By dwmkerr
Develop Claude Code agents, skills, plugins, hooks, slash commands, and status lines; coordinate multi-agent teams for parallel tasks; conduct autonomous technical research via web/GitHub analysis; automate GitHub PRs, Makefiles, shell scripts, and release-please configs; introspect agent/skill histories and session friction for improvements.
This skill should be used when the user asks to "create an agent", "write an agent", "build an agent", or wants to add new agent capabilities to Claude Code.
This skill should be used when the user asks to "create evals", "evaluate an agent", "build evaluation suite", or mentions agent testing, graders, or benchmarks. Also suggest when building coding agents, conversational agents, or research agents that need quality assurance.
This skill should be used when the user asks to "create an agent team", "run a multi-agent team", "coordinate multiple Claude sessions", "use agent teams", or wants to parallelize work across multiple Claude Code instances.
This skill should be used when the user asks to "create a hook", "add a hook", "write a hook", or mentions Claude Code hooks. Also suggest this skill when the user asks to "automatically do X" or "run X before/after Y" as these are good candidates for hooks.
This skill should be used when the user asks to "set up memory", "configure CLAUDE.md", "add rules", "create project rules", "organize instructions", or mentions Claude Code memory, CLAUDE.md files, .claude/rules, rules, or project instructions. Also use when the user wants to persist preferences, add coding conventions, scope instructions to specific files, or understand when to use rules vs hooks or other memory mechanisms.
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
General purpose Claude Code toolkit plugin for skill/hook/agent development, research, skill analysis, Github quality of life and more.
Add the marketplace and install:
/plugin marketplace add dwmkerr/claude-toolkit
/plugin install toolkit@claude-toolkit
If commands don't appear, enable and restart:
/plugin enable toolkit@claude-toolkit
# Or bust the cache in a terminal if stuff's still not loading...
# rm -rf ~/.claude/plugins/cache
toolkit Plugin
researchclaude-code-memory-and-rulesclaude-code-hook-developmentclaude-code-skill-developmentagent-developmentclaude-code-slash-commandsclaude-code-statusline-developmentanthropic-evaluationsshell-script-developmentmakefile-developmentrelease-please-developmentclaude-code-plugin-developmentlearn-and-improveclaude-code-agent-teamsdwmkerr Plugin
toolkit PluginThis plugin is general purpose and should be useful for anyone.
/toolkit:skill-historyThis is useful for troubleshooting whether Claude has actually invoked or missed skills, and in response to what queries.

/toolkit:agent-historyWhat agents have been spawned?
/toolkit:ghprOpen or create a pull request for my current branch
feat/, fix/, chore/, etc.)Example, when no PR exists:

And when it does. The browser opens automatically:

researchUse the research skill to investigate options for implementing OAuth in a Node.js app
./scratch/research/Tip: "research" is a generic term — Claude may use built-in tools (Explore, WebFetch) instead of this skill. Be explicit: say "use the research skill" or "use the researcher agent" to ensure the structured research workflow is triggered.
claude-code-memory-and-rulesSet up CLAUDE.md and rules for my project
.claude/rules/, and auto memory/init, and the /memory commandclaude-code-hook-developmentCreate a hook that runs tests before git push and requires explicit confirmation before pushing to remote.
.claude/hooks/.claude/settings.jsonExample output

See github.com/dwmkerr/effective-shell for some real-world examples (or most of my recently edited open source projects).
claude-code-skill-developmentnpx claudepluginhub dwmkerr/claude-toolkit --plugin toolkitStructured protocols for feature exploration and development workflows
Personal Claude Code plugin for dwmkerr with repo management and custom workflows
Teaches Claude Code how to work with git-workforest managed repositories
Tools for PDF conversion and document processing
Personal Claude Code plugin for dwmkerr with repo management and custom workflows
Claude Code settings and skills for spec-driven development workflows
Coding workflow skills: intelligent commits, push & PR, branch cleanup, CLAUDE.md maintenance, README generation, changelog creation, README updating, and GitHub Actions setup
Harness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
Commands for Git operations, commits, and PRs
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns