Drizzle）。 触发词：数据库检查、migration 检查、慢 SQL、索引、锁表、schema 漂移、db review。 触发场景：新增/修改 migration 文件后、数据库相关代码 review、上线前检查、性能排查中发现 DB 瓶颈。

power-agent Bundle

Progressive-disclosure workflow for PyPSA studies. Use whenever the user wants to load or build a PyPSA network, inspect components or time series, run power flow, solve operational OPF, or run capacity-expansion / investment optimization — even when they just say "optimize the dispatch", "size the storage", "run an expansion", or hand over a netCDF/CSV network like case39.nc. Exposes network inspection and feasibility before large optimization, and operational optimization before investment. Reach for this instead of answering PyPSA questions unaided.

power-agent Skill

Progressive-disclosure workflow for PowerWorld Simulator studies through PowerMCP. Use whenever the user wants to open a PowerWorld case, solve the base power flow, inspect flows or voltages, change model data, run contingency analysis, or pull sensitivity matrices (PTDF, LODF, Jacobian, Ybus) — even when they just say "solve this case", "run contingencies", or "give me the PTDF". Exposes base-case operations before contingencies and matrix analytics. Reach for this instead of answering PowerWorld questions unaided.

zengtianli Skill

数据 deliverable 写入前的三角对账（本地 DB + ≥2 独立网源），消灭"Wuxing 错配 Jiaxing / xlsx 没对公报 / 作者顺序错"那类因 cross-check 缺失被退回的事件。用户说"/verify-data X" / "校核 X" / "三角对账 X" / "X 对不对"，或自己在写 deliverable（报告 / xlsx / 简历 / 论文 / 法律意见）前需要落入具体声明时触发。

zengtianli Bundle

洪水风险图项目知识。当处理风险图数据、QGIS空间处理、Excel表格填充时触发。

anyhui Bundle

飞书云空间：管理云空间中的文件和文件夹。上传和下载文件、创建文件夹、复制/移动/删除文件、查看文件元数据、管理文档评论、管理文档权限、订阅用户评论变更事件；也负责把本地 Word/Markdown/Excel/CSV 导入为飞书在线云文档（docx、sheet、bitable）。当用户需要上传或下载文件、整理云空间目录、查看文件详情、管理评论、管理文档权限、订阅用户评论变更事件，或要把本地文件导入成新版文档、电子表格、多维表格/Base 时使用。

aws-samples Skill

Parse a customer-provided control framework file (xlsx/json/md) into normalized framework_objectives[]. Produces map-framework-parsed.json consumed by map-assemble. Supports CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001.

bastani-inc Bundle

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

bastani-inc Bundle

Use this skill whenever a task involves a document file (PDF, DOCX, PPTX, XLSX, or image) and you need to read it or pull text, tables, or specific values out of it — to answer a question about its contents, look up a figure, or extract data. Provides fast, local, model-free extraction via the `lit` CLI with disciplined, low-cost search patterns.

extruct-ai Skill

Create an Extruct company table from user-provided data, upload rows, and optionally add enrichment columns. Handles the full flow: parse input (CSV, pasted list, or structured data), create or reuse a table, upload domains in batches, add agent columns, and trigger enrichment. Triggers on: "create table", "upload companies", "add to extruct", "new extruct table", "import companies", "upload list to extruct".

glebis Skill

Use when the user wants to install the tools, skills, and software recommended for a specific lab meeting — the lesson's toolkit. Triggers on "set up tools for meeting 1", "install lesson toolkit", "what do I need installed", "установи инструменты урока", "поставь скиллы занятия", "что нужно установить к занятию". Fetches the cohort curriculum from agency-lab.glebkalinin.com, reads the meeting's toolkit list, checks what is already installed, installs the missing pieces (globally by default), and records them in the lab vault.

glebis Bundle

Use when the user wants a practice assignment between Claude Code Lab meetings — a concrete task tied to a specific lab meeting, that combines their personal goals with what was actually covered in the presentation. Triggers on "give me homework", "generate a practice task", "what should I practice", "homework for meeting 3", "задание на неделю". Fetches the current cohort's curriculum from agency-lab.glebkalinin.com, uses the meeting summary as the presentation record, reads the lab vault (plus optional sandbox) for personal context, and writes the assignment as a new markdown file. Also updates progress.md and optionally installs recommended agents.

alexzhu0 Skill

Use when reviewing schema migrations, SQL changes, data backfills, index changes, or rollout plans for data loss risk, locking, rollback gaps, validation checks, and production safety.

altinity Bundle

Read-only ClickHouse security audit expert for live or exported systems. Use when assessing ClickHouse security posture, reviewing users, roles, grants, settings profiles, row policies, table functions, external sources, table engines, executable UDFs, audit logs, named collections, password hash hygiene, SQL SECURITY DEFINER, impersonation, TLS/network exposure, Keeper/interserver security, encryption at rest, backups, the HTTP interface surface, cluster security, or version-specific ClickHouse security behavior. Diagnoses from SQL/system tables, supplied configuration files, query logs, access metadata, and ClickHouse/Altinity documentation.