Agent skill · Security

scope-check

Use when determining which repositories or files a task affects. Distinguishes between target repos (where changes happen) and reference repos (for learning patterns). Supports both standard mode returning { targets, references } and audit mode detecting specific config files to audit. Returns structured scope object.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill scope-check --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 12 KB
Bundled scripts: none
Path: skills/analysis/scope-check/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Scope Check Skill **Purpose:** Analyze a prompt and return target repositories + reference repositories, or audit-specific files and repos. **Input:** `prompt` (string) - The user's request; `mode` (string, optional) - "default" or "audit" **Output:** - Default mode: `{ targets: string[], references: string[] }` - Structured object with repo paths - Audit mode: `{ repos: string[], files: string[] }` - Repos to audit and specific files to check --- ## How to Execute This is a TEXT ANALYSIS task - analyze the prompt text as your sole input: ### Default Mode (targets & references) 1. Scan the prompt for **reference indicators** (repos mentioned for pattern learning) 2. Scan the prompt for **target indicators** (repos where changes should happen) 3. Apply default: CWD is target if no explicit target mentioned 4. Return: `scope: { targets: [...], references: [...] }` 5. Complete in under 200 tokens **Expected output format:** ``` scope: { targets: ["{CODE_ROOT}/metasaver-com"], references: ["{CODE_ROOT}/rugby-crm"] } ``` ### Audit Mode (repos & files) 1. Detect repo targets using Step 2 rules (repositories to audit) 2. Detect specific files using Step 2A rules (config files to check)

What's inside
Steps it walks through
  1. How to Execute
  2. Default Mode (targets & references)
  3. Audit Mode (repos & files)
  4. Step 1: Detect Reference Repositories
  5. Step 2: Detect Target Repositories
  6. Step 2A: Detect Audit Files (Audit Mode Only)
  7. Step 3: Known Repositories Reference
  8. Step 4: Handle Special Cases
  9. Examples
  10. Example 1: Clear reference vs target
  11. Example 2: No repo mentioned (use CWD)
  12. Example 3: Only reference mentioned
  13. Example 4: Multiple targets
  14. Example 5: Target implicit from context
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the scope-check skill do?

Use when determining which repositories or files a task affects. Distinguishes between target repos (where changes happen) and reference repos (for learning patterns). Supports both standard mode returning { targets, references } and audit mode detecting specific config files to audit. Returns structured scope object.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill scope-check --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going