Data & Analytics

redhat-developer Bundle

Gives the milestone dates for an RHDH version — Feature Freeze, Code Freeze, Docs Input Freeze, Docs Freeze, Go/No Go & Push, and GA announce — reading active releases from the RHDHPLAN release Feature in Jira and planned ones from the RHDH release schedule spreadsheet. Use for "when is code freeze for 1.11", "RHDH release dates", "GA date for 2.1", "what are the key dates for 1.10.3", or "has 1.10 passed feature freeze yet".

redhat-developer Bundle

Builds the "RHDH CVE Management - <version>-plugins.csv" export by walking `rhdh-plugin-export-overlays` git history on a release branch since a revision, scoped to generally-available plugin workspaces, then enriching each CVE from Jira RHIDP, RHDHBUGS, and RHDHPLAN. Use for "generate the plugin overlay CVE CSV for 1.10.3", "what CVEs were fixed in plugins since 1.10.2", or "rebuild the plugin CVE list with the ProdSec CVSS scores".

seed-forge Bundle

办公文档通用 Outflow 编排：从内容（Markdown/数据/大纲）出发，调度社区上游技能生成目标格式文档（docx/pdf/xlsx/pptx）。depends on docx, pdf, xlsx, pptx 社区上游技能。用户提到'导出为 Word''生成 PDF''做成 Excel''做成 PPT''导出文档'时使用。

seed-forge Bundle

办公文档格式互转编排：文件 → 文件的格式转换（docx→pdf, pptx→pdf, xlsx→pdf 等）。depends on 社区上游 docx/pdf/xlsx/pptx 和 LibreOffice soffice。用户提到'转成 PDF''格式转换''docx 转 pdf''文档格式互转'时使用。

seed-forge Bundle

DAO 层通用 SQL 方言兼容性检查 + 系统性修复工作流。支持 MyBatis/JPA/MyBatis-Plus/SQLAlchemy 四种持久层框架，扫描源码识别 Oracle/PostgreSQL/MySQL 方言混用风险，自动修复 80% 常见陷阱，剩余 20% 由 Agent 辅助人工确认。七阶段流程 + adapter 模式框架适配。触发词：SQL 兼容性、方言混用、Oracle 转 PG、PG 转 Oracle、MyBatis 迁移、JPA 方言、Hibernate SQL、SQLAlchemy raw SQL、数据库国产化改造、DAO 层 SQL 检查。

seed-forge Bundle

MySQL 慢查询全链诊断。开启/分析 slow query log，定位 Top-N 慢 SQL， 用 EXPLAIN 检查执行计划，识别缺失索引、全表扫描、大结果集、锁等待， 输出结构化报告与优化建议。支持 MySQL 5.7+ 与 8.0 performance_schema。

seed-forge Bundle

数据库数据层安全迁移专家技能。覆盖 schema 演进（加列/改约束/建索引）与数据搬迁的完整安全流程：备份→幂等检测→迁移→验证→失败回滚。当项目需要变更已有表结构、生产报 no such column / 唯一约束冲突、或需编写独立迁移脚本时使用。与 devlab-dao-sql-compat 互补：本技能管数据层面，后者管 SQL 语法层面。Triggers on "数据迁移", "表结构变更", "schema 演进", "no such column", "唯一约束冲突", "迁移脚本", "db migration".

seed-forge Bundle

NL2SQL/Text2SQL 知识基座（供 extends 继承）。聚合两阶段架构、查询类型分类、字段/术语映射、条件与 metric 抽取、多表 JOIN 推理、SQL 正确性与评测的深度知识与踩坑。通常被 devlab-nl2sql-engineering 继承，不直接面向用户触发。

seed-forge Bundle

Oracle 知识基座。覆盖 Connection Types、JDBC Driver、Connection Pool、LOB Handling、Character Set、SQL Dialect。供 devlab-oracle-usage 通过 extends 继承。

ntaffzii Bundle

Use this skill to simulate how a trading rule would have performed on historical price data — win rate, average return, max drawdown, profit factor — from a CSV or list of prices the user supplies, no market-data API required. Trigger on "backtest this strategy", "ทดสอบกลยุทธ์ย้อนหลัง", "how would this rule have performed historically", "moving average crossover backtest", "max drawdown of this strategy". If the user wants to size a position or apply a risk gate on a trade they're about to take, use position-sizer/drawdown-circuit-breaker instead — this skill evaluates a rule against the past, not a single upcoming trade.

