Stay in Lane
Before making changes, verifies they match what was actually requested. Activates when about to modify files, add features, or refactor code. Catches scope creep before it happens - no "while I'm here" improvements.
Install
npx skills add ElliotJLT/Claude-Skill-Potions --skill stay-in-lanegit clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/stay-in-lane ~/.claude/skills/stay-in-lanePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Stay In Lane <purpose> Claude's helpful instincts cause scope creep. User asks to fix a typo, Claude refactors the function. User asks for one feature, Claude adds three. This skill forces a scope check before every change: "Was this asked for?" </purpose> ## When To Activate <triggers> - About to modify a file - About to add a new feature or function - Thinking "while I'm here, I should also..." - About to refactor or "improve" existing code - Adding error handling, validation, or edge cases not mentioned </triggers> ## Instructions ### Before ANY Change Ask yourself: ```markdown ## Scope Check **User asked for:** [restate the request in one sentence] **I'm about to:** [describe the change] **Match?** [Yes / No / Adjacent] ``` ### Decision Matrix | Match | Action | |-------|--------| | **Yes** | Proceed | | **No** | Stop. Don't do it. | | **Adjacent** | Ask first OR note it for later | ### Adjacent Work "Adjacent" means related but not requested: - Fixing a bug and noticing a nearby code smell - Adding a feature and seeing an optimization opportunity - Updating a file and wanting to improve formatting For adjacent work: 1. Complete the requested change FIRST 2. Note the adjacent item: "I noticed X could be improved" 3. Let the user decide ### Common Scope Creep Patterns **The Helpful Refactor:** > User: "Fix the typo in the error message" > Claude: *rewrites entire error handling system* **The Preemptive Feature:** > User: "Add a save button"
Details
- Skill name
stay-in-lane- Repository
- ElliotJLT/Claude-Skill-Potions
- Path
skills/stay-in-lane/SKILL.md- License
- MIT
- Repo updated
- 12 February 2026
FAQ
What does the Stay in Lane skill do?
Before making changes, verifies they match what was actually requested. Activates when about to modify files, add features, or refactor code. Catches scope creep before it happens - no "while I'm here" improvements.
How do I install the Stay in Lane skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill stay-in-lane. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Stay in Lane popular?
It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.
Related skills
Agent Audit
62ElliotJLT/Claude-Skill-Potions
When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.
Battle Plan
62ElliotJLT/Claude-Skill-Potions
Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.
Breadcrumbs
62ElliotJLT/Claude-Skill-Potions
Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.
Trace It
62ElliotJLT/Claude-Skill-Potions
Before modifying shared code (utilities, types, configs, base classes), traces all callers and dependents first. Activates when editing files in shared/, utils/, lib/, or anything imported by 3+ files. Prevents "fixed one thing, broke three others.
Single Purpose Variables
43obra/clank
Use each variable for exactly one purpose - no hybrid coupling or hidden meanings
Validating Inputs
43obra/clank
Check all external inputs for validity - garbage in, nothing out, never garbage out
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.