Auto Scope
Scopes a coding task before implementation — names the handful of files actually relevant (read/edit these), the areas to leave alone, and any open scope questions, so work doesn't start by reading the whole repo. Fires proactively at the start of substantive, multi-file, or unfamiliar-area work; stays silent on single-file edits, one-line fixes, questions, and continued work in an area already scoped this session. Use when beginning a feature, bug fix, or refactor that could plausibly touch several files or an area not yet seen this session.
Install
/plugin marketplace add borkweb/skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add borkweb/skills --skill auto-scopegit clone --depth 1 https://github.com/borkweb/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/core/auto-scope ~/.claude/skills/auto-scopePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Auto-Scope Before diving into a substantive coding task, name the files that matter and the ones that don't — so the work doesn't open by reading the whole repo to orient. The output is an **in-context scope brief**, not a file on disk and not a lock on the filesystem. Any file can still be read later; the brief steers the default, it doesn't enforce it. The win is that 5–15 named files replace an exploratory sprawl. ## 1. Self-gate — decide whether to fire at all Run only when the task plausibly touches **multiple files or an area not seen this session.** **Skip silently** — emit nothing, not even a note that you skipped — when the task is any of: - a single-file or one-line edit - a question, explanation, or review with no code change - continued work in an area already scoped earlier this session If you're skipping, say nothing about scoping and proceed normally. A "I decided not to scope this" line is itself noise. ## 2. Discover Use the current runtime's working search tool. Find entrypoints, direct callers, relevant tests and implicated config/schema files. Stop when there is enough evidence to start; do not inventory tools or narrate routine tool selection. ## 3. Degrade gracefully
Details
- Skill name
auto-scope- Repository
- borkweb/skills
- Path
skills/core/auto-scope/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Auto Scope skill do?
Scopes a coding task before implementation — names the handful of files actually relevant (read/edit these), the areas to leave alone, and any open scope questions, so work doesn't start by reading the whole repo. Fires proactively at the start of substantive, multi-file, or unfamiliar-area work; stays silent on single-file edits, one-line fixes, questions, and continued work in an area already scoped this session. Use when beginning a feature, bug fix, or refactor that could plausibly touch several files or an area not yet seen this session.
How do I install the Auto Scope skill?
Claude Code plugin: /plugin marketplace add borkweb/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Auto Scope popular?
It lives in borkweb/skills, which has 9 GitHub stars and 0 forks.
Related skills
Prototype
9borkweb/skills
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
Agents Md Lint
9borkweb/skills
Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.
Caveman
9borkweb/skills
Speak in a terse caveman style only when explicitly requested by name. Supports lite, full and ultra; persists until stopped. Ordinary brevity or token-efficiency requests do not activate it.
Cmd Clean Code
9Olshansk/agent-skills
Improve code readability without altering functionality using idiomatic best practices
Wp Local Env
9morrealev/wordpress-manager
Use when the user wants to work with a local WordPress development environment — WordPress Studio, LocalWP, or wp-env. Handles environment detection, site lifecycle, WP-CLI proxy, REST API access, symlink workflows, database operations, and preview/share.
Cmd Code What
9Olshansk/agent-skills
Catch the user up on what the agent has been doing in the current session with 3-5 ultra-tight bullet points. Use when the user invokes /cmd-what, asks "what are you doing", "what did you do", "catch me up", "status", "where are we", or otherwise needs a fast situational summary of in-flight agent work.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.