Workflow plugins

Exactly one claimant per intent. Rails and .NET.

23 skills · 7 commands · 6 agents · hooks

Structured phased decomposition for agentic execution. Injects the Locus dispatcher next to every prompt, enforces the classification line at turn end, and ships the Algorithm as a progressively-disclosed skill.

18 skills · 17 agents · hooks

Complete collection of agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use

11 skills · 15 commands · 9 agents · hooks

Complete collection of agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use

11 skills · 15 commands · 9 agents · hooks

Complete collection of agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use

11 skills · 15 commands · 9 agents · hooks

Awesome SDD, maintained by blackPeanut. Spec-Driven Development pipeline: 24 atomic Socratic skills (survey/scaffold → spec → ux-flows → design → data-model → api → screens → tasks → tests → implement → review → ship) + a living decomposition roadmap (steps + dependency graph + parallel-safe execution waves) above the per-feature flow + 10 subagents, plus a TDD implementation engine with agent-team and dynamic-workflow modes. The Q&A skills are depth-tunable (easy/medium/hard); the ideation analyses (researcher/strategist/analyst/devil's-advocate) run as named subagents gated by that dial; diagrams are confirmed in prose; and every acceptance criterion is covered end-to-end. Surface-aware: declare target surfaces at design (backend/web/mobile/desktop/CLI/worker/library, as C4 containers); downstream gates the `ui` task layer, UI-driven flows, and frontend test tiers. UI features get a design pipeline (auto-skipped for backend-only work): design-system (the committed canon — Figma MCP / Pencil MCP / code-markdown; on pencil it also bootstraps and seeds the .pen library), ux-flows (user flows + SCR inventory) and screens (the per-state manifest tasks/implement/review build against, reuse-first). Every stage prints a copy-ready handoff (what changed + files to review + `/clear` + the next command).

24 skills · 10 agents

從需求到 PR 的完整開發流程編排，含狀態機棘輪與暫停確認點。

23 skills · 8 agents · hooks

Portable agent practices: design, planning, delegation, verification, debugging, review and testing discipline

19 skills · 9 commands · 3 agents · hooks

Complete Claude agentic dev-kit: 11 specialized subagents, 9 skills, 4 commands, 9 hook scripts, and 6 MCP integrations for the full software development lifecycle.

9 skills · 4 commands · 11 agents · 6 MCP servers · hooks

Find local businesses, build a site from their own Instagram, send a short video, run it on jtakeit

12 skills · 16 commands · 1 agent · 2 MCP servers

Profil Claude Code dev-fullstack : doctrine de travail, sub-agents et skills.

15 skills · 15 agents · hooks

23 subagent specializzati, collaudo parallelo, gate meccanici su merge e produzione, journal tracciato e generatore di materiale didattico.

6 skills · 24 agents · hooks

Planning, execution, git, pull request, code review, and agent orchestration skills

30 skills

A standard operating procedure for AI-assisted delivery. Install this, then run `keel init` in a project.

25 skills · 3 agents · hooks

Question → Evidence → Draft → Verify → Cite discipline for scholarly writing in LaTeX and BibTeX, with citation enforcement.

23 skills · 5 agents · hooks

Squad agentica generica: descobrimento, PO, Scrum Master, Architect, Designer, Innovation, Dev, QA, Security, Tech Writer, Data e Delivery. Board ageis com colunas To Do / Developing / QA / Done, RFC como contrato e adaptacao por projeto sem tocar no nucleo.

3 skills · 12 commands · 12 agents · hooks

Risk-scaled feature, fix, verification, and commit workflows with test-driven implementation and evidence-based completion

27 skills

Use when a bug is reported, found, fixed, or reopened, or before working in a bug-prone area. Check BUG_LIST.md before debugging: many "new" bugs are regressions of fixed ones.

27 skills

Cold-start briefing from the project's newest handoff, open bugs and next-session prompt in one script pass, turns Remote Control on, then stops. Use at session start or on "call handoff", "catch up", "where did we leave off".

27 skills

Bootstrap a brand-new project with proven architecture defaults and continuity scaffolding. Use when starting a new project from scratch, or when touching a legacy project that has no handoff/git/structure yet.

27 skills

Superpowers skills + harness quality loops: TDD, debugging, policy enforcement, learning from failures

18 skills · 3 commands · 4 agents · hooks

Phase-locked development workflow plugin. Enforces earned progression through discovery, design, planning, execution, verification, and integration.

16 skills · 9 agents · hooks

karpathy-guidelines와 issue-driven development가 구조적으로 통합된 커스텀 개발 워크플로우 하네스

25 skills · hooks

Kit de workflow: feature-delivery, planos, review, testes e subagents por wave

17 skills · 8 agents · hooks

Polyglot dev-workflow hooks (lint on edit, verification before stopping, a dangerous-command and secret guard, advisory reminders) plus the skills those hooks point at.

25 skills · hooks

Security-first, requirements-first Solana full-stack companion: 15 skills, cohort knowledge base, agents, and workflows.

19 skills · 7 agents

Self-configuring, verification-first DevOps workflow for AI coding agents. Built for Claude Code; its AGENTS.md contract is tool-agnostic (Codex reads it natively), and no adapters for other tools ship yet. Includes constitution, hooks, project analyzer, claim validator, three-tier memory, EARS specs, OWASP ASI 2026 security baseline, and a signed skill library.

25 skills

23-agent FSM pipeline. Marketplace install ships agents, commands, and templates only. Run the /fsm-setup-hooks command after install to complete the enforcement layer (hooks cannot be installed via the plugin marketplace and are required for the full package).

2 commands · 23 agents

Nested spec→plan→work→verify→review→compound loop for disciplined AI-assisted development, plus an agent-native runtime pillar (/flywheel:process + /flywheel:run) that turns recurring domain operations into self-improving, persistence-aware process contracts Claude executes as the backend. Also an autonomous metric-driven loop, parallel multi-specialist review, and spec↔code sync. Plans route each task to a model/effort tier so cheap work runs cheap and judgment runs strong. /flywheel:route does the same for work delegated outside a plan: tool, fresh session or subagent, at which model and effort.

18 skills · 6 agents · hooks

Standard Claude Code setup used across all of Gabe Borges' repos. Applies the Plain English output style everywhere, strips AI-attribution footers from GitHub writes, appends the writing rules to subagent prompts, keeps Codex calls off GPT-6 Astra unless the user named it, re-injects the writing rules reminder with every user message, and bundles the writing-voice, read-aloud-prep, bear-notes, codex-delegate, model-routing-review, and pair-debate skills, the grill, build, spec, routine, wayfinder, handoff, research, wait-what, teach, writing-for-agents, domain-modeling, investigate, and resolving-merge-conflicts skills rewritten in plain English from Matt Pocock's set, four routed subagents (haiku-medium, opus-medium, opus-xhigh, and the user-summoned fable-xhigh), the add-to-git, setup, and setup-repo commands, and the frontend-design and context7 plugins.

18 skills · 3 commands · 4 agents