Agent skill

Plugin Slash Command

by qf-studio in qf-studio/navigator

Generate new Navigator slash commands following project conventions.

MITAuto-check: notesAgent Workflows

Install Plugin Slash Command

skills CLI
$ npx skills add qf-studio/navigator --skill plugin-slash-command -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install qf-studio/navigator plugin-slash-command --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/qf-studio/navigator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/plugin-slash-command .claude/skills/plugin-slash-command && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
plugin-slash-command
GitHub stars
354
Token cost
~3k tokens
SKILL.md length
516 words
Files
6
Skills in repo
32
Repo updated
First seen
Licence
MIT

At a glance

Generate new Navigator slash commands following project conventions.

  • Works in 6 steps: Gather Command Requirements → Analyze Similar Commands → Design Command Structure → …
  • User says add slash command
  • SKILL.md covers When to Invoke, What This Does, Execution Steps and Example Workflows, plus 2 more sections
  • Runs Python scripts from its folder

What it does

Plugin Slash Command is an agent skill from qf-studio/navigator. Generate new Navigator slash commands following project conventions. Use when user says "add slash command", "create command", "new /nav command", or "add /nav:[name] command".

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files (for example `examples/medium-command-example.md`, `examples/simple-command-example.md` and `functions/command_generator.py`).

It sits in Agent Workflows, covering Hooks and plugins. The repository describes itself as: Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of crashing at 7. The licence is MIT.

When your agent uses it

  • User says add slash command
  • New /nav command
  • Add /nav:[name] command

Example prompts

  • “add slash command”
  • “create command”
  • “new /nav command”
  • “/plugin-slash-command”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Glob, Bash

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gather Command Requirements
  2. Analyze Similar Commands
  3. Design Command Structure
  4. Generate Command File
  5. Validate Generated Command
  6. Show Usage Example

What it can do on your machine

Read from SKILL.md and the folder at commit f1cf0eb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Plugin Slash Command loads about 3k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 516 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Grep, Glob, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from qf-studio/navigator at commit f1cf0eb, republished under its MIT licence (© qf-studio). 516 words, ~2,963 tokens.

Download SKILL.mdSave it as .claude/skills/plugin-slash-command/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
plugin-slash-command
description
Generate new Navigator slash commands following project conventions. Use when user says "add slash command", "create command", "new /nav command", or "add /nav:[name] command".
allowed-tools
Read, Write, Edit, Grep, Glob, Bash
version
1.0.0

Navigator Slash Command Generator

Generate new slash commands for the Navigator plugin following established conventions and patterns.

When to Invoke

Auto-invoke when user says:

  • "Add a slash command for..."
  • "Create a new /nav:[name] command"
  • "Generate slash command..."
  • "Add /nav:[feature] command"
  • "New Navigator command for..."

What This Does

  1. Asks for command details (name, purpose, complexity)
  2. Analyzes existing commands for pattern matching
  3. Generates command markdown file with proper structure
  4. Validates YAML frontmatter and formatting
  5. Shows usage example

Execution Steps

Step 1: Gather Command Requirements

Ask user:

  • Command name (kebab-case, without /nav: prefix)
    • Example: "marker", "compact", "update-doc"
  • Command purpose (one sentence description)
    • Example: "Create context markers to save conversation state"
  • Command complexity:
    • Simple: Single action, minimal steps (e.g., marker)
    • Medium: Multiple steps, some logic (e.g., compact)
    • Complex: Multi-phase execution, integrations (e.g., init, start)
  • User-facing or internal?
    • User-facing: Part of standard Navigator workflow
    • Internal: For plugin development/maintenance
Step 2: Analyze Similar Commands

Use Task agent to find similar commands:

"Find existing Navigator commands similar to [purpose]:
 - Commands in commands/*.md
 - Similar complexity level
 - Common structure patterns
 - Return 2-3 best examples"

What to extract from examples:

  • Section structure (What This Does, When to Use, etc.)
  • Tone and style (conversational, 2nd person)
  • Emoji usage patterns
  • Example format
  • Troubleshooting patterns
Step 3: Design Command Structure

Based on complexity level:

Simple commands:

- YAML frontmatter (description)
- Title
- What This Does (2-3 sentences)
- Usage (basic syntax + examples)
- When to Use (2-3 scenarios)
- Expected Output
- Troubleshooting (2-3 common issues)
- Closing statement

