Data & Analytics

matejformanek Skill

PostgreSQL's PL/pgSQL procedural-language implementation — `src/pl/plpgsql/src/` — the parser (`pl_gram.y` + `pl_scanner.c`), compiler (`pl_comp.c` — turns source text into `PLpgSQL_function` struct), executor (`pl_exec.c` — the interpreter with 268 KB of statement handlers), function/DO/procedure dispatch (`pl_handler.c`), and the trusted-language sandbox boundary. Loads when the user asks about PL/pgSQL semantics not obvious from SQL (nested exceptions, RAISE / GET STACKED DIAGNOSTICS, cursor lifecycle, RECORD variables, EXECUTE dynamic SQL, GET DIAGNOSTICS, transaction control from within a procedure, plan caching for expressions, or the trusted-vs-untrusted distinction), when investigating "why is my PL/pgSQL slower than raw SQL" (typically plan-cache or exception-block reasons), when adding a new PL/pgSQL feature (has scenario `integrate-with-plpgsql`), or when working with PL/pgSQL security (recall from `2026-06-04-a9-plpgsql` session that trusted-PL gate is enforced exactly twice in `pl_handler.c`, EXE

matejformanek Skill

PostgreSQL's per-connection multi-process model — postmaster fork, backend startup / initialization / query loop / clean shutdown, auxiliary processes (checkpointer, bgwriter, walwriter, autovacuum launcher, WAL summarizer, pgarch), background workers (bgworker.c registry + parallel/logical-rep workers), signal handling, and the FATAL/ERROR/PANIC hierarchy. Loads when the user asks about how a connection becomes a backend, what runs before the first query, why a query dies mid-flight, how signals + ProcessInterrupts + CHECK_FOR_INTERRUPTS work together, how autovacuum / bgworker workers get scheduled, or when planning a feature that hooks a startup phase / adds a new auxiliary process / touches shutdown ordering. Skip when the question is about client-side (libpq, drivers) or about the SQL-level session properties (that's `tcop` for query dispatch, `gucs-config` for GUCs).

matejformanek Skill

PostgreSQL's SQL/JSON support — jsonpath (SQL:2016 path language) + jsonb (binary-encoded JSON) + the SQL/JSON operators like `->`, `->>`, `@?`, `@@`, `jsonb_path_query`. Covers `src/backend/utils/adt/jsonb*.c` (jsonb storage + operators + GIN opclass + subscripting) and `jsonpath*.c` (path language parser + executor). Loads when the user asks about jsonpath semantics, path variables ($, @, current), lax vs strict mode, predicate expressions, `jsonb_path_query` / `jsonb_path_exists`, JSON_TABLE (SQL:2023 / PG 17+), jsonb_gin operator class, memory management in jsonpath_exec (Tom Lane's 5a2043bf713 rewrite), or "why is my JSON search slow" (usually GIN or path complexity). Skip when the ask is about the older `json` type (`json.c` is separate — text representation) or about JSON output formats (that's `format_type` territory).

matejformanek Skill

Add or modify a PostgreSQL system-catalog entry — covers adding a pg_proc.dat builtin function, pg_operator.dat operator, pg_type.dat type, pg_cast.dat cast, pg_opclass.dat opclass, adding a new column on pg_class / pg_aggregate / pg_attribute / etc., BKI bootstrap entries, OID assignment policy (genbki.pl, unused_oids), catversion (CATALOG_VERSION_NO) bumping, and regenerating postgres.bki. Use whenever a PG patch edits anything under src/include/catalog/ (.h or .dat), adds a SQL-visible builtin (function/operator/type/cast/opclass), assigns or recycles an OID, or bumps the catversion. Skip for user-level information_schema queries on a running server, Django / Alembic / Rails / Flyway / Liquibase migrations, Oracle DBA_* / MySQL information_schema / Snowflake INFORMATION_SCHEMA catalog questions, schema design and normalization advice, ER-diagram tooling, and adding constraints to user-application tables.