ntaffzii Bundle

Use this skill to score how many stocks in a universe are in an established "stage 2" uptrend (price above the 50-day MA, 50-day MA above the 200-day MA) from a plain CSV, no market-data API required. Trigger on "uptrend participation", "stage 2 stocks", "how many stocks are in an uptrend", "50 MA above 200 MA screen". Pairs with [market-breadth-analyzer](../market-breadth-analyzer/SKILL.md) for a fuller market-regime read.

ntaffzii Bundle

Use this skill to score market breadth (the percentage of a stock universe trading above a moving average) from a plain CSV of tickers/prices/moving averages, with no market-data API required. Trigger on "market breadth", "% of stocks above 200-day MA", "breadth score", "how many stocks are participating", "is this rally broad or narrow". If the user wants a live number pulled from a real-time data feed rather than a CSV they already have, this skill still applies — just have them export/paste the data first, since this skill doesn't fetch prices itself.

carta Bundle

ManCo (management company) budgeting in Excel for Carta Fund Admin firms. TRIGGER: build/create/draft a budget, pull/import the budget, add/refresh actuals, interleave Budget/Actual/Variance, sub-account drill-down, pacing/variance analysis, "what did we spend on [X] YTD", "where did we overspend", what-if/scenario modeling (headcount, revenue shocks). ALSO fires on ANY generic management-company ask naming no specific report AND no visual surface, and shows the capability menu: "help with our ManCo", "ManCo financials", "ManCo reporting", "not sure what I need". NOT FOR: a ManCo microapp/dashboard/visual report — "build a manco microapp for [firm]", "spin up the ManCo dashboard" → carta-manco-reporting whatever the verb ("build" claims this skill only for a budget); single-FUND financials, portfolio valuations, LP reporting, cap tables, loans (carta-loan-dashboard); a NAMED consolidating statement (P&L, BS, TB, cash flow) → carta-consolidating-financial-reports or fa-manco:carta-consolidating-cash-flow.

carta Bundle

Aggregates recent deal flow in the Carta CRM into a dealmaker-facing report, auto-discovering which fields matter for this tenant's schema. Use this skill when the user says things like "deal flow analytics", "analyze our deal flow", "review deals added in the last 12 months", "who introduced most of our deals", "breakdown of deals by sector", "where is our deal flow coming from", or "/deal-flow-analytics". Defaults to a trailing-12-month window but accepts any date range or dimension the user specifies. Returns counts and concentration callouts per dimension, not a list of individual deals — use search-deals for that.

carta Bundle

Issue securities on a Carta cap table. Use when the user asks to issue certificates, stock certificates, option grants (ISO, NSO, EMI, CSOP, Unapproved, Startup Concessions, Non-Concessional, ZEPO), profits interest units (PIUs), to draft shares, grants or units, or to resume issuing from a draft set. USE WHEN the user says "issue", "grant", "draft", "award", "give equity", "give shares", "give stock", "create a certificate", "create a grant", "issue a profits interest", "issue PIUs", "grant profits interest units", "set up an option grant", "issue equity to a named person", or names any specific security type above. Also USE WHEN the user points at a spreadsheet, CSV, Carta import template, or a grant/award document as the source of the issuance ("issue the grants in this file", "here's our import template").

carta Bundle

PRIMARY and DEFAULT skill for ALL Carta investors data queries — use before any other skill for Carta Web / Fund Admin data. Carta Web / Fund Admin investors data queries against the data warehouse. For investments, portfolio companies, fund data, fund metrics, NAV, TVPI, DPI, IRR, cash flows, balance sheets, cap tables, ownership %, shareholders, 409a valuations, FMV, MOIC, fund holdings, financing rounds, convertible notes, SAFEs. Prefer over carta-soi for data queries (Cowork persistent artifacts); over carta-portfolio-valuations for read-only valuation/MOIC/investment data (that skill runs/updates valuation projects); over carta-lp-dashboard unless asked by name; over carta-consolidating-financial-reports for single-fund balance sheets. Use instead: carta-co-investors for co-investor / "who else invested" analysis; carta-waterfall-modeling for exit-waterfall / "who gets paid if X exits" modeling; carta-manco for ManCo budgeting, actuals, pacing, sub-account drill-downs, or budget/actuals breakdowns.

