From qe-framework
Guides creation of Claude Code slash commands to automate repetitive workflows. Activates when user requests to create or add a command, or wants to turn a recurring task into a reusable prompt.
How this skill is triggered — by the user, by Claude, or both
Slash command
/qe-framework:Qcommand-creatorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill guides the creation of Claude Code slash commands. Slash commands are reusable workflows callable as `/command-name` within a Claude Code conversation.
This skill guides the creation of Claude Code slash commands. Slash commands are reusable workflows callable as /command-name within a Claude Code conversation.
Slash commands are markdown files stored in .claude/commands/ (project level) or ~/.claude/commands/ (global/user level) that expand into prompts when invoked. They are suitable for:
Every slash command is a markdown file with the following structure:
---
description: Brief description shown in /help (required)
argument-hint: <placeholder> (optional, if the command accepts arguments)
---
# Command Title
[Detailed instructions for the agent to execute autonomously]
Automatically detect the appropriate location:
git rev-parse --is-inside-work-tree 2>/dev/null.claude/commands/~/.claude/commands/~/.claude/commands/.claude/commands/Inform the user of the chosen location before proceeding.
Load references/patterns.md to review available patterns:
Ask the user: "Which pattern is closest to what you have in mind?"
Guidelines:
submit-stack, ensure-cisubmit_stack, ensure_cimy-command.md → invoked as /my-command<angle-brackets>, optional arguments: [square-brackets]Reference references/best-practices.md to create the command file with agent-optimized instructions.
Core principles:
mkdir -p [directory path]/command-name [arguments] to test it"Common patterns to remember:
pytest, pyright, ruff, prettier, make, etc.npx claudepluginhub inho-team/qe-framework --plugin qe-frameworkCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.