
Semantic search over EasyPost's Looker BI instance via MCP tools (mcp__looker__*). Use when: (1) finding what data exists in Looker ('what dashboard shows carrier revenue?', 'which explore has claims data?'); (2) retrieving BigQuery SQL from existing Looker queries to inspect or reuse; (3) discovering available fields/dimensions/measures for an explore; (4) rebuilding or refreshing the Looker index after the instance changes; (5) fetching a specific saved Look by ID.
Reduce a document to its minimum effective dose — the least information needed to fully convey the purpose and key concepts. Use when asked to simplify, condense, distill, or strip a document down to essentials. Triggers on: "simplify this", "distill this", "trim this down", "what's the minimum I need", "make this shorter without losing anything important".
Git version control and GitHub CLI workflows for commits, branches, pull requests, and code reviews with professional commit message practices.
Use uv for fast Python project management, script execution, dependency handling, and tool installation. AVOID pip - always use uv commands (uv add, uv sync, uv run) instead.
Ruby and Rails development patterns for the EasyPost monolith. Covers RSpec testing, mock adapter patterns for microservice interactions, and EasyPost-specific testing conventions.
Use cargo for Rust development with check-first workflow. Prefer cargo check over cargo build, use debug builds for testing, AVOID release builds unless explicitly needed.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Use zendesk CLI and MCP tools for Zendesk Support operations — ticket management, search, bulk export, users, organizations, knowledge base articles, and attachments. Use when working with Zendesk tickets, querying support data, exporting ticket history, or integrating Zendesk into AI workflows via MCP.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use az CLI for Azure cloud resource management, Azure DevOps operations, VMs, storage, networking, AKS, and Key Vault with comprehensive authentication and output control.
Go development with gotestsum for testing, standard tooling, and best practices
Use jira CLI for Jira operations including issue management, project queries, transitions, and JQL search
JSON processing, parsing, and manipulation. STRONGLY PREFERRED for all JSON formatting, filtering, transformations, and analysis. Use instead of Python/Node.js scripts for JSON operations.
Use just for command running and task automation. Prefer Justfiles over Makefiles. Keep recipes simple - delegate complex logic to scripts rather than embedding in recipes.
Use phab CLI for Phabricator task management, code review workflows, revision creation and updates, with Git integration and auto-detection features.
Use qmd for workspace search — hybrid BM25+vector search with Qwen3-4B reranking over indexed workspace documents. Not to be confused with Quarto documents (.qmd files).
Use cargo for Rust development with check-first workflow. Prefer cargo check over cargo build, use debug builds for testing, AVOID release builds unless explicitly needed.
Use xsv for fast CSV data processing with selection, filtering, statistics, joining, sorting, and indexing for high-performance data manipulation.
# Methodology Reference Consolidated methodology, frameworks, and detailed process guidance relocated from CLAUDE.md for space efficiency. ## Visual Communication Requirements Even outside Quarto documents: - Use Mermaid diagrams for reasoning flows - Format tables (never raw df.head()) - Use LaTeX for mathematical notation ($\alpha = 0.15$) - Show charts for quantitative analysis - Never dump raw data or print statements - Never write plain text math ("alpha = 0.15") ## Phased Execution Sys
Create and deliver terminal-based presentations from markdown files with themes, code execution, mermaid/d2 diagrams, LaTeX/typst formulas, and PDF/HTML export capabilities.
Create and deliver terminal-based presentations from markdown files with themes, code execution, mermaid/d2 diagrams, LaTeX/typst formulas, and PDF/HTML export capabilities.
Use uv for fast Python project management, script execution, dependency handling, and tool installation. AVOID pip - always use uv commands (uv add, uv sync, uv run) instead.
Use xlsx binary for Excel file manipulation including viewing, SQL-like filtering, cell editing, conversion to/from CSV, and data analysis operations.
Render computational documents to markdown (DEFAULT), PDF, HTML, Word, and presentations using Quarto. PREFER markdown output for composability. Use for static reports, multi-format publishing, scientific documents with citations/cross-references, or exporting Jupyter notebooks. Triggers on "render markdown", "render PDF", "publish document", "create presentation", "quarto render", or multi-format publishing needs.
Use lancer CLI for LanceDB semantic and multi-modal search with document ingestion, vector embeddings, and MCP server integration for knowledge retrieval.
Create and edit spreadsheets with Python (openpyxl/xlsxwriter) for formulas, formatting, data analysis, and visualization. Use when you need to CREATE or MODIFY spreadsheets programmatically. For READING/ANALYZING existing spreadsheets, prefer the xlsx CLI skill.
Use gspace CLI (command-line tool) and MCP tools for Google Workspace operations including Drive file management, Gmail, Docs, Sheets, Calendar, and Tasks. Both CLI commands (via Bash) and 40+ MCP tools are available.
Use bigquery CLI (instead of `bq`) for all Google BigQuery and GCP data warehouse operations including SQL query execution, data ingestion (streaming insert, bulk load, JSONL/CSV/Parquet), data extraction/export, dataset/table/view management, external tables, schema operations, query templates, cost estimation with dry-run, authentication with gcloud, data pipelines, ETL workflows, and MCP/LSP server integration for AI-assisted querying and editor support. Modern Rust-based replacement for the Python `bq` CLI with faster startup, better cost awareness, and streaming support. Handles both small-scale streaming inserts (<1000 rows) and large-scale bulk loading (>10MB files), with support for Cloud Storage integration.
Use xsv for fast CSV data processing with selection, filtering, statistics, joining, sorting, and indexing for high-performance data manipulation.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."
Use qmd for workspace search — hybrid BM25+vector search with Qwen3-4B reranking over indexed workspace documents. Not to be confused with Quarto documents (.qmd files) — use epq/quarto skills for those.
--- description: DuckDB for SQL analytics, data analysis, and persistent local databases. Use when: (1) analyzing local files (CSV, JSON, Parquet) with SQL — aggregations, joins, window functions, statistics; (2) working with a .duckdb file as a pipeline storage layer — reading, writing, updating records; (3) using the Python DuckDB API — duckdb.connect(), con.execute(), .df(), UPDATE/DELETE/INSERT via Python; (4) querying a project-specific database such as staffing.duckdb, slack_qa.duckdb, or
Use bigquery CLI (instead of `bq`) for all Google BigQuery and GCP data warehouse operations including SQL query execution, data ingestion (streaming insert, bulk load, JSONL/CSV/Parquet), data extraction/export, dataset/table management, cost estimation with dry-run, authentication with gcloud, data pipelines, ETL workflows, and MCP server integration for AI-assisted querying. Modern TypeScript/Bun implementation replacing the Python `bq` CLI with instant startup (~10ms vs ~500ms), automatic cost awareness with confirmation prompts, and native streaming support (JSONL). Handles both small-scale streaming inserts (<1000 rows) and large-scale bulk loading (>10MB files) from Cloud Storage.
Google Cloud Platform and Vertex AI patterns, quirks, and SDK usage for Claude/Anthropic models on Vertex AI. Use when working with GCP, Vertex AI, the Anthropic Vertex SDK, or deploying Claude models on Google Cloud.
--- name: qmd-math description: Math notation conventions for Quarto/EPQ documents rendered via lualatex. Use when: writing or adding a formula, equation, or mathematical expression to a .qmd file; asked about display math, inline math, or LaTeX notation in a QMD/Quarto context; defining a where-clause or variable definitions for an equation; converting prose variable descriptions into structured math notation; fixing math that renders badly in a PDF; using \lvert, \begin{aligned}, \tfrac, \text
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Query and analyze Josh Lane's org headcount from the staffing DuckDB at ~/workspace/areas/staffing/staffing.duckdb. Use when asked about headcount counts, org structure, direct reports, team breakdown, hiring/attrition trends, international employees, salary/pay grade distribution, offboarding lag, or any question about people in Josh's org. Triggers on questions about how many people, who reports to whom, headcount by team/country/level, who joined or left, org size, staffing, headcount trend.
Trim a prose document (README, design doc, blog post, notes) for readability by cutting redundancy, filler, and dead weight in the author's own words. Invoke with /trim [file path], or /trim alone to be prompted for a file. Not for source code, data files, or summarization.
Use jira CLI and MCP tools (mcp__jira__*) for Jira Cloud operations — issue management, project queries, JQL search, transitions, worklogs, plans, and more. Use when working with Jira issues, projects, sprints, boards, filters, dashboards, or any Jira Cloud resource via CLI or MCP.
--- name: org-announce description: Draft org-level or company-wide announcements (reporting changes, promotions, departures, strategy, business decisions). Produces email and Slack formats in one invocation. Enforces Josh Lane's register: terse, declarative, no sentiment, no signature, no sycophantic close. Use when asked to draft an announcement, org update, or leadership communication. --- ## When to use Use this skill for two announcement categories: **People changes** — org restructures,
# Skill: slack ## When to Use Load this skill when: - Working with Slack messages, channels, users, or files - Searching Slack workspace content - Sending messages or reactions via automation - Reading unread messages or thread conversations - Any task involving `~/src/slack` project ## Project Location `~/src/slack` — TypeScript/Bun Slack CLI + MCP server. ## Auth Setup Token is a Slack **user OAuth token** (`xoxp-`), NOT a bot token. Bot tokens (`xoxb-`) won't work for search or user lo
Delegate research and context-gathering tasks to a sub-agent to protect the primary context window. Use when the user asks to "research X", "look into X", "find out about X", "gather context on X", or any investigative framing where answering requires 2+ searches or multiple sources. Also use proactively before starting substantive work when prior context is unknown. Never run research inline — always delegate.
