Slash Commands
Create and use Claude Code slash commands with bash execution and file references
What You Can Do
You can create reusable slash commands that execute instantly in Claude Code conversations. Commands support bash execution, file references, arguments, and tool permissions. Use built-in commands like /cost, /review, /memory, and /clear, or define custom project and personal commands stored in .claude/commands/ or ~/.claude/commands/.
Features
`/cost`, `/clear`, `/compact`, `/config`, `/agents`, `/mcp`, `/memory`, `/model`, `/review`, `/resume`, `/help`
Store reusable prompts in `.claude/commands/` for team access and version control
Create user-specific commands in `~/.claude/commands/` for individual workflows
Prefix instructions with `!` to run shell commands and inject output into prompts
Specify which tools (Bash, Read, Write) each command can access via `allowed-tools`
Accept user input with `$1`, `$2`, or `$ARGUMENTS` placeholders and display hints
Define description, tool access, and argument format in command metadata
Embed file content and paths directly in command prompts
Example Output
Example 1: Built-in /cost command
Tokens used in this session: 45,230
Input tokens: 32,100 | Output tokens: 13,130
Estimated cost: $0.87
Example 2: Custom /optimize command output
Performance Analysis:
✓ Identified O(n²) loop in data processing (lines 45-52)
✓ Missing memoization on recursive function
✓ Suggests caching layer for repeated queries
Recommended fix: Implement request deduplication
Example 3: Bash-enabled /git-status command
Current branch: feature/auth-improvements
Staged changes: 3 files modified
Recent commits:
a1b2c3d Fix login validation
d4e5f6g Add password reset flow
g7h8i9j Initial auth module
Suggestion: Create PR for feature/auth-improvements
What's Included
- SKILL.md: Complete slash command reference with syntax, built-in command list, and format specifications
- Command templates: Ready-to-use project and personal command examples (code review, git helpers, optimization)
- YAML format guide: Metadata structure for descriptions, tool permissions, and argument handling
- Bash execution patterns: Examples using `!` prefix to inject shell output into prompts
- Directory setup instructions: Quick commands to create `.claude/commands/` and `~/.claude/commands/` directories
Who It's For
- Full-stack engineers — Create commands for git workflows, environment setup, and code review processes
- DevOps and platform engineers — Build commands for deployment checks, infrastructure queries, and health monitoring
- Data scientists and analysts — Define commands for data validation, notebook execution, and analysis workflows
- Technical team leads — Set up shared project commands for consistent code review, testing, and documentation practices
- Automation specialists — Create bash-enabled commands that combine file operations, queries, and intelligent prompts
Best For
- Automating repetitive development workflows (code reviews, testing, formatting)
- Integrating bash scripts and system queries into AI prompts
- Creating team-wide or personal command shortcuts for complex multi-step processes
- Injecting real-time system output (git status, logs, metrics) into Claude's context
- Defining role-based commands with specific tool access and permission controls
You might also like
This skill maps construction claims as interdependent probability states rather than isolated analyses, allowing you to evaluate how changes in one contractual interpretation cascade through damages calculations, delay causation, and liability allocation. You can simultaneously model competing scenarios—concurrent causation, ambiguous change order triggers, insurance coverage dependencies—and identify which settlement positions minimize exposure across all correlated outcomes, not just single interpretations.
by parcadei
You can formally verify mathematical proofs by translating theorems into Lean 4 code, leveraging Mathlib's extensive library of formalized mathematics. The skill guides you through researching existing lemmas, designing proof strategies, testing approaches, implementing formal proofs, and verifying correctness—turning informal mathematical claims into machine-checked theorems without requiring deep Lean syntax expertise.
by parcadei
You'll follow the strict TDD workflow: write a failing test that defines expected behavior, verify it fails, write minimal production code to pass the test, then refactor for quality. This approach ensures complete test coverage, catches bugs early, and produces well-designed code backed by comprehensive test suites. Claude guides you through each phase with examples and enforces TDD principles to prevent shortcuts.
by parcadei
You can rapidly process multiple subcontractor bid responses—from trade contractors, material suppliers, and specialty vendors—into a cohesive, auditable estimate structure. Claude extracts key bid components, identifies pricing inconsistencies against benchmarks or prior projects, flags scope gaps and exclusions, and organizes everything by CSI division for seamless estimate assembly. This eliminates manual spreadsheet comparison and reduces the risk of overlooked scope omissions or pricing anomalies when managing 15+ concurrent bids.
by parcadei
You can create, list, enable, disable, and run markdown-based AI automation pipes that execute on schedules ranging from every 30 minutes to custom cron expressions. Manage service connections to Telegram, Slack, Discord, and other platforms directly from the CLI, and troubleshoot pipe execution with built-in logging and debugging commands.
by screenpipe
You can deploy this agent to execute specific implementation tasks within a larger development plan. It operates independently with fresh context, follows test-driven development principles for every code change, and creates comprehensive handoff documentation that captures progress, decisions, and learnings for the next task executor. This ensures consistent code quality, prevents rework, and maintains continuity across distributed implementation efforts.
by parcadei
Feed your logs, metrics, and traces into Claude to automatically detect anomalies, correlate alerts, and identify root causes in distributed systems. This skill generates step-by-step remediation procedures, prioritizes incidents by severity, and creates incident reports—compressing hours of manual triage into minutes.
You can systematically analyze construction estimates by breaking down components, validating labor and material pricing against market data, identifying embedded errors or outdated assumptions, and applying data-driven contingency allocation. Claude helps you produce risk-adjusted cost projections that are defensible to stakeholders and competitive in bid scenarios, reducing estimate variance and catching pricing gaps before client submission.
by parcadei