matejformanek Skill

Edit the PostgreSQL executor or planner — covers src/backend/executor/ (nodeXxx.c, ExecInitNode/ExecProcNode/ExecEndNode/ExecReScan dispatch, PlanState lifecycle, EXPLAIN wiring) and src/backend/optimizer/ (Path → Plan via createplan.c, RelOptInfo lifecycle, add_path cost-dominance pruning, cost_* units in cost.h). Use whenever a PG patch adds or modifies a plan-node executor, introduces a new Path or Plan type, changes cost-model fields in cost.h, adds EXPLAIN output for a node, plumbs a node into execParallel.c, or tweaks join-path enumeration. Skip for end-user query tuning, EXPLAIN ANALYZE of a production query, work_mem / shared_buffers tuning, MySQL / MongoDB / BigQuery / Snowflake / DuckDB / Spark / Trino query engines, ORM query-builder optimization, and pandas / polars dataframe operations.

matejformanek Skill

Build a PostgreSQL backend loadable extension (.so / contrib module) — covers the .control file, the foo--1.0.sql install script + foo--1.0--1.1.sql upgrade scripts, PGXS vs meson build wiring, the `_PG_init` entry point, shared_preload_libraries vs LOAD vs CREATE EXTENSION load timing, chained hook installation (ProcessUtility_hook, planner_hook, ExecutorStart_hook), trusted vs untrusted extensions, and SQL-callable C function declarations (PG_FUNCTION_INFO_V1, PG_RETURN_*). Use whenever a PG extension is being written or modified — wiring _PG_init, registering hooks, picking PGXS vs meson, writing install/upgrade SQL, declaring CREATE FUNCTION ... LANGUAGE C, or marking the extension trusted. Skip for VS Code / Chrome / Firefox / Safari / browser extensions, NPM / pip / RubyGems / Cargo packages, IntelliJ / Eclipse plugins, and shell completion scripts.

knoopx Bundle

Create CLI plots from tabular data — 27 chart types from stdin/CSV/TSV. Use when generating bar, line, scatter, or box charts from DuckDB pipe output.

knoopx Skill

Process JSON with DuckDB — schema inference, SQL queries, complex joins, and streaming. Use when Nushell pipelines aren't enough for JSON analytics.

aibangjuxin Skill

You are a highly skilled AI Engineer specializing in the practical application of machine learning models. You are an expert in Python and popular AI/ML frameworks like TensorFlow, PyTorch, and scikit-learn. You excel at data preprocessing, model training, evaluation, and deployment.

tamnguyendinh Bundle

Use when the user asks to create, edit, or analyze spreadsheets.

zinohome Bundle

Comprehensive spreadsheet creation, editing, and analysis. Create with openpyxl (formulas, formatting, charts), analyze with pandas, recalculate formulas via LibreOffice. Financial modeling standards included. Triggers: Excel, XLSX, XLS, XLSM, CSV, TSV, spreadsheet, 表格, 电子表格.

cody-hutson Bundle

WMS Specialist — principal owner of the warehouse management system (WMS). Learns the WMS from its supplied doc corpus, builds an internal model, and answers/acts as its principal owner — grounded only in the ingested corpus. Composes artifact-generator and intake-desk per ADR-019 (invokes, never re-implements). Modes: Answer · Assess. Use when a question is about how the warehouse management system works, what a change to WMS configuration or a wave/allocation/replenishment flow implies, or a decision that needs the WMS principal owner's grounded judgment. Triggers: "wms question", "warehouse management system", "how does the WMS handle allocation", "wms wave / pick / putaway / replenishment behavior", "assess this change against the WMS", "what does the WMS corpus say about ...".

the-perfect-developer Bundle

This skill should be used when the user asks to "use pandas", "analyze data with pandas", "work with DataFrames", "clean data with pandas", or needs guidance on pandas best practices, data manipulation, performance optimization, or common pandas patterns.

floomhq Skill

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path. Also trigger for cleaning or restructuring messy tabular data files into proper spreadsheets.

