slash-command-creator
Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, update an existing slash command, or asks about syntax and options.
What this skill does
# Slash Command Creator
Create custom slash commands for Claude Code
to automate frequently-used prompts.
## Quick Start
Initialize a new command:
```bash
./run.sh scripts/init_command.py <command-name> [--scope project|personal]
# Namespaced command (creates frontend/build.md)
./run.sh scripts/init_command.py frontend/build --scope project
```
## Command Structure
Slash commands are Markdown files with optional YAML frontmatter:
```markdown
---
description: Brief description shown in /help
---
Your prompt instructions here.
$ARGUMENTS
```
### File Locations
| Scope | Path | Shown as |
|----------|---------------------- |-----------|
| Project | `.claude/commands/` | (project) |
| Personal | `~/.claude/commands/` | (user) |
### Namespacing
Organize commands in subdirectories:
- `.claude/commands/frontend/component.md` → `/component` shows "(project:frontend)"
- `~/.claude/commands/backend/api.md` → `/api` shows "(user:backend)"
## Features
### Arguments
**All arguments** - `$ARGUMENTS`:
```markdown
Fix issue #$ARGUMENTS following our coding standards
# /fix-issue 123 → "Fix issue #123 following..."
```
**Positional** - `$1`, `$2`, etc.:
```markdown
Review PR #$1 with priority $2
# /review 456 high → "Review PR #456 with priority high"
```
### Bash Execution
Execute shell commands inline using the exclamation mark prefix.
The allowed-tools field is required in frontmatter:
```markdown
---
allowed-tools: Bash(git status:*), Bash(git diff:*)
---
Current status: !`git status`
Changes: !`git diff HEAD`
```
**Tip (Boris Cherny)**: Inline Bash pre-computes context,
reducing round-trips with Claude:
```markdown
# Current branch
!`git branch --show-current`
# Changed files
!`git diff --name-only`
# Based on above, create a PR with...
```
This pattern is especially powerful for `/commit-push-pr` style commands
where context changes frequently.
### File References
Include file contents with `@` prefix:
```markdown
Review @src/utils/helpers.js for issues.
Compare @$1 with @$2.
```
## Frontmatter Options
| Field | Purpose | Required |
| -------------------------- | ------------------------------- | -------- |
| `description` | Brief description for /help | Yes |
| `allowed-tools` | Tools the command can use | No |
| `argument-hint` | Expected arguments hint | No |
| `model` | Specific model to use | No |
| `disable-model-invocation` | Prevent Skill tool invocation | No |
| `hooks` | Hooks for command execution | No |
See [references/frontmatter.md](references/frontmatter.md) for detailed reference.
### Hooks in Commands
Define hooks that run during command execution:
```yaml
---
description: Deploy to staging with validation
hooks:
PreToolUse:
- matcher: "Bash"
hooks:
- type: command
command: "./scripts/validate-deploy.sh"
---
```
## Examples
See [references/examples.md](references/examples.md) for complete examples:
- Simple review/explain commands
- Commands with positional arguments
- Git workflow commands with bash execution
- Namespaced commands for frontend/backend
## Creation Workflow
1. **Identify the use case**: What prompt do you repeat often?
2. **Choose scope**: Project (shared) or personal (private)?
3. **Initialize**: Run `./run.sh scripts/init_command.py <name>`
4. **Edit**: Update description and body
5. **Test**: Run the command in Claude Code
## Triggers
This skill activates when users want to:
- Create a new slash command for Claude Code
- Update or modify an existing slash command
- Learn about slash command syntax or frontmatter options
- Understand best practices for command design
- Organize commands with namespacing
## Extension Points
1. **init_command.py customization**: Modify the template generation script
to match organizational standards or add custom frontmatter fields
2. **Frontmatter schema**: Add custom frontmatter fields for organization
metadata (e.g., `owner`, `category`, `version`)
3. **Command templates**: Create reusable command templates in `assets/`
for common patterns (review, deploy, test workflows)
## Anti-Patterns
Avoid these common mistakes when creating slash commands:
- **Overly complex commands**: Commands should do one thing well;
split complex workflows into multiple commands
- **Missing descriptions**: Always include a description for discoverability
- **Hardcoded paths**: Use arguments ($1, $2) instead of hardcoding file paths
- **Excessive bash execution**: Prefer Claude's tools over shell commands
- **No argument hints**: For commands with arguments, include `argument-hint`
## Design Rationale
**Why Markdown format?** Markdown is readable, versionable, and familiar.
YAML frontmatter provides structured metadata without sacrificing readability.
**Why separate project/personal scopes?** Project commands are shared via VCS.
Personal commands are private and portable across projects.
**Why namespacing?** Subdirectories prevent naming conflicts and organize
commands by domain, making large command libraries manageable.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.