carta Bundle

Internal subskill for carta-reporting. Exports Carta report data to a branded Excel file. Invoked by carta-reporting or carta-reporting-markdown when the user requests Excel output. Also the entry point when the main skill receives a message starting with "Generate Carta Excel —" (the artifact prompt bar payload).

carta Bundle

Fund Forecasting (Tactyc) read-only analytics — fund performance and per-investment metrics for funds IN FUND FORECASTING (Tactyc) ONLY. A SEPARATE domain from Carta Web / Fund Admin, with its own funds and data — use carta-explore-data for those (data-warehouse, cap-table, accounting) queries. Metrics: TVPI, DPI, RVPI, gross/net IRR, MOIC, NAV, unrealized FMV, realized proceeds, committed/contributed/called capital, planned reserves, management fees & expenses, waterfall tiers and net proceeds to LP/GP, and per-company MOIC/IRR/FMV/ownership %/holding period/round events. Also route here for the Fund Forecasting app URL (fund-forecasting.app.carta.com) or 'Tactyc'. If the user hasn't said which system the fund is in, ask first — don't assume Fund Forecasting. Reports existing data only — no scenarios, no build/edit. NOT the interactive 'fund modeling' micro-app / firm-level scenario console (reprice companies, exit & IRR scenarios, reserves planning) — use carta-fund-modeling (Fund Admin data, not Tactyc).

carta Skill

Internal subskill for carta-reporting. Drives the full Claude Code interaction: schema preview, customization checkpoint, transform config (filtering, sorting, formulas, aggregations), output preview, and hand-off to carta-reporting-excel. Invoked by carta-reporting (Claude Code path) after the preview file lands. Not for direct user invocation.

carta Bundle

Internal file-ingest sub-skill for carta-issuance. Turns an uploaded spreadsheet (.xlsx/.xlsm/.csv/.tsv) or document (.pdf/.docx) into the `knowns.rows` the config panel already consumes, for certificates, option grants and profits interest units. Not invocable directly — dispatched by carta-issuance Phase 0.25.

carta Bundle

Routes to Schedule of Investments, Co-Investor Lookup, or Performance Benchmarks. Trigger on any of: "SOI", "schedule of investments", "fund holdings", "what is the fund invested in", "portfolio breakdown", "co-investor", "coinvestor", "who co-invested", "who else invested", "co-investors by stage", "performance benchmark", "peer comparison", "fund percentile", "IRR vs peers", "TVPI benchmark", "how does my fund stack up", /carta-portfolio-analytics-routing. NOT FOR: portfolio valuations/marks, LP documents, K-1, SPA audit, Form ADV, cap table, 409A, comparable company selection, loan dashboard.

carta Bundle

Builds multi-entity consolidating financial reports in Excel: consolidating P&L (income statement), balance sheet, and trial balance — individually or all three together. Resolves the firm, the entities to include, the reporting period, and the target workbook, then builds the chosen report(s). TRIGGER on "consolidating financial reports", "consolidating P&L", "firm-wide income statement", "P&L for all entities", "P&L by tag", "P&L by department", "consolidating balance sheet", "BS by entity", "balance sheet of all entities", "consolidating trial balance", "TB by entity", "all three consolidating reports", "the full financial package". ALSO fires on a generic ask with no report named — "consolidating financials", "firm-wide financial statements" — and shows the report menu. NOT FOR: single-fund/entity financials, ManCo budgets/actuals/pacing/what-if (carta-manco), consolidating cash flow (carta-manco), SOI, co-investors, Form ADV, LP reporting, cap tables, Fund Admin requests (carta-fund-admin-requests).

iamdemetris Skill

Use when writing, reviewing, or upgrading a Ruby on Rails app (Rails 7 or Rails 8); designing ActiveRecord models and queries, ActionPack controllers, Hotwire (Turbo, Stimulus, Turbo Streams) views, Sidekiq or Solid Queue workers, Action Mailer, Devise plus Pundit auth, RSpec plus factory_bot tests, and reversible migrations with strong_migrations. Covers N+1 elimination, includes vs preload vs eager_load, scopes, polymorphic and STI tradeoffs, concerns vs service objects, schema.rb vs structure.sql, propshaft and importmaps, Solid Cache, Solid Cable, Russian doll caching, and Rails 7 to Rails 8 upgrade mechanics. Triggers: Rails, ActiveRecord, ActionPack, Hotwire, Turbo, Stimulus, Sidekiq, Solid Queue, Devise, Pundit, strong_migrations, factory_bot, structure.sql. Produces models, migrations, controllers, Turbo Stream views, jobs, Pundit policies, request specs, upgrade checklists. Not for language agnostic API contract design across services, see senior-backend-engineer.

iamdemetris Skill

Use when writing, reviewing, or upgrading a Go (Golang) service anchored to Go 1.22+ (generics, range over int, log/slog, http.ServeMux method routing). Covers idiomatic error wrapping with fmt.Errorf and errors.Is / errors.As, context.Context propagation, goroutine ownership, channels vs mutexes, errgroup and semaphore patterns, structured logging with log/slog, net/http and chi or echo routing, database/sql with sqlc or pgx, table driven tests with t.Run, the race detector in CI, and pprof profiling. Triggers: Go, Golang, go.mod, go.sum, goroutine, channel, context.Context, slog, errors.Is, errors.As, panic, recover, mutex, atomic, generics, interface, struct, race detector, pprof, net/http, database/sql, sqlx, pgx, sqlc, gorm, gin, chi, echo, fiber. Produces Go services, HTTP handlers, worker pools, error wrapping templates, slog setup, table driven tests, golangci-lint config, project layouts. Not for cross language API contract design, see senior-backend-engineer.

iamdemetris Skill

Use when writing, reviewing, or debugging modern Python (3.12, 3.13) across web services, data pipelines, ML glue, and scripts. Covers type hints (mypy, pyright, PEP 695, `Self`, `Protocol`, `TypedDict`), `pyproject.toml` packaging, `uv` installs and lockfiles, ruff lint and format, dataclasses with `frozen=True`/`slots=True`, `pydantic` models, `asyncio` and `TaskGroup`, `asyncio.to_thread`, the GIL and `multiprocessing`, pytest fixtures and parametrize, hypothesis, FastAPI, httpx, sqlalchemy, pandas, polars, numpy, and profiling with cProfile, py-spy, or scalene. Triggers: Python, type hint, mypy, pyright, pyproject.toml, uv, dataclass, pydantic, asyncio, async, await, GIL, multiprocessing, pytest, pytest-xdist, FastAPI, sqlalchemy. Produces FastAPI endpoints and pydantic models, frozen/slotted dataclasses, asyncio TaskGroup patterns, pytest suites and fixtures, and CI workflows. Not for Django/DRF specifics, see django-expert.

iamdemetris Skill

Use when designing an experiment or A/B test, writing or reviewing an experiment proposal or analysis plan, sizing a study (power, alpha, MDE), checking an A/A test, picking a unit of randomization, choosing between A/B, multi armed bandit, switchback, or a quasi experiment (difference in differences, regression discontinuity, instrumental variable, synthetic control), analyzing results with confidence intervals and multiple testing correction, interpreting lift, defining primary and guardrail metrics, running cohort or segmentation analysis, or writing a result memo with a decision recommendation. Triggers: data scientist, experiment, A/B test, A/A test, hypothesis, p value, confidence interval, multi armed bandit, switchback, causal inference, lift, statistical power, sample size, MDE, propensity, segmentation, cohort, ATE. Not for shipping a model to production (serving, monitoring, retraining), see senior-ml-engineer; not for pipelines or warehouses, see senior-data-engineer.

