KS
Killer-Skills

land — how to use land how to use land, what is land, land alternative, land vs git flow, land install, land setup guide, git workflow automation, AI agent workflow, repository management

v1.0.0
GitHub

About this Skill

Perfect for Development Agents needing automated git workflow management. land is a git workflow automation process that ensures a clean, committed, and pushed repository state

Features

Automates git workflow using git push command
Ensures a clean and committed repository state
Wraps up work sessions with a pushed repo state
Follows Steve Yegge's 'Landing the Plane' workflow
Integrates with Beads agent memory system
Pushes changes to the repository until git push succeeds

# Core Topics

thewoolleyman thewoolleyman
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
51
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add thewoolleyman/tab-groups-windows-list/land

Agent Capability Analysis

The land MCP Server by thewoolleyman 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 land, what is land, land alternative.

Ideal Agent Persona

Perfect for Development Agents needing automated git workflow management.

Core Value

Empowers agents to maintain a clean and committed repository state using git push, ensuring seamless workflow sessions with protocols like HTTPS or SSH.

Capabilities Granted for land MCP Server

Automating git workflow for clean repo states
Ensuring successful git push for committed changes
Streamlining work sessions with reliable repo management

! Prerequisites & Limits

  • Requires git installation and configuration
  • Needs active repository access
  • Must successfully execute git push to land the plane
Project
SKILL.md
2.9 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Land the Plane

Based on Steve Yegge's "Landing the Plane" workflow from the Beads agent memory system. See: https://github.com/steveyegge/beads/blob/ff67b88/AGENT_INSTRUCTIONS.md#landing-the-plane

You are wrapping up a work session. Your job is to leave the repo in a clean, committed, pushed state with nothing left dangling.

The plane is NOT landed until git push succeeds. Do not stop before pushing. Do not say "ready to push when you are" -- that is a failure. YOU must push.

Steps

Follow these steps IN ORDER. Do not skip any step. Do not ask for confirmation between steps -- just execute the full sequence and report the results at the end.

1. Check for uncommitted work

Run git status and git diff --stat to see what's changed. If there are NO changes (working tree clean, nothing untracked), skip to step 7 and report "Already clean -- nothing to land."

2. Stage changes

Stage all modified and untracked files. Use git add with specific file paths -- do NOT use git add -A or git add .. Review the list and exclude:

  • .env files or anything that looks like secrets/credentials
  • Large binary files that shouldn't be in git
  • Runtime/temp files (.pid, .log, node_modules/, etc.)

If you find files that should be excluded, mention them in your summary.

3. Sync beads issue state

Run bd sync to commit beads issue changes to git. This ensures any issue updates from this session (status changes, new issues, closed issues) are captured before the final push.

If bd is not installed or .beads/ doesn't exist, skip this step silently.

4. Commit

Create a single commit with a clear, descriptive message summarizing ALL the work done in this session. Look at the diff and recent conversation context to write a meaningful message -- not a generic "checkpoint" or "wip".

Format:

<concise summary of what changed>

<optional body with details if the change is non-trivial>

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

5. Push -- NON-NEGOTIABLE

Pull with rebase first, then push to the remote tracking branch:

git pull --rebase
git push

If the push fails, resolve the issue and retry. Do NOT force push. If it cannot be resolved, report the specific error.

6. Clean up git state

git stash list

If there are stale stashes, note them in the summary (do not drop them without being asked).

7. Confirm clean state

Run git status one final time. Report:

  • The commit hash and message
  • The branch and remote
  • Whether the working tree is clean
  • Any files that were intentionally skipped

Output format

Report a brief summary like:

Landed. <commit-hash> on <branch> -> <remote>
  <one-line commit message>
  <N> files changed
  Working tree: clean

Or if there were issues:

Partial landing:
  Committed: <hash>
  Push: failed (behind remote -- pull needed)
  Skipped: .env, build/output.bin
  Stale stashes: 2 (run `git stash list` to review)

Related Skills

Looking for an alternative to land 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