ed3design Skill

Use when reviewing or writing Python code with `try`/`except Exception:` clauses around SQL queries (asyncpg, psycopg2, sqlalchemy, sqlite3) where the except-branch either (a) silently returns an empty collection (`signals = []`, `rows = {}`, `data = None`), (b) re-renders the UI with empty state ("No active signals", "No data today"), or (c) catches with a bare/overly-broad type — without `logger.exception()` or re-raise. Danger: a schema-drift bug (column does not exist, FK-target-rename, ORM-out-of-sync) and a legitimate empty-result look IDENTICAL to the user. A dashboard panel saying "No signals today" silently means EITHER no signals OR the SQL crashed and was swallowed. Trigger phrases like "dashboard shows empty but DB has data", "except Exception: signals = []", "dashboard card permanently empty", "code swallows DB error". Do NOT load for non-DB silent-except, catch-and-re-raise patterns, or narrow except-clauses that log.

ed3design Skill

Use when adding regression-test coverage for a bug-class that manifests as a repeated source-code pattern across multiple call-sites in the same file or codebase, NOT a single localized bug. Pattern: write a static-source-inspect-test that reads the source file directly via `Path(__file__).resolve().parents[N] / "src/file.py"`, extracts pattern candidates via regex (e.g. all triple-quoted SQL blocks containing certain tokens), and asserts each candidate contains the fix-marker. Critical: include a whitelist-skip for f-string templates with externalized variables that receive the fix at their definition site. Trigger on phrases like "write bug-class coverage test", "static source inspect test", "regression guard for the same bug pattern in multiple call-sites", "why not just endpoint mocks for all 4 spots?". Do NOT load for single-call-site bugs, bug classes not recognizable in the source pattern, or files with complex multi-layer f-string nesting where false-positive whitelisting becomes unreliable.

ed3design Skill

Use when exposing a read-only SQL endpoint to a less-trusted caller (browser via HTTP, MCP-Tool to LLM, internal dashboard with copy-paste query box, future API consumer). The endpoint accepts a SQL string and must reject all mutating statements before executing. Encodes the regex-based denylist+allowlist pattern: (1) strip SQL comments (`--` and `/* */`) BEFORE matching to prevent comment-smuggle bypass, (2) normalize whitespace + uppercase, (3) denylist regex for INSERT/UPDATE/DELETE/DROP/CREATE/ALTER/TRUNCATE/CALL, (4) allowlist regex for SELECT/WITH/EXPLAIN/ANALYZE start-tokens. Trigger phrases like "read-only SQL endpoint", "SELECT-only API", "SQL escape hatch", "DB query as HTTP endpoint", "MCP tool exposes raw SQL", "Postgres read API". Do NOT load when a real SQL parser is available (sqlparse, pglast), for write-allowed endpoints, stored-procedure invocation, or DBs where SELECT itself has side-effects.

ed3design Skill

Use when about to write or execute SQL against a PostgreSQL/TimescaleDB table whose exact schema (column names, types, deprecated-vs-active-variant) is not 100% certain from current context — especially in forensic debugging where multiple tables have similar names (`ohlcv_1d` vs `ohlcv_1d_hist`, `users` vs `users_v2`) or column names have shifted over time. Iron-Law: `SELECT column_name, data_type FROM information_schema.columns WHERE table_name=$1 ORDER BY ordinal_position` is the cheapest 30-second insurance against UndefinedColumn, false-positive-empty-result, and wrong-table-queried. Trigger on phrases like "writing a query against table X", "UndefinedColumn", "column X does not exist", "verify DB schema", "I think the column is called Y", "before any forensic query". Do NOT load for ORM-mediated queries (SQLAlchemy/Django catch drift at model-load), first-time-schema-design, catalog-queries on information_schema itself, or connection issues.

ed3design Skill

Use when classifying exceptions or other library-provided objects by type AND the semantically-distinct behaviors map onto a class-hierarchy where subclasses inherit from a base with DIFFERENT desired handling. Common in retry-logic for HTTP clients (requests/httpx — Timeout vs HTTPError vs ConnectionError), Telegram bots (BadRequest inherits from NetworkError but should NOT be treated as network), SQL clients (OperationalError vs ProgrammingError), file IO (FileNotFoundError vs PermissionError vs OSError). Trigger on phrases like "retry logic for TelegramError", "isinstance vs type()", "exception type check", "subclass trap", "HTTPError vs Timeout". Produces class-hierarchy mapping via `mro()`, explicit type-classification helper, and tests locking the distinction. Do NOT load when all hierarchy exceptions should be handled identically, when docs explicitly state "always catch base class", or for first-time exception-handling design.

ed3design Skill

Use when writing aggregating SQL (SUM/AVG/COUNT) or Python-side aggregates over a NULL-able column where NULL means "data not present / not backfilled / unknown" (NOT "intentionally zero"). The naive `COALESCE(SUM(x), 0)` or `df.col.fillna(0).sum()` masks NULL-rows silently — drift goes undetected for weeks. Instead, ALWAYS pair the aggregate with an explicit `count(*) FILTER (WHERE col IS NULL)` Counter (Postgres) or `df.col.isna().sum()` (pandas), surfaced in the same response shape. Trigger phrases like "aggregate PnL", "monthly sum", "trade statistics", "NULL handling", "summary report with NULLable column", "why doesn't the aggregate match the memory", "drift in reporting". Do NOT load for columns where NULL is semantically zero (intentional NOT-NULL-DEFAULT-0 design — then COALESCE is correct), for non-aggregating queries (single-row SELECTs), or for transient runtime calculations where NULL means "in-flight" rather than "unknown".

ed3design Skill

Use when observing a "surprising anomaly" in backtest output, SQL query result, multi-run-eval-report, ML-model-performance-table, or any reporting-layer artefact suggesting a system bug, market outlier, methodological problem, or drift. Before treating the anomaly as real and dispatching forensic resources, run a 3-step triage: (1) NULL-handling check — are NULLs in numerator/denominator mishandled, was IS NOT NULL omitted? (2) Cross-window / unique-ID check — do overlapping sub-windows / joins count rows multiple times? (3) Methodology-consistency check vs previous report — was the same SQL replicated exactly? Trigger phrases like "why is WR suddenly so low", "I don't understand this anomaly", "24h drift", "baseline has changed", "backtest gives different numbers today than yesterday". Do NOT load for confirmed-real anomalies, first-time-setup-debugging without baseline, code-bugs in the algorithm itself, or UI rendering bugs.

harness Skill

Advanced engineering analytics via Harness Software Engineering Insights (SEI) MCP. Configure sprint velocity and estimation accuracy tracking, engineering investment allocation breakdowns, sprint planning with capacity forecasts, and release readiness assessments. Use when asked about sprint analytics, investment allocation, sprint planning, capacity forecasting, or release readiness. Do NOT use for DORA metrics (use dora-metrics instead). Trigger phrases: sprint velocity, sprint analytics, investment allocation, capacity planning, sprint forecast, release readiness, engineering productivity, estimation accuracy, sprint planning, scope creep, code quality trends.

mateaix Bundle

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file; create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Also trigger for cleaning or restructuring messy tabular data. The deliverable must be a spreadsheet file.

mateaix Skill

Use the optional iOfficeAI/OfficeCLI engine for advanced inspection, validation, copy-on-write editing, template merge, or visual rendering of existing .docx, .xlsx, and .pptx files. Prefer MateClaw's built-in renderDocx/renderXlsx/renderPptx tools for simple new documents. Use this skill when preserving an existing template, modifying complex Office structure, checking formatting issues, validating OpenXML, or rendering a document for visual QA. This integration targets https://github.com/iOfficeAI/OfficeCLI, not the unrelated prompt-generation project with the same name.

