Back to Skills

context7-skills

verified

Use when managing Context7 CLI skills with npx ctx7 (search, install, list, remove, info).

View on GitHub

Marketplace

context7-skills

narumiruna/context7-skills-skill

Plugin

context7-skills

Repository

narumiruna/context7-skills-skill
1stars

skills/context7-skills/SKILL.md

Last Verified

January 24, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/narumiruna/context7-skills-skill/blob/main/skills/context7-skills/SKILL.md -a claude-code --skill context7-skills

Installation paths:

Claude
.claude/skills/context7-skills/
Powered by add-skill CLI

Instructions

# Context7 Skills

## Purpose

This skill **must directly execute** Context7 CLI commands for managing skills.

**Printing commands without execution is forbidden.**

## Scope (Authoritative & Closed)

Only the following commands are permitted (per `npx ctx7 skills --help`):

- `npx ctx7 skills search|s`
- `npx ctx7 skills install|i`
- `npx ctx7 skills list|ls`
- `npx ctx7 skills remove|rm`
- `npx ctx7 skills info`

Anything outside this list is **out of scope and prohibited**.

## Execution Rules (Non-Negotiable)

Execution rules apply **only after** required permissions (if any) are granted.

1. Commands **MUST be executed using `npx ctx7`**.
2. The `skills` / `skill` namespace is **mandatory**.
3. Only commands listed in **Scope** may be executed.
4. **Exactly one** target flag may be present **at most**.
5. `install` may include `--all`; no other install options are allowed.
6. Invalid, ambiguous, or incomplete input **MUST be corrected before execution**.
7. **No other shell commands** may be executed under any circumstances.

## Permission Requirements (Hard Gate)

Network-dependent commands (e.g., `search`, `info`, remote `install`) **MUST NOT** be executed unless the execution environment **explicitly grants** outbound network permission.

Requesting environment permission is **not** a user confirmation step and **not** a request for additional user input.

### Permission Flow

If a command is network-dependent:

1. **Request** outbound network permission from the execution environment / agent permission system.
2. If permission is **granted**, execute the command.
3. If permission is **denied or unavailable**, **stop** and report the limitation. Ask the user to run it locally or provide the output.

### No Redundant Confirmation

If the user explicitly requested a network-dependent command and no extra input is needed, proceed to the permission request **immediately** without asking for additional confirmation.

### Network Failures

If execution fails with

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
5954 chars