Medium commands:

- YAML frontmatter
- Title + overview
- What This Does (detailed explanation)
- When to Use (5-6 scenarios with examples)
- Usage / Execution Steps
- Output Format
- Integration notes (if applicable)
- Troubleshooting (4-5 issues)
- Best Practices
- Closing statement

Complex commands:

- YAML frontmatter
- Title + comprehensive overview
- What This Does (with comparisons)
- Execution Plan (multi-step)
- Pre-flight checks
- Step-by-step implementation
- Validation steps
- Integration with PM tools (if applicable)
- Success criteria
- Troubleshooting (comprehensive)
- Edge cases
- Performance notes
- Closing statement
Step 4: Generate Command File

Use predefined function: functions/command_generator.py

python
# Generates command markdown following Navigator conventions
generate_command(
    name="[command-name]",
    description="[one-line purpose]",
    complexity="simple|medium|complex",
    sections={
        "what_this_does": "...",
        "when_to_use": [...],
        "usage": "...",
        "execution_steps": [...],
        "troubleshooting": [...]
    }
)

File location: commands/[command-name].md

Structure:

  1. YAML frontmatter with description
  2. Title (# Command Name - Navigator Context)
  3. Overview paragraph (what user is doing)
  4. Content sections (based on complexity)
  5. Closing statement (emoji + key takeaway)
Step 5: Validate Generated Command

Use predefined function: functions/command_validator.py

Checks:

  • YAML frontmatter is valid
  • Description field exists and is clear
  • Markdown structure is correct
  • All sections have content
  • Code blocks are properly formatted
  • Examples are realistic
  • Troubleshooting addresses real issues
  • Tone matches Navigator style (conversational, helpful)
  • Emoji usage is consistent with other commands
  • File name matches command name (kebab-case)
Step 6: Show Usage Example

Display:

✅ Slash Command Created: /nav:[command-name]

File: commands/[command-name].md
Lines: [count]
Complexity: [simple/medium/complex]

Try it:
/nav:[command-name]

What it does:
[brief description]

Next steps:
1. Test the command manually
2. Update plugin documentation if public-facing
3. Add to CLAUDE.md command list if needed

Example Workflows

Example 1: Simple Command

User: "Add a slash command for showing Navigator version"

Execution:

  1. Gather requirements:

    Name: version
    Purpose: Display current Navigator plugin version
    Complexity: Simple
    Type: User-facing
  2. Analyze similar (via Task agent):

    Found similar: marker.md (simple, informational)
    Pattern: Short description → Usage → When to use → Output
  3. Design structure:

    - Frontmatter
    - Title: "Navigator Version Info"
    - What This Does: 1 paragraph
    - Usage: Basic syntax
    - When to Use: 2-3 scenarios
    - Output Format: Example
    - Closing statement
  4. Generate: commands/version.md

    markdown
    ---
    description: Display Navigator plugin version and system info
    ---
    
    # Navigator Version Info
    
    Check which version of Navigator you're running.
    
    ## What This Does
    
    Displays the current Navigator plugin version, Claude Code version, and system configuration.
    
    ## Usage
    
    ```bash
    /nav:version

    When to Use

    Reporting issues:

    • Include version info in bug reports
    • Help maintainers reproduce issues

    Checking updates:

    • See if you're on latest version
    • Compare with marketplace version

    System diagnostics:

    • Verify plugin installed correctly
    • Check configuration loaded

    Output Format

    Navigator Plugin
    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
    Version: 2.2.0
    Installed: /Users/you/.claude/plugins/navigator
    Config: .agent/.nav-config.json
    
    System:
    - Claude Code: 1.5.0
    - Project: /Users/you/project
    - Platform: darwin

    Keep your Navigator up to date for latest features 🚀

  5. Validate: ✅ All checks pass

  6. Show usage:

    ✅ Slash Command Created: /nav:version
    
    File: commands/version.md
    Lines: 45
    Complexity: Simple
    
    Try it: /nav:version
Example 2: Medium Command

User: "Create a command for archiving old task documentation"

Execution:

  1. Gather requirements:

    Name: archive-tasks
    Purpose: Move completed tasks to archive directory
    Complexity: Medium (file operations, validation)
    Type: User-facing
  2. Analyze similar:

    Found: markers.md (file management, user selection)
    Found: compact.md (multi-step process)
    Pattern: Overview → Execution Plan → Steps → Validation
  3. Design structure:

    - Frontmatter
    - Title + overview
    - What This Does (comparison with manual approach)
    - When to Use (5 scenarios)
    - Execution Plan (Step 1-4)
    - Output Format
    - Troubleshooting (4 issues)
    - Best Practices
    - Closing
  4. Generate: commands/archive-tasks.md (full content)

  5. Validate: ✅ All checks pass

  6. Show usage: Command ready to use


Output Format

After generating command, show:

✅ Slash Command Created: /nav:[name]

Structure:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📄 commands/[name].md

Sections:
✅ YAML frontmatter
✅ Title and overview
✅ What This Does
✅ When to Use ([N] scenarios)
✅ Usage / Execution Plan
✅ [Additional sections based on complexity]
✅ Troubleshooting
✅ Closing statement
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Command: /nav:[name]
Purpose: [brief description]
Lines: [count]

Test it:
/nav:[name]

Documentation:
- Add to README.md if user-facing
- Update CLAUDE.md command list
- Add to plugin.json if needed

Best Practices

Show full SKILL.md (433 more words)Show less
Command Naming
  • Use kebab-case (marker, update-doc, archive-tasks)
  • Be specific but concise (not too generic, not too verbose)
  • Match feature purpose (nav:compact for compacting)
  • Avoid abbreviations unless very common
Description Writing
  • One sentence, clear purpose
  • Action-oriented ("Create", "Display", "Update")
  • Mention key benefit or what it does
  • Under 100 characters
Content Structure
  • Start with user perspective ("You are...")
  • Use 2nd person ("your task", "you can")
  • Include realistic examples
  • Show expected output
  • Address common issues in troubleshooting
Tone and Style
  • Conversational and helpful
  • Use emojis for visual markers (✅❌📖🚀)
  • Bold key terms and actions
  • Code blocks for all commands/output
  • Bullet lists for readability
Examples Quality
  • Real-world scenarios (not toy examples)
  • Show before/after when relevant
  • Include expected output
  • Cover common use cases
  • Demonstrate Navigator benefits
Troubleshooting Section
  • Address real issues users might encounter
  • Provide specific solutions (not generic advice)
  • Include verification commands
  • Link to related docs if helpful

Common Command Patterns

Informational Commands

Pattern: Simple structure, quick output Examples: version, status, list Sections: Description → Usage → Output

Action Commands

Pattern: Execute something, show result Examples: marker, compact, archive Sections: Description → Execution → Validation → Result

Setup/Configuration Commands

Pattern: Multi-step process, checks Examples: init, migrate, setup Sections: Pre-flight → Steps → Validation → Troubleshooting

Management Commands

Pattern: User selection, operations, feedback Examples: markers (list/load), tasks (list/select) Sections: Overview → Modes → Operations → Results


Troubleshooting

Generated Command Too Short

Problem: Command content is sparse, missing sections

Solutions:

  1. Increase complexity level (simple → medium)
  2. Add more scenarios to "When to Use"
  3. Expand troubleshooting section (more common issues)
  4. Add Best Practices section
  5. Include more examples
Command Doesn't Match Navigator Style

Problem: Tone or structure feels off

Solutions:

  1. Re-analyze example commands (marker.md, compact.md)
  2. Check emoji usage (should match existing patterns)
  3. Verify 2nd person perspective ("You are...")
  4. Ensure conversational tone (not technical manual)
  5. Add personality to closing statement
YAML Validation Fails

Problem: Invalid frontmatter

Solutions:

  1. Check YAML syntax (proper indentation)
  2. Ensure description field exists
  3. Verify no special characters break parsing
  4. Test with: python -c "import yaml; yaml.safe_load(open('commands/[name].md').read().split('---')[1])"
Examples Are Too Generic

Problem: Examples don't feel realistic

Solutions:

  1. Base examples on actual Navigator usage
  2. Use real file paths (not /path/to/file)
  3. Show actual output format (not [output here])
  4. Include context (why user would run this)

Success Criteria

This skill succeeds when:

  • Generated command file is syntactically valid
  • YAML frontmatter passes validation
  • All required sections present
  • Tone matches Navigator style (conversational, helpful)
  • Examples are realistic and useful
  • Troubleshooting addresses real issues
  • Command can be invoked in Claude Code
  • Minimal manual editing needed (<10% of content)

The plugin-slash-command skill automates Navigator command creation, ensuring consistency and saving development time 🔧

© qf-studio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files in skills/plugin-slash-command of qf-studio/navigator.

  • SKILL.md
  • examples/medium-command-example.md
  • examples/simple-command-example.md
  • functions/command_generator.py
  • functions/command_validator.py
  • templates/command-template.md

Open the folder on GitHubat commit f1cf0eb

Compare with similar skills

Plugin Slash Command next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Plugin Slash Command compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plugin Slash Command this skillqf-studio/navigator354—~3kAutomated safety check: NotesMIT
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k11 repos~4.1kAutomated safety check: NotesApache-2.0
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k11 repos~3.5kAutomated safety check: PassMIT
Plugin Settings Patternanthropics/claude-plugins-official38k7 repos~3kAutomated safety check: PassApache-2.0
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 11 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes
  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 11 repos~3.5k tokens
    Agent WorkflowsAuto-check passed
  • Plugin Settings Pattern

    anthropics/claude-plugins-official

    Official

    Shows how Claude Code plugins keep per-project settings and state in .claude/plugin-name.local.md files with YAML frontmatter and a markdown body.

    38k GitHub starsUsed in 7 repos~3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    38k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed

More from qf-studio/navigator

All 32 skills in this repo
  • Backend Endpoint

    qf-studio/navigator

    Create REST/GraphQL API endpoint with validation, error handling, and tests.

    354 GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check: notes
  • Nav Start

    qf-studio/navigator

    Load Navigator documentation navigator when starting development session, resuming work, or beginning new feature.

    354 GitHub stars~4.7k tokensUpdated today
    Auto-check: notes
  • Backend Test

    qf-studio/navigator

    Generate backend tests (unit, integration, mocks) for existing code.

    354 GitHub stars~1.5k tokensUpdated today
    Auto-check: notes
  • Database Migration

    qf-studio/navigator

    Create database migration with schema changes and rollback. An agent skill from qf-studio/navigator.

    354 GitHub stars~3.7k tokensUpdated today
    Auto-check: notes
  • Frontend Component

    qf-studio/navigator

    Create React/Vue component with TypeScript, tests, and styles.

    354 GitHub stars~4.5k tokensUpdated today
    Auto-check: notes
  • Frontend Test

    qf-studio/navigator

    Generate frontend component tests (React Testing Library, Vue Test Utils, snapshot) for existing components.

    354 GitHub stars~1.6k tokensUpdated today
    Auto-check: notes

Categories

Questions about Plugin Slash Command

What does Plugin Slash Command do?

Generate new Navigator slash commands following project conventions. Plugin Slash Command is an agent skill from qf-studio/navigator. Generate new Navigator slash commands following project conventions.

When should I use Plugin Slash Command?

Plugin Slash Command fits situations like: user says add slash command; new /nav command; add /nav:[name] command.

How do I install Plugin Slash Command in Claude Code?

Run `npx skills add qf-studio/navigator --skill plugin-slash-command -a claude-code`. Or copy the skill folder (skills/plugin-slash-command in qf-studio/navigator) into .claude/skills/plugin-slash-command in your project. Claude Code loads it when a task matches its description.

How do I install Plugin Slash Command in Codex?

Run `npx skills add qf-studio/navigator --skill plugin-slash-command -a codex`. Or copy the skill folder (skills/plugin-slash-command in qf-studio/navigator) into .agents/skills/plugin-slash-command in your project. Codex loads it when a task matches its description.

Can I use Plugin Slash Command in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qf-studio/navigator --skill plugin-slash-command -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plugin-slash-command, .gemini/skills/plugin-slash-command, .github/skills/plugin-slash-command and .opencode/skills/plugin-slash-command in your project.

What does Plugin Slash Command need to run?

Going by SKILL.md and its folder, Plugin Slash Command needs Python for the scripts in its folder. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, Bash.

Does Plugin Slash Command access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Plugin Slash Command safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Plugin Slash Command use?

Plugin Slash Command is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plugin Slash Command use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Plugin Slash Command?

Skills that share tags, products or a category with Plugin Slash Command: Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars) and Plugin Settings Pattern (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plugin Slash Command?

qf-studio (a GitHub organization) maintains it in qf-studio/navigator, which has 354 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 7, 2026.

Source: qf-studio/navigator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.