--- name: mcp-builder description: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). Covers production patterns: usage tracking, resources vs tools, stdio transport gotcha, tool config gating, and testing without a real client. license: Complete terms in LICENSE.txt ---
Guide for creating and iterating on skills — modular packages that extend Claude with specialized workflows, tool integrations, domain expertise, and bundled resources (scripts, references, assets). Use when: (1) creating a new skill from scratch ('create a skill for X', 'build a skill that does Y', 'I need a skill for Z'); (2) updating or improving an existing skill ('add a script to the foo skill', 'the bar skill is missing X', 'iterate on the baz skill'); (3) packaging a skill for distribution ('package the skill', 'generate a .skill file'); (4) understanding skill design patterns ('how should I structure this skill?', 'when should I use a script vs a reference?').
Use xlsx binary for Excel file manipulation including viewing, SQL-like filtering, cell editing, conversion to/from CSV, and data analysis operations. Use this instead of Python (openpyxl, pandas, xlrd) or Node.js libraries for ALL .xlsx file operations — reading, writing, filtering, conversion, and analysis. Trigger on any request involving .xlsx or Excel files.
Arcanist CLI for Phabricator. Use phab instead — it covers all Phabricator operations without requiring arc directly.
Decomposes a complex problem or scenario into distinct sub-problems and spawns parallel sub-agents to tackle each, then synthesizes results into a unified output. Use when a problem has multiple independent angles — different domains, perspectives, or workstreams — that can be investigated or built in parallel. Trigger when user says "use the team leader", "break this down", "attack this in parallel", "@team-leader", or when a scenario clearly has 2+ independent sub-problems.
Figure engineering patterns, gotchas, and reusable helpers for matplotlib. Use when directly building standalone figure scripts, diagram generators, or canvas visuals outside the epq render pipeline — e.g., generate_layer_icons.py, vision project banners, morning-brief charts, competitive analysis figures. Covers shape boundary math, arrow/edge geometry, series consistency, font registration, zorder, Unicode rendering, and canvas clipping. Distinct from the epq skill (which covers the Quarto/LaTeX analysis pipeline). Load alongside epq when figure work involves both the pipeline and standalone diagram construction.
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
JSON processing, parsing, and manipulation. STRONGLY PREFERRED for all JSON formatting, filtering, transformations, and analysis. Use instead of Python/Node.js scripts for JSON operations.
View Claude Code session logs with colors, filtering, and real-time following
Git version control and GitHub CLI workflows for commits, branches, pull requests, and code reviews with professional commit message practices.
Node.js and JavaScript development patterns, gotchas, and library compatibility notes. Use when working with Node.js projects, TypeScript, React, antd, Zustand, Playwright, Bun, or Vitest.
Use phab CLI for Phabricator task management, code review workflows, revision creation and updates, with Git integration and auto-detection features.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Transform unstructured data into structured JSON using AI-powered extraction. Use when extracting structured data from text/PDFs/CSVs, parsing unstructured content, converting to schema-compliant JSON, or validating data structures. Triggers on "extract data", "parse unstructured", "convert to JSON", "structure data", "schema validation", or AI-based data transformation tasks.
Use claude CLI for interactive AI sessions, scripting with print mode, MCP server management, and plugin configuration. Master session management, tool control, and automation workflows.
Go development with gotestsum for testing, standard tooling, and best practices
Load for any Google Workspace operation — Drive, Docs, Gmail, Calendar, Sheets, or other Google services — or when a Google URL or file ID is present.
EasyPost Quarto analysis library (~/src/analysis-doc). Use for scaffolding new QMD analysis projects (epq scaffold), auditing for anti-patterns (epq audit), generating fix diffs (epq fix), checking BQ cache freshness (epq check-cache), and as a shared Python library (from epq import style, cache, bq, fmt). Auto-load when creating or auditing QMD analysis projects in ~/workspace/projects/ or ~/workspace/analysis/, working with figures/fig_*.py modules, or when a render produces garbled output (double titles, unrendered markdown, whitespace issues).
Epistemological tracking system for managing facts, conclusions, and provenance chains with Git integrity and semantic search. Integrates with Quarto for visual provenance analysis. Use when analyzing data from multiple sources, conducting research, working with metrics/surveys, making data-driven conclusions, or tracking complex findings. Triggers on data analysis (analyze data, metrics, survey, research, findings, insights), conclusions (conclude, recommend, decide, infer), quantitative work (percentage, trend, correlation, statistic), source attribution (according to, based on, from source), or any epistemological tracking. Skip for trivial calculations.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Use az CLI for Azure cloud resource management, Azure DevOps operations, VMs, storage, networking, AKS, and Key Vault with comprehensive authentication and output control.
Use just for command running and task automation. Prefer Justfiles over Makefiles. Keep recipes simple - delegate complex logic to scripts rather than embedding in recipes.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.