slash-command-factory
Generate 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.
Install with Tessl CLI
npx tessl i github:alirezarezvani/claude-code-skill-factory --skill slash-command-factory49
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description provides a reasonable overview of the skill's purpose (generating slash commands) but suffers from missing explicit trigger guidance and overly broad domain terms that don't help with skill selection. The lack of a 'Use when...' clause is a significant gap that would make it harder for Claude to know when to select this skill over others.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases like 'create a slash command', 'generate a command', 'make a new Claude Code command', or 'build a custom command'
Replace the broad category list (business research, healthcare compliance, etc.) with specific action verbs describing what the skill does, such as 'guides users through command design', 'validates command syntax', 'generates YAML frontmatter'
Include file extension or naming triggers users might mention, such as '.md command files', 'commands/ directory', or 'slash command workflow'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (slash command generation) and mentions some actions (5-7 question flow, outputs to directory, validation), but the list of use cases (business research, content analysis, etc.) is more of a category dump than concrete actions the skill performs. | 2 / 3 |
Completeness | Describes what it does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance should cap completeness at 2, and this has no trigger guidance at all, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes 'slash commands' and 'Claude Code' which are relevant, but missing natural user phrases like 'create a command', 'make a slash command', 'new command'. The domain-specific terms (healthcare compliance, API integration) are too broad to serve as effective triggers. | 2 / 3 |
Distinctiveness Conflict Risk | 'Slash commands' and 'generated-commands/' directory provide some distinctiveness, but terms like 'workflow optimization', 'documentation automation', and 'content analysis' could easily overlap with other skills handling those domains. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, executable guidance with excellent code examples and clear command patterns. However, it severely violates token efficiency by being extremely verbose (700+ lines) with redundant content and inline details that should be in separate files. The lack of progressive disclosure makes it difficult to navigate and wastes context window space.
Suggestions
Extract the 10 preset command details into a separate PRESETS.md file, keeping only a brief list with one-line descriptions in the main skill
Move the comprehensive naming convention section and bash permission patterns to a separate REFERENCE.md file
Remove redundant sections - validation rules, installation steps, and output structure are repeated multiple times
Add explicit error recovery workflow: 'If validation fails → review specific error → fix issue → re-run validation → only proceed when valid'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 700+ lines with significant redundancy. Repeats naming conventions, validation rules, and installation steps multiple times. Includes extensive preset command details that could be separate files. Many sections explain concepts Claude already knows (what YAML is, basic file operations). | 1 / 3 |
Actionability | Provides fully executable code examples with complete YAML frontmatter, proper command structures, and copy-paste ready templates. The three official patterns (Simple, Multi-Phase, Agent-Style) include concrete, working examples that can be directly used. | 3 / 3 |
Workflow Clarity | The 5-7 question flow is clearly sequenced, and the generation process has numbered steps. However, validation is mentioned but lacks explicit feedback loops for error recovery. The 'If validation fails, you'll get specific fix instructions' is vague rather than showing the actual retry workflow. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with all 10 preset commands fully detailed inline. The preset command details, bash permission patterns, and naming conventions should be in separate reference files. No clear navigation structure - everything is dumped into one massive document. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1007 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.