Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By jugrajsingh
Parallel sub-agent research with persistent reports, evidence-backed analysis, and generic dispatch
npx claudepluginhub jugrajsingh/skillgarden --plugin researcherUnderstand HOW code works — pattern descriptions, data flow, architectural notes with file:line citations
Find WHERE code lives for a research question — file paths grouped by purpose
Dispatch parallel agents for independent problems, verify independence, merge results, and flag conflicts
Find similar implementations to model after — code snippets with context, multiple variations
Decompose a research question into sub-questions, dispatch locator/analyzer/pattern-finder agents in parallel, synthesize findings into a persistent report
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
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.
No description provided.
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Core workflow for structured development: Research → Plan → Implement → Validate with thoughts/ management
General purpose Claude Code toolkit with research agents, skills, and introspection commands
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Codebase cleanup and hygiene — dead code detection, duplication scan, staleness check, safe removal with archiving
CLAUDE.md lifecycle management - init, audit, sync, and optimize project context files
Python project scaffolding, configuration management, and best practices auditing with uv-native tooling
Git workflow validation - enforces explicit file staging, conventional commits, and blocks AI footers
Makefile generation for local development, deployment, and root orchestration with audit capabilities
A plugin marketplace for Claude Code that brings developer best practices as composable plugins. Install what you need, they work together seamlessly.
Git workflow validation with enforcement. Explicit file staging, conventional commits, no AI footers.
What it enforces:
git add . → Blocked. List files explicitly.git commit -m "fixed stuff" → Blocked. Use type(scope): subjectCommands:
| Command | Description |
|---|---|
/gitmastery:commit | Atomic commits with conventional format |
/gitmastery:feature | Start a feature branch |
/gitmastery:finish | Complete current branch |
/gitmastery:release | Create versioned release |
/gitmastery:changelog | Generate Keep a Changelog format |
/gitmastery:init | Initialize git-flow |
CLAUDE.md lifecycle management. Generate, audit, sync, and optimize hierarchical context files throughout a repository.
Commands:
| Command | Description |
|---|---|
/claudemd:init | Generate root + module-level CLAUDE.md files |
/claudemd:audit | Health check all context files for anti-patterns and staleness |
/claudemd:sync | Detect and fix drift between docs and codebase |
/claudemd:optimize | Reduce context cost while preserving signal |
Structured error escalation protocol. 3-strike workflow when stuck on a problem: diagnose, pivot, escalate.
Commands:
| Command | Description |
|---|---|
/unstuck | Start the escalation protocol |
Design brainstorming, implementation planning with 3-file persistence, session recovery, and worktree isolation. Drives the front of the development workflow.
Commands:
| Command | Description |
|---|---|
/planner:brainstorm | Explore design ideas through guided dialogue |
/planner:plan | Create implementation plan with task decomposition and batching |
/planner:resume | Recover session state via 5-Question Reboot Test |
/planner:handoff | Generate session transfer document |
/planner:worktree | Set up git worktree isolation for a branch |
Persistence: Creates docs/plans/{slug}-task_plan.md, findings.md, and progress.md for cross-session project memory.
Parallel sub-agent research with persistent reports. Dispatches locator, analyzer, and pattern-finder agents for evidence-backed codebase analysis.
Commands:
| Command | Description |
|---|---|
/researcher:research | Research a codebase question with parallel sub-agents |
/researcher:dispatch | Dispatch parallel agents for independent problems |
Agents: locator (haiku, fast file finding), analyzer (sonnet, data flow tracing), pattern-finder (sonnet, existing pattern discovery).
Codebase cleanup and hygiene. Assess dead code, duplication, and staleness, then execute cleanup with safety gates.
Commands:
| Command | Description |
|---|---|
/tidyup:assess | Analyze codebase for cleanup candidates (read-only) |
/tidyup:cleanup | Execute cleanup with user approval and test verification |
Safety: Never deletes files -- archives to .archive/ instead. Always runs tests after changes.
Batch execution with subagent pipeline, TDD enforcement, code review, verification, and branch completion. The execution engine for plans created by planner.
Commands:
| Command | Description |
|---|---|
/shipit:execute | Execute plan with implement-review-verify pipeline |
/shipit:tdd | Run RED-GREEN-REFACTOR cycle for a single task |
/shipit:review | Dispatch comprehensive code review |
/shipit:verify | Evidence-before-claims verification gate |
/shipit:ship | Complete branch (merge, PR, keep, or discard) |
/shipit:describe-pr | Generate PR description from changes and plan |
Pipeline: Each task goes through implementer → spec-reviewer → quality-reviewer agents. Uses Claude Code native Tasks for real-time coordination.
Python project scaffolding and best practices. Generate pyproject.toml, Pydantic Settings, pre-commit hooks, and audit existing projects.
Commands:
| Command | Description |
|---|---|
/pysmith:setup | Full Python dev environment (pyproject + settings + pre-commit + makefile) |
/pysmith:pyproject | Generate pyproject.toml with uv-native config |
/pysmith:settings | Generate Pydantic Settings + YAML configuration |
/pysmith:precommit | Generate .pre-commit-config.yaml with security hooks |
/pysmith:patterns | Browse 9 copy-paste Python code patterns |
/pysmith:audit | Audit project against Python best practices |
Makefile generation for development and deployment. Supports role-separated Makefiles with self-documenting targets.
Commands: