outfitter-dev/agents
Overview
This skill provides a concise guide and conventions for authoring custom slash commands for Claude Code. It explains file layout, frontmatter schema, argument patterns, bash execution, file references, and validation checklists. Use it to create reproducible, safe, and discoverable project or personal commands. The guidance focuses on practical rules and examples so commands work reliably in team and local contexts.
How this skill works
Commands are single Markdown files placed in a commands directory and invoked explicitly with a slash (e.g., /review or /fix-issue 123). Each command uses YAML frontmatter to declare description, allowed tools, model overrides, and argument hints; content can reference positional arguments ($1, $2), $ARGUMENTS, file inclusions (@path), and preprocessed bash output (!command). After authoring, commands are discovered via /help and validated against naming, frontmatter, and content quality checks.
When to use it
- When you need a reusable, user-invoked prompt or workflow (slash command).
- When automating repo-specific tasks like reviews, commits, or deployments.
- When you want to expose controlled tool access (Bash, Read, Grep) for a command.
- When you need argument parsing or file inclusion in a prompt.
- When bundling shareable commands for a project, plugin, or personal use.
Best practices
- Use concise, action-oriented descriptions under 80 characters for /help discovery.
- Name files in kebab-case without spaces (e.g., fix-issue.md).
- Declare allowed-tools explicitly to limit runtime capabilities and increase safety.
- Prefer positional arguments ($1, $2) or $ARGUMENTS and document argument-hint in frontmatter.
- Test bash snippets in a terminal before embedding; prefix backticks with ! for preprocessing.
- Validate commands with the provided checklist: frontmatter, naming, content, and tool syntax.
Example use cases
- Create /review to check code quality, potential bugs, and security issues for a PR.
- Create /fix-issue <number> to fetch an issue reference, implement a fix, and produce a commit message.
- Create /commit to generate a git commit message from staged changes using Bash context.
- Create deployment commands that run pre-flight checks and optionally skip tests via flags.
- Bundle commands into a plugin folder to distribute common workflows to other projects.
FAQ
Project commands belong in .claude/commands/ (shared via git). Personal commands go in ~/.claude/commands/ and are private to your account.
How do I pass arguments with spaces?
Quote arguments when invoking (e.g., /cmd "arg with spaces"). Use $ARGUMENTS to access the whole argument string.
How do I include shell output in the command context?
Prefix backticks with an exclamation mark like !git status --short to run the command and embed its output.
30 skills
This skill helps you pick the fastest, most suitable CLI tool for a task, with graceful fallback and proactive research when needed.
This skill helps you develop with Bun by showcasing native APIs, SQLite, HTTP servers, and testing patterns for faster, easier Bun projects.
This skill helps you build type-safe Hono APIs with end-to-end typing, OpenAPI, and RPC client integration.
This skill helps you author reusable slash commands for Claude Code, enabling fast creation and management of command files.
This skill provides a concise, multi-source project status report across VCS, PRs, issues, and CI, helping you identify blockers and plan effectively.
This skill helps you learn and apply Outfitter stack patterns across handlers, results, errors, and package conventions for safer, reusable code.
This skill designs multi-skill workflow pipelines with artifact-based state handoff to streamline planning, implementation, and review.
This skill helps you design transport-agnostic stack architectures by detailing inputs, outputs, error taxonomy, and package choices for scalable systems.
This skill scans a codebase to identify Outfitter Stack adoption candidates and generates an audit report with a deployment plan.
This skill helps you discover and evaluate community skills and plugins, assessing safety and quality before use.
This skill helps you diagnose and fix Outfitter stack issues across results, MCP, CLI output, exit codes, and logging.
This skill creates GitHub issues on outfitter-dev/outfitter for problems found using the stack, streamlining bug reports, enhancements, and documentation gaps.
This skill transforms external repositories into Claude Code plugins by guiding discovery, analysis, and packaging into ready-to-use plugins.
This skill helps you configure Claude Code skills with context modes, allowed-tools, and argument hints to tailor isolated or integrated agent execution.
This skill guides you through completing a GitButler virtual branch, ensuring safe snapshots, proper merge flow, and cleanup.
This skill guides architectural decisions and code quality assessments, helping you balance speed, maintainability, and safety through disciplined engineering
This skill helps you write type-safe TypeScript by enforcing strict config, Zod validation, and modern TS features for reliable runtime behavior.
This skill analyzes a codebase to map architecture, extract patterns, and guide evidence-based conclusions with clear confidence tracking.
This skill helps you create, configure, and document Claude agents and subagents, guiding frontmatter, task tool usage, and agent roles.
This skill helps clarify unclear requirements and map paths for complex features through structured questions, options, and guided planning.
This skill guides you in creating standards-aligned skills by following discovery, archetype selection, initialization, customization, and validation.
This skill helps you create and publish Claude Code plugins, guiding initialization, validation, and distribution across marketplaces.
This skill helps you manage long-running tasks and preserve state across context compaction by using persistent Task operations and delegated exploration.
This skill guides end-to-end scenario testing with real dependencies, enabling validation across services without mocks for authentic behavior.
This skill helps you configure Codex CLI profiles, policies, and trust settings with ease across top-level and project scopes.
This skill audits documentation against the current codebase, verifying accuracy, links, and docstring coverage to improve reliability.
This skill helps you configure Claude Desktop and Code by managing MCP servers and project settings with clear file paths and validation.
This skill helps maintain session continuity by managing tasks, preserving intent across compaction, assigning subagents, and coordinating multi-step work with
This skill should be used when capturing reusable workflows from conversations, codifying decision heuristics, or when "patternify", "capture", or "codify workflow" are mentioned.
REDIRECT: Use cli-dev:cli-dev instead. CLI development skills live in the cli-dev plugin.
