alirezarezvani/claude-code-skill-factory / generated-skills/slash-command-factory
slash-command-factory
VerifiedGenerate custom Claude Code slash commands through intelligent 5-7 question flow. Creates powerful commands for business research, content analysis, healthcare compliance, API integration, documentation automation, and workflow optimization. Outputs organized commands to generated-commands/ with validation and installation guidance.
| File | Kind | Size |
|---|---|---|
| HOW_TO_USE.md | markdown | 4.3 KB |
| SKILL.md | skill md | 23.9 KB |
| command_generator.py | script | 12.3 KB |
| expected_output.json | config | 1.1 KB |
| presets.json | config | 24.5 KB |
| sample_input.json | config | 276 B |
| validator.py | script | 10.9 KB |
HOW_TO_USE.md
View on GitHub# How to Use Slash Command Factory
Generate custom Claude Code slash commands in minutes!
---
## Quick Start
### Use a Preset (30 seconds)
```
@slash-command-factory
Use the /research-business preset
```
→ Instant business research command ready to install
### Create Custom Command (2-3 minutes)
```
@slash-command-factory
Create a command for analyzing customer feedback and generating product insights
```
→ Answers 5-7 questions → Complete custom command generated
---
## 10 Available Presets
1. **/research-business** - Market research, competitor SWOT, strategic insights
2. **/research-content** - Multi-platform trends, SEO strategy, content gaps
3. **/medical-translate** - Medical terms → 8th grade (DE/EN)
4. **/compliance-audit** - HIPAA/GDPR/DSGVO validation
5. **/api-build** - Complete API client with tests
6. **/test-auto** - Auto-generate test suites
7. **/docs-generate** - Documentation automation
8. **/knowledge-mine** - Extract insights from documents
9. **/workflow-analyze** - Process optimization
10. **/batch-agents** - Multi-agent coordination
---
## Official Command Structures
This skill uses **three official patterns** from Anthropic documentation:
### Simple Pattern (code-review)
- **Best for**: Straightforward tasks with clear input/output
- **Structure**: Context → Task
- **Example Presets**: code-review, deps-audit, metrics-report
### Multi-Phase Pattern (codebase-analyze)
- **Best for**: Complex discovery and documentation
- **Structure**: Discovery → Analysis → Task
- **Example Preset**: codebase-analyze
### Agent-Style Pattern (ultrathink)
- **Best for**: Specialized expert roles and coordination
- **Structure**: Role → Process → Guidelines
- **Example Presets**: ultrathink, openapi-sync, batch-agents
**The skill auto-detects** which pattern fits your command purpose!
---
## Naming Convention
All commands follow **kebab-case** (lowercase with hyphens):
**Valid**:
- ✅ `code-review`
- ✅ `api-document`
- ✅ `update-docs`
**Invalid**:
- ❌ `code_review` (underscores)
- ❌ `CodeReview` (CamelCase)
- ❌ `review` (too short)
The skill **automatically converts** your purpose to valid command names!
---
## Installation
**After generation**, commands are in: `generated-commands/[command-name]/`
**To install**:
**Project-level** (this project only):
```bash
cp generated-commands/[command-name]/[command-name].md .claude/commands/
```
**User-level** (all projects):
```bash
cp generated-commands/[command-name]/[command-name].md ~/.claude/commands/
```
**Then**: Restart Claude Code
---
## Usage Examples
### Business Research Command
```
@slash-command-factory
Use /research-business preset
[Command generated: generated-commands/research-business/]
# Install
cp generated-commands/research-business/research-business.md .claude/commands/
# Use
/research-business "Tesla" "EV market"
```
### Custom Healthcare Command
```
@slash-command-factory
Create command for German PTV 10 application generation
Q1: Purpose? Generate PTV 10 therapy applications
Q2: Tools? Read, Write, Task
Q3: Agents? Yes - health-sdk-builder agents
Q4: Output? Files
Q5: Model? Sonnet
[Command generated: generated-commands/generate-ptv10/]
# Install
cp generated-commands/generate-ptv10/generate-ptv10.md .claude/commands/
# Use
/generate-ptv10 "Patient info" "60 sessions"
```
---
## Output Structure
**Simple command**:
```
generated-commands/my-command/
├── my-command.md # The command file
└── README.md # Installation guide
```
**Complex command**:
```
generated-commands/my-command/
├── my-command.md # Command (ROOT)
├── README.md # Install guide (ROOT)
├── TEST_EXAMPLES.md # Testing (ROOT)
├── standards/ # Standards folder
├── examples/ # Examples folder
└── scripts/ # Helper scripts
```
**Organization**: All .md in root, folders separate
---
## Testing Generated Commands
```bash
# After installation
/my-command test-arguments
# Check it works as expected
```
See TEST_EXAMPLES.md in each command folder for specific test cases.
---
## Tips
- Use presets for speed (30 seconds)
- Custom for unique needs (2-3 minutes)
- Always validate before installing
- Test with simple cases first
- Customize .md files if needed
---
**Generate powerful slash commands in minutes!** ⚡
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |