Development plugins

Execute Markdown plans as dependency-ready task DAGs: every task in its own Git worktree, independently verified before it integrates, with durable recovery evidence and human-reviewed PR delivery. Requires Git. Works in Claude Code and Codex.

2 skills · 6 agents · hooks

Generate a navigable, version-controlled multi-page Markdown wiki from a codebase, engineered for on-demand retrieval as Claude's context while staying human-readable. Two-pass outline-then-fill generation across a parallel agent swarm of planner, diagram author, page writers, and index synthesizer; consumes a code-atlas index as ground truth when present, else self-scans. Pure static Markdown (no embeddings), Mermaid diagrams derived from the dependency graph, per-page source provenance, and git-blob hash-diff staleness detection that regenerates only stale pages. A SessionStart hook loads the wiki index at session start

2 skills · 6 agents · hooks

Comprehensive code quality automation with linting, testing, security scanning, and pre-commit hooks. Enforces coding standards, catches issues before commit, and provides detailed quality reports.

5 commands · 3 agents · hooks

Build and audit GOV.UK-compliant services: GOV.UK Design System components, patterns and styles, plus WCAG 2.2 AA accessibility and the public sector accessibility regulations.

2 skills · 5 commands · 1 agent · hooks

Build, audit, and preview modern web apps with shadcn/ui components on Radix UI primitives and Tailwind CSS, meeting WCAG 2.2 AA accessibility. The default design system for net-new SME and startup web apps.

2 skills · 5 commands · 1 agent · hooks

Build, audit, and preview Material Design interfaces in the app's own framework (Svelte SMUI/m3-svelte, React @mui/material): the shared Material system (colour, type, spacing, elevation, theming) and component inventory, plus WCAG 2.2 AA accessibility for consumer and general-purpose web apps.

2 skills · 5 commands · 1 agent · hooks

Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual Editing.

4 skills · 4 commands · 1 MCP server

Autonomous TDD pipeline for building features end-to-end. Chains PRD → gate tests → implementation → live validation → remediation in a self-correcting loop. Uses headless Claude sessions via the relentless CLI for multi-phase execution. Includes autoresearch for autonomous skill optimization.

9 skills

Six-stage AI-native SDLC: Python-gated artifacts, hooks as guardrails, TDD from build to maintain.

6 commands · 2 agents · hooks

Claude Code MCP plugin that saves 98% of your context window. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and intent-driven search.

7 skills · 1 MCP server · hooks

Generates and validates RosTooling ROS 2 model files (.ros, .ros2, .rossystem) against the Xtext grammar and validators, with an optional headless language server for real diagnostics.

4 skills · 2 commands · 1 agent · hooks · LSP

Three-cell multi-agent system — Development, Delivery Engineering, and QA.

2 skills · 6 commands · hooks

Guard hooks, implementer/reviewer subagents and workflow skills for spec-driven, test-first development with adversarial review.

5 skills · 3 agents · hooks

Five-role orchestrator protocol (Product Owner / orchestrator / worker / reviewer / supervisor) for OpenSpec-driven task implementation, reusable across projects.

1 skill · 2 commands · 6 agents

개발하기 — repo의 에이전트 친화도를 채점하고(ai-readiness-cartography), herdr pane에 일을 넘길 때 모델·권한을 고른다(herdr-dispatch)

9 skills

Skills dựng form dynaform, nhúng @dnu/dynaform-builder và quy ước mfe-dynaform.

9 skills

Slash commands and a skill for the qli CLI.

1 skill · 7 commands · 1 MCP server

Run a skein workspace as an orchestrator — plan work in execution-plan.md, launch implementer workspaces with a standard prompt, refresh status across GitHub, trackers and skein

8 skills · hooks

Work on a Unity project with a live editor over MCP and the Unity CLI: the edit-compile-test-play loop, Safe Mode recovery, EditMode tests without assembly definitions, and documentation audits.

9 skills

Pull request bodies that double as IEC 62304 / ISO 13485 verification records.

9 skills

Cloud-safe core: design, refine, execute, comprehensive-review, close-out, post-build. Also login (interactive). No interactive gates that dead-end headless; installable in cloud build and pipeline environments.

7 skills · 1 MCP server · hooks

A small, visual software factory: /factory <feature> runs a feature or bug through spec-writer, builder, four parallel reviewers and an approver on its own branch, then merges to main or hands it to you. Repo-specific commands live in .factory/repo.md from /factory setup. Live dashboard included.

1 skill · 8 agents

Bootstrap new repositories from BazelStarterTemplate and keep existing ones in line with it: hermetic Bazel builds, devenv, format/lint, tests, CI, release-please, OCI images, Doxygen.

5 skills · 4 agents

Platform .NET guardrails, /plan from an issue with red tests, /validate against Platform and deterministic hooks.

2 skills · 4 commands · 1 agent · 1 MCP server · hooks

Platform .NET guardrails, /plan from an issue with red tests, /validate against Platform and deterministic hooks.

2 skills · 4 commands · 1 agent · 1 MCP server · hooks

Steering for Kernel (kernel.sh) cloud browsers in TypeScript projects: a live-tested knowledge skill, debugging and login workflows, hooks that catch deprecated fields and leaked API keys, and the Kernel MCP server.

7 skills · 1 MCP server · hooks

Claude Code skills for a stronger GitHub presence: repository audit, README writer, community health files, discoverability, release notes, repository hardening, profile optimizer, repository families, and upstream contributions.

9 skills

An Opus orchestrator that takes homelab apps through requirements, design, mockups, build, review, QA and release, with your sign-off at four gates.

2 skills · 7 agents

Skills del ciclo issue → spec → PR → conocimiento, RAG local sobre docs/knowledge y hooks que hacen cumplir los límites del agente.

8 skills · hooks

Stateful codebase audit, remediation queue, docs drift and UX review as nine namespaced skills.

9 skills