KS
Killer-Skills

work — how to use work with Apache Arrow how to use work with Apache Arrow, work vs other query engines, work setup guide for BigQuery, what is work in data engineering, work alternative for PostgreSQL, work install for Rust developers, work tutorial for data integration, work best practices for efficient data reading, work documentation for AI agents

v1.0.0
GitHub

About this Skill

Ideal for Data Engineering Agents requiring streamlined multi-source data integration with Apache Arrow. Work is a Rust-based query engine that utilizes Apache Arrow for efficient data reading from various sources, including BigQuery and PostgreSQL

Features

Fetches issue details and creates branches using kebab-title format
Supports Test-Driven Development (TDD) for behavior changes
Implements non-behavioral wiring and types directly
Confirms repository safety with a clean tree on the main branch
Lists open issues and allows users to select one for processing
Creates deterministic branches for issue tracking and resolution

# Core Topics

fwojciec fwojciec
[0]
[0]
Updated: 3/7/2026

Quality Score

Top 5%
20
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add fwojciec/quiver/work

Agent Capability Analysis

The work MCP Server by fwojciec is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use work with Apache Arrow, work vs other query engines, work setup guide for BigQuery.

Ideal Agent Persona

Ideal for Data Engineering Agents requiring streamlined multi-source data integration with Apache Arrow.

Core Value

Enables agents to drive issue work from selection to PR with minimal back-and-forth using TDD methodology. It provides direct implementation of non-behavioral wiring/types and leverages Rust for reading data from BigQuery and PostgreSQL sources.

Capabilities Granted for work MCP Server

Automating data integration workflows
Implementing TDD for behavior changes
Streamlining PR creation from issue selection

! Prerequisites & Limits

  • Requires clean repo state on main branch
  • Depends on Apache Arrow infrastructure
  • Needs issue number input for branch creation
Project
SKILL.md
1.3 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Work Issue End-to-End

Drive issue work from selection to PR with minimal back-and-forth.

Phase 1: Preflight + Selection

  1. Confirm repo is in a safe starting state (usually clean tree on main).
  2. If issue number is missing, list open issues and ask user to pick one.
  3. Fetch issue details (including comments) and create branch <number>-<kebab-title>.

Phase 2: Implement

  1. Prefer TDD for behavior changes (red/green/refactor).
  2. Implement non-behavioral wiring/types directly.
  3. Run make validate during development.
  4. Keep scope aligned with issue constraints.

Phase 3: Review

  1. Run code-review skill.
  2. Run review-with-gemini when available.
  3. Apply straightforward fixes automatically.
  4. If blocking feedback remains, pause and present options:
    • fix and re-review,
    • proceed with explicit override,
    • stop and document learnings.

Phase 4: Finalize

  1. Run full checks (make validate-full when available, else project equivalent).
  2. Commit cleanly.
  3. Push branch and open PR with summary + test plan + Closes #<issue>.
  4. Comment on issue with PR link and validation status.

Phase 5: Handoff

After PR creation, ask whether to:

  1. merge now,
  2. leave for user merge,
  3. keep iterating on branch.

Prefer ending in a clean local state on latest main unless user wants continued branch work.

Related Skills

Looking for an alternative to work or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication