Command Reference
Complete documentation for all 16 slash commands. Commands automate complex multi-step workflows by orchestrating multiple agents, tools, and processes.
Workflow Commands (4)
Core workflow commands that embody the Plan-Delegate-Assess-Codify philosophy.
/workflows:plan
Transform feature descriptions into well-structured project plans following conventions.
Arguments
[feature description, bug report, or improvement idea]
Workflow
- Repository Research (Parallel) - Launch 3 agents simultaneously:
repo-research-analyst- Project patternsbest-practices-researcher- Industry standardsframework-docs-researcher- Framework documentation
- SpecFlow Analysis - Run
spec-flow-analyzerfor user flows - Choose Detail Level:
- MINIMAL - Simple bugs/small improvements
- MORE - Standard features
- A LOT - Major features with phases
- Write Plan - Save as
plans/<issue_title>.md - Review - Call
/plan_reviewfor multi-agent feedback
This command does NOT write code. It only researches and creates the plan.
/workflows:plan Add OAuth integration for third-party auth
/workflows:plan Fix N+1 query in user dashboard
/workflows:review
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees.
Arguments
[PR number, GitHub URL, branch name, or "latest"]
Workflow
- Setup - Detect review target, optionally use git-worktree for isolation
- Launch 12 Parallel Review Agents:
kieran-rails-reviewer,dhh-rails-reviewersecurity-sentinel,performance-oraclearchitecture-strategist,data-integrity-guardianpattern-recognition-specialist,git-history-analyzer- And more...
- Ultra-Thinking Analysis - Stakeholder perspectives, scenario exploration
- Simplification Review - Run
code-simplicity-reviewer - Synthesize Findings - Categorize by severity (P1/P2/P3)
- Create Todo Files - Using file-todos skill for all findings
P1 (Critical) findings BLOCK MERGE. Address these before merging.
/workflows:review 42
/workflows:review https://github.com/owner/repo/pull/42
/workflows:review feature-branch-name
/workflows:review latest
/workflows:work
Execute work plans efficiently while maintaining quality and finishing features.
Arguments
[plan file, specification, or todo file path]
Phases
- Quick Start
- Read plan & clarify requirements
- Setup environment (live or worktree)
- Create TodoWrite task list
- Execute
- Task execution loop with progress tracking
- Follow existing patterns
- Test continuously
- Figma sync if applicable
- Quality Check
- Run test suite
- Run linting
- Optional reviewer agents for complex changes
- Ship It
- Create commit with conventional format
- Create pull request
- Notify with summary
/workflows:work plans/user-authentication.md
/workflows:work todos/042-ready-p1-performance-issue.md
/workflows:codify
Document a recently solved problem for the knowledge base.
Arguments
[optional: brief context about the fix]
Workflow
- Preconditions - Verify problem is solved and verified working
- Launch 7 Parallel Subagents:
- Context Analyzer - Extract YAML frontmatter skeleton
- Solution Extractor - Identify root cause and solution
- Related Docs Finder - Find cross-references
- Prevention Strategist - Develop prevention strategies
- Category Classifier - Determine docs category
- Documentation Writer - Create the file
- Optional Specialized Agent - Based on problem type
- Create Documentation - File in
docs/solutions/[category]/
Auto-Triggers
Phrases: "that worked", "it's fixed", "working now", "problem solved"
/workflows:codify
/workflows:codify N+1 query optimization
Utility Commands (12)
Specialized commands for specific tasks like changelog generation, bug reporting, and parallel resolution.
/changelog
Create engaging changelogs for recent merges to main branch.
Arguments
[optional: daily|weekly, or time period in days]
Output Sections
- Breaking Changes (top priority)
- New Features
- Bug Fixes
- Other Improvements
- Shoutouts
- Fun Fact
/changelog daily
/changelog weekly
/changelog 7
/create-agent-skill
Create or edit Claude Code skills with expert guidance on structure and best practices.
Arguments
[skill description or requirements]
/create-agent-skill PDF processing for document analysis
/create-agent-skill Web scraping with error handling
/generate_command
Create a new custom slash command following conventions and best practices.
Arguments
[command purpose and requirements]
/generate_command Security audit for codebase
/generate_command Automated performance testing
/heal-skill
Heal skill documentation by applying corrections discovered during execution.
Arguments
[optional: specific issue to fix]
Approval Options
- Apply and commit
- Apply without commit
- Revise changes
- Cancel
/heal-skill API endpoint URL changed
/heal-skill parameter validation error
/plan_review
Have multiple specialized agents review a plan in parallel.
Arguments
[plan file path or plan content]
Review Agents
dhh-rails-reviewer- Rails conventionskieran-rails-reviewer- Rails best practicescode-simplicity-reviewer- Simplicity and clarity
/plan_review plans/user-authentication.md
/report-bug
Report a bug in the compounding-engineering plugin.
Arguments
[optional: brief description of the bug]
Information Collected
- Bug category (Agent/Command/Skill/MCP/Installation)
- Specific component name
- Actual vs expected behavior
- Steps to reproduce
- Error messages
- Environment info (auto-gathered)
/report-bug Agent not working
/report-bug Command failing with timeout
/reproduce-bug
Reproduce and investigate a bug using logs and console inspection.
Arguments
[GitHub issue number]
Investigation Process
- Read GitHub issue details
- Launch parallel investigation agents
- Analyze code for failure points
- Iterate until root cause found
- Post findings to GitHub issue
/reproduce-bug 142
/triage
Triage and categorize findings for the CLI todo system.
Arguments
[findings list or source type]
User Decisions
- "yes" - Create/update todo file, change status to ready
- "next" - Skip and delete from todos
- "custom" - Modify and re-present
This command does NOT write code. It only categorizes and creates todo files.
/triage code-review-findings.txt
/triage security-audit-results
/resolve_parallel
Resolve all TODO comments using parallel processing.
Arguments
[optional: specific TODO pattern or file]
Process
- Analyze TODO comments from codebase
- Create dependency graph (mermaid diagram)
- Spawn parallel
pr-comment-resolveragents - Commit and push after completion
/resolve_parallel
/resolve_parallel authentication
/resolve_parallel src/auth/
/resolve_pr_parallel
Resolve all PR comments using parallel processing.
Arguments
[optional: PR number or current PR]
Process
- Get all unresolved PR comments
- Create TodoWrite list
- Launch parallel
pr-comment-resolveragents - Commit, resolve threads, and push
/resolve_pr_parallel
/resolve_pr_parallel 123
/resolve_todo_parallel
Resolve all pending CLI todos using parallel processing.
Arguments
[optional: specific todo ID or pattern]
Process
- Get unresolved TODOs from
/todos/*.md - Analyze dependencies
- Spawn parallel agents
- Commit, mark as resolved, push
/resolve_todo_parallel
/resolve_todo_parallel 042
/resolve_todo_parallel p1
/prime
Prime/setup command for project initialization.
/prime