mateaix Skill

当用户提出数据查询需求（如'查数'、'查一下订单量'、'有多少用户'、'帮我跑个SQL'等），使用数据源工具发现表结构，生成并执行只读 SQL 查询。

mateaix Skill

读取与摘要文本类文件（txt、md、json、yaml、csv、log、代码文件等）。PDF 与 Office 文件由专用技能处理。

rodydavis Skill

Discover how to leverage SQLite's JSON support to build a NoSQL-like document store, complete with TTL-based expiration, within this powerful embedded database.

anton-abyzov Skill

Google Workspace CLI (gws) — unified command-line tool for Gmail, Drive, Sheets, Docs, Calendar, Chat, Admin, and 40+ Google APIs. Use this skill when the user wants to interact with any Google Workspace service from the terminal or via AI agents, set up gws authentication, configure the gws MCP server, manage Google Drive files, read or send Gmail, create or query Google Sheets, edit Google Docs, manage Calendar events, or automate any Google Workspace workflow. Also activate when the user mentions 'gws', 'google workspace cli', 'google drive cli', 'gmail from terminal', 'sheets api', 'google docs api', 'gws mcp', 'workspace automation', or asks to 'list my drive files', 'send email via cli', 'read my calendar', 'update spreadsheet', 'create a google doc'. Do NOT activate for native Claude MCP integrations (claude_ai_Gmail, claude_ai_Google_Calendar) unless the user explicitly wants to use gws instead, or needs services not covered by native integrations (Sheets, Docs, Drive, Chat, Admin).

ruan-cat Bundle

Use CloudBase document database Web SDK only for confirmed NoSQL collection work. Query, create, update, and delete document data; if the task mentions PostgreSQL / CloudBase PG / app.rdb(), route to postgresql-development instead.

ruan-cat Bundle

Use CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.

ruan-cat Skill

This is the required documentation for agents operating on the CloudBase Relational Database through MCP. It defines the canonical SQL management flow with `queryMysqlDatabase`, `manageMysqlDatabase`, `queryPermissions`, and `managePermissions`, including MySQL provisioning, destroy flow, async status checks, safe query execution, schema initialization, and permission updates.

5dive-ai Bundle

Audit a funnel end to end and come back with the ONE leak worth fixing plus the test that proves it — instrument the steps, measure step-to-step conversion against real benchmarks, find where users actually drop, separate a traffic-quality problem from a product problem, and design an experiment with a pre-committed success number. Use this for "signups are flat", "traffic is up and revenue isn't", activation and onboarding drop-off, checkout or paywall abandonment, trial-to-paid conversion, landing-page and pricing-page performance, retention/churn cliffs, and A/B test design or readout (including calling a test dead). Also use it to kill vanity metrics and pick a north-star. NOT for building dashboards or wiring an analytics SDK — this is the decide-what-to-fix layer that sits on top of the numbers.

genfeedai Bundle

Collect X and LinkedIn post metrics for the Genfeed content loop and emit normalized Metric JSON for feedback scoring.

genfeedai Bundle

Design repeatable Genfeed content operations systems with intake, source research, briefs, skill routing, review gates, publishing cadence, and analytics loops. Triggers on content factories, AI content agency retainers, content operations, and client production workflows.

sananthanarayan Bundle

Plan the human rollout of an AI tool or workflow to an organisation — sized cohorts, enablement per cohort, named champions, a comms plan that states what will not change, and an adoption gate every wave must pass before the next one opens. Use when a tool has been chosen and the question is how it reaches people without stalling or backlash. Do NOT use to phase a technical cutover (that's migration-plan) or to choose which use case to roll out (that's ai-use-case-triage).

xiaomimimo Skill

Query the raw trajectory SQLite database directly when the built-in memory and history tools are insufficient. Use when you need structured analysis across sessions: finding repeated errors, grouping tool calls by pattern, verifying what was actually executed, or locating specific past commands/decisions that text search cannot surface. Provides the database schema, ready-to-use SQL query templates, and per-goal strategies.