safe-bypass-flow
Isolates risky coding tasks into separate worktrees to protect the main project branch.
Install
mkdir -p .claude/skills/safe-bypass-flow && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14631" && unzip -o skill.zip -d .claude/skills/safe-bypass-flow && rm skill.zipInstalls to .claude/skills/safe-bypass-flow
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when starting bypass, autopilot, or long-running risky coding work that should be isolated from the main checkout before executionKey capabilities
- →Prepare an isolated execution environment
- →Record base ref and SHA for recovery
- →Create a dedicated Git worktree and branch
- →Checkpoint worktree before destructive work
- →Push checkpoints to remote for recovery
- →Remove worktree after successful merge
How it works
This skill establishes an isolated Git worktree and branch for risky operations, records the base reference, checkpoints progress, and pushes changes to a remote for recovery.
Inputs & outputs
When to use safe-bypass-flow
- →Running long-running refactors
- →Isolating destructive cleanup tasks
- →Safety-first experimentation
About safe-bypass-flow
Prepares an isolated execution environment using Git worktrees. It requires a recovery path and checkpointing before executing complex or destructive refactors.
Use when starting bypass, autopilot, or long-running risky coding work that should be isolated from the main checkout before execution
When not to use it
- →When starting from the main checkout
- →When skipping remote pushes for temporary branches
- →When deleting worktrees before confirming remote backup
Limitations
- →Requires Git worktree functionality
- →Relies on `scripts/harness` for preflight and checkpointing
- →Requires manual confirmation of remote backup before worktree removal
How it compares
This skill enforces a safety-first workflow by isolating risky coding tasks in dedicated Git worktrees with explicit recovery paths, unlike directly performing changes on the main checkout.
Compared to similar skills
safe-bypass-flow side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| safe-bypass-flow (this skill) | 0 | 2mo | No flags | Intermediate |
| glab | 6 | 3mo | Review | Intermediate |
| bash-linux | 7 | 6mo | Review | Intermediate |
| azure-devops-cli | 4 | 5mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
glab
NikiforovAll
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
bash-linux
davila7
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
azure-devops-cli
github
Manage Azure DevOps resources via CLI including projects, repos, pipelines, builds, pull requests, work items, artifacts, and service endpoints. Use when working with Azure DevOps, az commands, devops automation, CI/CD, or when user mentions Azure DevOps CLI.
gitlab-ci-patterns
wshobson
Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.
create-worktree-skill
disler
Use when the user explicitly asks for a SKILL to create a worktree. If the user does not mention "skill" or explicitly request skill invocation, do NOT trigger this. Only use when user says things like "use a skill to create a worktree" or "invoke the worktree skill". Creates isolated git worktrees with parallel-running configuration.
domain-dns-ops
steipete
Domain/DNS ops across Cloudflare, DNSimple, Namecheap for Peter. Use for onboarding zones to Cloudflare, flipping nameservers, setting redirects (Page Rules/Rulesets/Workers), updating redirect-worker mappings, and verifying DNS/HTTP. Source of truth: ~/Projects/manager.