clean-up — community clean-up, robot_sf_ll7, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Code Maintenance Agents requiring automated repository validation and formatting. robot_sf in the ll7 namespace.

ll7 ll7
[0]
[0]
Updated: 3/3/2026

Agent Capability Analysis

The clean-up skill by ll7 is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for Code Maintenance Agents requiring automated repository validation and formatting.

Core Value

Empowers agents to enforce code standards by running Ruff format/fix and parallel tests, ensuring a clean and validated codebase with consistent formatting and adherence to the dev guide workflow.

↓ Capabilities Granted for clean-up

Validating repository structure
Automating code formatting with Ruff
Running parallel tests for code validation

! Prerequisites & Limits

  • Requires access to the Robot SF repository
  • Dependent on Ruff format/fix and parallel test tools
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

clean-up

Install clean-up, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Clean Up

Overview

Clean and validate the current branch for the Robot SF repo by applying the dev guide workflow, running Ruff format/fix, and running parallel tests.

Cleanup Workflow

  1. Confirm repo and guidance

    • Verify the working directory looks like the Robot SF repo (e.g., .git, docs/dev_guide.md, .specify/memory/constitution.md, and .github/copilot-instructions.md exist).
    • Read docs/dev_guide.md, .specify/memory/constitution.md, and .github/copilot-instructions.md to align with required rules.

  2. Ensure environment

    • If VIRTUAL_ENV is empty and .venv/bin/activate exists, run source .venv/bin/activate.
    • If .venv/bin/activate is missing, follow dev guide setup: uv sync --all-extras, source .venv/bin/activate, and uv run pre-commit install.

  3. Run formatting and fixes first

    • Use the shared script: scripts/dev/ruff_fix_format.sh
    • If Ruff reports issues, fix them and rerun until clean.

  4. Run tests in parallel

    • Use the shared script: scripts/dev/run_tests_parallel.sh
    • Default behavior is fail-fast + failed-first ordering: pytest -n auto -x --failed-first
    • Optional ordering toggle: scripts/dev/run_tests_parallel.sh --new-first
    • To disable fail-fast when you need a full failure set: scripts/dev/run_tests_parallel.sh --no-fast-fail
    • If tests fail, evaluate test value first (Constitution Principle XIII / dev guide testing strategy). Classify failures and decide whether to fix, defer, or ask for direction before removing or relaxing tests.

  5. Run diff-based quality gates and fix them.

    • Run changed-files coverage check: BASE_REF=origin/main scripts/dev/check_changed_coverage.sh
      • If you changed any test files, run these new tests locally.
    • Run touched-definition TODO docstring check: BASE_REF=origin/main scripts/dev/check_docstring_todos_diff.sh

  6. Report and follow-ups

    • Summarize commands run and results.
    • Note remaining failures, flaky tests, or follow-up tasks (for example, GUI tests if rendering changes were made, or CHANGELOG updates for user-facing changes).
  • Suggest commit batches and messages for any uncommited changes.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is clean-up?

Ideal for Code Maintenance Agents requiring automated repository validation and formatting. robot_sf in the ll7 namespace.

How do I install clean-up?

Run the command: npx killer-skills add ll7/robot_sf_ll7/clean-up. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for clean-up?

Key use cases include: Validating repository structure, Automating code formatting with Ruff, Running parallel tests for code validation.

Which IDEs are compatible with clean-up?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for clean-up?

Requires access to the Robot SF repository. Dependent on Ruff format/fix and parallel test tools.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add ll7/robot_sf_ll7/clean-up. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use clean-up immediately in the current project.

Related Skills

Looking for an alternative to clean-up or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

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
AI

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
AI