routr
claudeEvery routr-* router skill: debug, ship, plan, spec, test, review, deploy, frontend, motion, mobile, AI SDK, video, marketing, security, perf and more, with multi-route plans and depth fallbacks.
29 skills
Claude Code and Codex plugins their authors filed under "development". All categories.
Every routr-* router skill: debug, ship, plan, spec, test, review, deploy, frontend, motion, mobile, AI SDK, video, marketing, security, perf and more, with multi-route plans and depth fallbacks.
29 skills
Production-grade engineering skills, sub-agents and commands (upstream: addyosmani/agent-skills, MIT; pinned, not copied)
25 skills · 4 agents
Structured developer methodology harness — working modes, team practices, and project workflow for any software team
7 skills · 16 commands · 2 agents
Contentstack agent skills for CMS modeling, Delivery SDK, Live Preview, Studio, Brand Kit, Developer Hub apps, Launch, and migrations.
24 skills
The engine around Addy Osmani's agent-skills, embedded: one plugin with its whole workflow under /kaizen: (spec, plan, build, test, review, ship, ideate, debug…), plus what it does not do — a quality gate that keeps a turn open while checks are red, agent-skills' review recorded by itself and required before any push, no secret committed, learnings brought back when a spec, a plan or a file they cover is touched, the PR followed to looks-ready (/kaizen:watch), approximated DORA metrics, friction and cost per feature (/kaizen:metrics). Stops at the merge-ready PR: no deployment
4 skills · 15 commands · 4 agents · hooks
Claude Code plugin for building NestJS bounded contexts with Hexagonal Architecture, DDD, CQRS, and event-driven patterns. 12 skills, 9 agents (Opus 5.5, Sonnet 5, Haiku), rulebook checker CLI with opt-in hooks, TDD workflow, GSD compatible.
12 skills · 9 agents · hooks
AI-assisted planning, development and governance tools
20 skills · hooks
Make the work prove itself. Challenge the goal, cut the clutter, and check what actually happened.
20 skills
Five-stage, repo-agnostic feature pipeline: grill the decisions, author RFC/PRD, discover per repo, build against named proofs, then one adversarial audit gate. Plus /ef:ready: a deterministic gate that keeps the agent rulebook small and true.
9 skills · 9 commands · hooks
Bootstrap и оркестрация команды субагентов: генератор setup с ролевым входом (dev / PM-аналитик) + PM-конвейер feature, движок team-up/team-lazy/team-down (рантайм Agent Teams), team-sync для миграции собранных команд, team-retro/onboard/doctor, готовые Workflow-скрипты, intake-протокол, каталог паттернов оркестрации, Codex second-opinion, hooks-гейты.
6 skills · 10 commands · hooks
Professional engineering discipline with user-owned workflows and model-specific corrections.
12 skills · 3 agents · hooks
Multi-agent code review: full-review cross-correlates several reviewers and has the finding-verifier agent check every finding; code-review-git posts line-level findings as a GitHub PR review and answers other reviewers' comments. Bundles the code-review-agent, security-auditor, code-metrics-analyst, and finding-verifier agents; code-review-git verifies every finding before it is shown. Also security-check, a focused security review of a branch, and the dependency-auditor agent.
8 skills · 3 commands · 5 agents
Framework-specific skills covering the full change lifecycle: React, Vue, NestJS, FastAPI, Flutter, React Native, Terraform, Playwright E2E, and real-device mobile QA with Appium. Every skill bakes in verification loops so changes are proven, not just written.
16 skills
Superpowers teaches Claude brainstorming, subagent driven development with built in code review, systematic debugging, and red/green TDD. Additionally, it teaches Claude how to author and test new skills.
15 skills · hooks
Claude development skills: Agent SDK reference, skill creation, slash command creation, Opus prompting, ultra validation workflows, team-coordinated planning, session retrospectives, and Cowork session migration/export utilities
10 skills · 4 commands · hooks
Plugins for claude code workflow productivity.
10 skills · 4 agents
Architecture, system design and business flow diagrams from a short YAML spec, drawn with the official AWS, Azure, Google Cloud, Kubernetes, GitHub and IBM icons plus 5,500 tech logos, auto-laid out and rendered to SVG, PNG, editable draw.io, React TSX, HTML and design documents. Skill orrery with a bundled CLI; commands /orrery:draw, /orrery:doc, /orrery:import-image, /orrery:review; agents planner, diagram-author, image-importer, patch-proposer and four reviewers (accuracy, conventions, flow, legibility). Lives in its own repo.
1 skill · 4 commands · 8 agents · hooks
Data science, bioinformatics, and research tooling skills for Sage Bionetworks
8 skills · 5 agents
Automated PR code review for GitHub — 6 specialized agents + Codex, wiki-based pattern learning, self-review/respond/re-review modes, model tiering, session-scoped /tmp, pre-commit drift-check hook, and Managed Agent CI option.
5 commands · 7 agents · hooks
Git and GitHub workflow skills: Conventional Commit messages, PR titles and descriptions with template detection, resolving PR review threads (its workflow instructs it to present its analysis and wait for approval before replying or resolving), and a catchup command to restore branch context. Also release, quick-fix, and ship-feature workflows, and changelog-generator and release-notes skills.
9 skills · 4 commands
Decision-Linked Development: record, link, and audit development decisions alongside code
12 skills · hooks
PyTorch torch.compile debugging tools and workflow automation
8 skills · 4 agents
Land governed project knowledge in a canonical Stable Knowledge Graph, route work by surface, and keep it coherent with graph validation.
12 skills
Nine task routes built from the best upstream skills, deduplicated, with an eval suite per route.
9 skills · 2 agents
Everyday dev commands -- commit, review, test, fix bugs, create PRs, check repo status, and inspect PR health. Agents: code-reviewer, debugger. Hook: auto-format. Commands use dynamic context injection for grounded, first-attempt responses.
1 skill · 7 commands · 2 agents · hooks
Repo analysis for coding agents with slash commands, skills, documentation agents, and a bundled Cartograph MCP server.
2 skills · 3 commands · 5 agents · 1 MCP server
Compact safeguards and explicit specialist workflows without runtime clutter
10 skills
Design and documentation toolkit with agents for creating system architectures, C4 diagrams, ADRs, and conducting quality analysis
1 skill · 3 commands · 5 agents · hooks
Structured web knowledge tools for development and research. Enables querying of Diffbot’s Knowledge Graph (for organizations, people, and news articles) as well as web extraction, crawling, entity resolution, and web search.
10 skills
Skills rebuilt for current models, each with a with/without eval and a measured delta.
9 skills