jame581 Bundle

Use when implementing localization (i18n/l10n) — TranslationServer, CSV/PO translation files, locale switching, RTL support, and pluralization in Godot 4.3+

sanjeevrg89 Bundle

Expert data engineering for ML — the pipelines, feature stores, and data-quality discipline that decide whether models work in production ("garbage in, garbage out"). Use when building or debugging ML data pipelines (ingestion, validation, transformation, batch vs streaming), orchestration (Airflow, Dagster, Flyte, Spark, Beam), the lakehouse (Delta Lake, Apache Iceberg, Hudi, Parquet), or data versioning (DVC, LakeFS, lakeFS). Use for streaming & real-time features (Kafka/Pulsar, Flink, Spark Structured Streaming, Beam, CDC/Debezium, windowed aggregations, watermarks, late/out-of-order data, exactly-once, online/offline consistency) and real-time inference (fraud, recsys). Use for the analytics /query side — data warehouses (BigQuery, Snowflake, Redshift) and OLAP/lakehouse query engines (Spark SQL, Trino/Presto, DuckDB), columnar/partitioning/clustering and query cost, SQL for ML (window functions, point-in-time/as-of joins, cohorting), and dbt-style transformation/label/feature derivation. Use for feature

tugoukezhang Bundle

Excel Xlsx

rgourley Bundle

Build a clean, point-in-time, ready-to-backtest OHLCV dataset for a US equity universe across an arbitrary date window. Emits parquet plus a manifest plus an edge-case log, with corporate actions reconciled, survivorship treatment documented, holidays and half-days preserved correctly, and any IPO partial coverage or trading halts flagged. The dataset is the artifact a downstream Python/R/Julia backtester consumes; the rendered summary is the operator-readable companion. First skill in the suite that ships dataset output mode.

rgourley Bundle

Reconcile a position file against splits, dividends, and spinoffs to catch breaks before they hit P&L or T+1 settlement. Use when an operator hands over a CSV of positions and asks "are these right after the recent corporate actions." Runs on a free Massive Basic key.

tbc-servicos Skill

Referência e geração de SQL embarcado em ADVPL/TLPP para Protheus. Cobre BeginSQL/EndSQL, macros essenciais (%table%, %xfilial%, %notDel%, %exp%, %Order%), TCSqlExec para INSERT/UPDATE/DELETE, joins, subconsultas e anti-patterns de segurança.

tbc-servicos Bundle

Build optimized and safe SQL queries for Protheus tables. Automatically includes mandatory filters (D_E_L_E_T_, branch), suggests appropriate indexes from SIX patterns, generates both Embedded SQL (preferring FWExecStatement) and Workarea (DBSelectArea/DBSeek) versions, and warns about common Protheus SQL pitfalls. Use when user says 'build query', 'SQL for Protheus table', 'FWExecStatement', 'TCQuery', 'Workarea vs SQL'.

tbc-servicos Bundle

Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across SQL databases (PostgreSQL, SQL Server, Oracle). Focuses on SQL injection prevention, access control, code standards, and anti-pattern detection. Complements SQL optimization prompt for complete development coverage. Use when user says "review SQL", "SQL security audit", "SQL anti-patterns", "check SQL quality".

tbc-servicos Bundle

Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across SQL databases (PostgreSQL, SQL Server, Oracle). Provides execution plan analysis, pagination optimization, batch operations, and performance monitoring guidance. Use when user says "optimize SQL", "slow query", "index strategy", "execution plan analysis".

matejformanek Skill

Building or modifying a Foreign Data Wrapper (FDW) — the SQL/MED interface for accessing external data as if it were PG tables. Covers the `FdwRoutine` callback set (`GetForeignRelSize` / `GetForeignPaths` / `GetForeignPlan` / `BeginForeignScan` / `IterateForeignScan` / `ReScanForeignScan` / `EndForeignScan` for scans, `BeginForeignInsert` / `ExecForeignInsert` / … for DML), the `postgres_fdw` reference implementation, plan pushdown (WHERE / JOIN / AGG / LIMIT), extended-explain support, and the FDW-related core code (`src/backend/foreign/foreign.c`, foreign-table catalog, user mappings). Loads when the user asks about writing an FDW, `CREATE FOREIGN TABLE`, why postgres_fdw is fast, pushdown decisions (`use_remote_estimate`, `fdw_startup_cost`), user mappings and password security (`password_required`), the loopback-back-to-self bypass-RLS pattern from postgres_fdw, or adding a new pushdown-shape. Skip when the ask is about specific non-postgres_fdw wrappers (file_fdw, oracle_fdw external, mysql_fdw external