getting-shittdone

Orchestrate plan-driven TDD execution of Linear issues with human approval gates.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/ships/eden --skill getting-shittdone
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: getting-shittdone
Source: https://github.com/ships/eden/tree/main/assets/claude/skills/getting-shittdone
Command: npx skills add https://github.com/ships/eden --skill getting-shittdone

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) and references (resource) components.

What problem does it solve?

It helps human-AI pairs reliably execute Linear issues through plan-driven TDD without losing alignment between research, implementation, and approvals.

Core Features & Use Cases

  • Human-approved phase workflow: Claude researches, plans, and implements while the human explicitly approves at Phase 2-3 and Phase 4 boundaries.
  • Repo-aware phase detection: It determines the right next step based on whether the branch exists and whether the issue-specific plan file exists and has been audited.
  • Dependency-aware branching: It selects a base branch by inspecting Linear blocking issues and uses discrete merge commits for unmerged blockers to enable clean rebasing later.
  • Plan Mode enforcement: It requires using Claude’s native Plan Mode for creating the persistent _PLAN_{issueKey}.md handoff artifact.
  • TDD execution guardrails: It directs commit delegation and requires explicit human review before marking the PR ready.

Quick Start

Use the getting-shittdone skill to start or resume execution of a specific Linear issue key with branch setup, plan creation in Plan Mode, and human checkpoints at each phase boundary.

Frequently Asked Questions about getting-shittdone

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute Linear issues using a test-driven development workflow with AI?

You can execute Linear issues using TDD by orchestrating a plan-driven workflow that creates issue branches, generates a persistent plan file, and applies changes via a test-first approach across defined phases with human approval gates.

How does repo-aware phase detection work when resuming a Linear TDD branch?

Repo-aware phase detection determines the next step by inspecting whether the issue branch exists and whether the issue-specific plan file has been created and audited, ensuring seamless workflow resumption without losing alignment.

Can I branch from a Linear issue that has unmerged blocking dependencies?

Yes, dependency-aware branching inspects Linear blocking issues to select a base branch and uses discrete merge commits for unmerged blockers, enabling clean rebasing later when the dependencies are resolved.

When do I need explicit human approval in a plan-driven TDD workflow?

Explicit human approval is required at Phase 2-3 and Phase 4 boundaries, ensuring the human reviews the research, plan, and implementation before the AI proceeds to the next step or marks the PR ready.

Does Claude Plan Mode support creating persistent handoff artifacts for TDD?

Yes, Plan Mode is enforced for creating the persistent plan file handoff artifact, which captures the research and implementation strategy to maintain alignment between the human and AI during TDD execution.

What are the limitations of automating Linear status updates during TDD execution?

The workflow updates Linear issue statuses throughout the TDD phases but does not modify the issue bodies, meaning you cannot automate adding detailed implementation notes or changing the issue description directly.