Central authority for Claude Code slash commands. Covers built-in commands, custom slash commands (project and personal), plugin commands, MCP slash commands, SlashCommand tool, frontmatter configuration, arguments ($ARGUMENTS, $1, $2), bash execution, file references, namespacing, and skills vs slash commands comparison. Assists with creating custom commands, configuring command behavior, understanding command types, and troubleshooting command issues. Delegates 100% to docs-management skill for official documentation.
Limited to specific tools
Additional assets for this skill
This skill is limited to using the following tools:
references/validation-checklist.md🚨 MANDATORY: Invoke docs-management First
STOP - Before providing ANY response about slash commands:
- INVOKE
docs-managementskill- QUERY for the user's specific topic
- BASE all responses EXCLUSIVELY on official documentation loaded
Skipping this step results in outdated or incorrect information.
Verification Checkpoint
Before responding, verify:
- Did I invoke docs-management skill?
- Did official documentation load?
- Is my response based EXCLUSIVELY on official docs?
If ANY checkbox is unchecked, STOP and invoke docs-management first.
Central authority for Claude Code slash commands. This skill uses 100% delegation to docs-management - it contains NO duplicated official documentation.
Architecture: Pure delegation with keyword registry. All official documentation is accessed via docs-management skill queries.
Keywords: slash commands, custom commands, built-in commands, project commands, personal commands, plugin commands, MCP commands, SlashCommand tool, command frontmatter, allowed-tools, argument-hint, $ARGUMENTS, bash execution, file references, namespacing, skills vs commands
Use this skill when:
Use these keywords when querying docs-management skill for official documentation:
| Topic | Keywords |
|---|---|
| Overview | "slash commands", "command overview" |
| Built-in Commands | "built-in slash commands", "built-in commands table" |
| Custom Commands | "custom slash commands", "command creation" |
| Topic | Keywords |
|---|---|
| Project Commands | "project commands", ".claude/commands" |
| Personal Commands | "personal commands", "~/.claude/commands" |
| Plugin Commands | "plugin commands", "plugin slash commands" |
| MCP Commands | "MCP slash commands", "mcp__server__prompt" |
| MCP Permissions | "MCP permissions wildcards", "mcp__servername", "approve all tools" |
| Topic | Keywords |
|---|---|
| Frontmatter | "command frontmatter", "allowed-tools", "argument-hint", "description" |
| Model Selection | "command model", "model frontmatter" |
| Tool Restrictions | "allowed-tools commands", "command permissions" |
| Topic | Keywords |
|---|---|
| Arguments | "$ARGUMENTS", "command arguments", "$1 $2 positional" |
| Bash Execution | "bash command execution", "! prefix commands" |
| File References | "file references commands", "@ prefix files" |
| Namespacing | "command namespacing", "subdirectory commands" |
| Thinking Mode | "thinking mode commands", "extended thinking slash" |
| Topic | Keywords |
|---|---|
| Tool Overview | "SlashCommand tool", "programmatic command execution" |
| Permissions | "SlashCommand permission rules", "disable SlashCommand" |
| Character Budget | "character budget limit", "SLASH_COMMAND_TOOL_CHAR_BUDGET", "15000 characters" |
| Disable Commands | "disable-model-invocation", "disable specific commands" |
| Topic | Keywords |
|---|---|
| Skills vs Commands | "skills vs slash commands", "when to use commands vs skills" |
What do you want to do?
User asks: "How do I create a custom command?"
1. Invoke docs-management skill
2. Use keywords: "custom slash commands", "command creation"
3. Load official documentation
4. Provide guidance based EXCLUSIVELY on official docs
User asks: "I want a command that runs git status and uses arguments"
1. Invoke docs-management skill with multiple queries:
- "bash command execution", "! prefix commands"
- "$ARGUMENTS", "command arguments"
- "allowed-tools commands"
2. Synthesize guidance from official documentation
User asks: "Should I use a skill or slash command for code review?"
1. Invoke docs-management skill
2. Use keywords: "skills vs slash commands", "when to use commands vs skills"
3. Guide user through decision criteria from official docs
| Issue | Keywords for docs-management |
|---|---|
| Command not found | "custom slash commands", ".claude/commands" |
| Arguments not working | "$ARGUMENTS", "positional arguments" |
| Bash not executing | "bash command execution", "allowed-tools" |
| Files not included | "file references commands", "@ prefix" |
| SlashCommand not invoking | "SlashCommand tool", "disable-model-invocation" |
| Namespace conflicts | "command namespacing", "conflict resolution" |
| MCP command missing | "MCP slash commands", "dynamic discovery" |
| MCP permission denied | "MCP permissions wildcards", "mcp__servername" |
This plugin provides slash commands in plugins/claude-ecosystem/commands/:
/claude-ecosystem:scrape-docs - Scrape Claude documentation from official sources/claude-ecosystem:refresh-docs - Refresh local index without network scraping/claude-ecosystem:validate-docs - Validate index integrity and detect driftDiscovery:
/help to see all available commands (built-in + plugin)claude-ecosystem: prefix (when no conflicts)Claude Code's built-in commands use these patterns:
| Pattern | Use Case | Examples |
|---|---|---|
| Verb-noun kebab-case | Action commands | /add-dir, /release-notes, /security-review |
| Single noun | State/display commands | /status, /permissions, /config, /cost |
| Single verb | Simple actions | /clear, /exit, /login, /resume |
Key insight: Built-in commands do NOT use dot-namespacing or noun-first grouping.
For action commands (scrape, refresh, validate, create, etc.):
Use verb-noun kebab-case: /scrape-docs, /refresh-docs, /validate-docs
For display/status commands (built-in examples):
Use single noun: /status, /config, /todos
For simple utilities (built-in examples):
Use single verb or short descriptive name: /clear, /compact, /review
Plugin commands get automatic namespacing via /plugin-name:command:
/claude-ecosystem:scrape-docs (fully qualified)/scrape-docs (short form when no conflicts)This means you don't need to embed the domain in the command name—the plugin prefix handles disambiguation.
Command files use the exact command name with .md extension:
/scrape-docs -> commands/scrape-docs.md/refresh-docs -> commands/refresh-docs.md/validate-docs -> commands/validate-docs.mdThis skill provides the validation criteria used by the command-auditor agent for formal audits.
| Resource | Location | Purpose |
|---|---|---|
| Validation Checklist | references/validation-checklist.md | Pre-creation verification checklist |
| Scoring Rubric | references/validation-checklist.md#audit-scoring-rubric | Formal audit scoring criteria |
| Category | Points | Key Criteria |
|---|---|---|
| File Structure | 20 | Correct location, .md extension, kebab-case naming |
| YAML Frontmatter | 25 | Description, allowed-tools, argument-hint present |
| Description Quality | 20 | Clear, concise, action-oriented, when-to-use guidance |
| Tool Configuration | 15 | Not over/under restricted for purpose |
| Content Quality | 20 | Well-structured, proper argument handling, file references |
Thresholds: 85+ = PASS, 70-84 = PASS WITH WARNINGS, <70 = FAIL
The command-auditor agent (Haiku model) performs formal audits using this skill:
skills: command-development/audit-commands commandOfficial Documentation (via docs-management skill):
This Plugin:
plugins/claude-ecosystem/commands/plugins/claude-ecosystem/skills/Date: 2025-11-30 Model: claude-opus-4-5-20251101