{
  "$schema": "https://top-agent-skills.com/schemas/catalog.v1.json",
  "type": "primary-category",
  "slug": "workflow-orchestration",
  "title": "Workflow Orchestration",
  "shortTitle": "Workflows",
  "description": "Brainstorm → spec → plan → build → review → merge. Multi-step multi-agent orchestration.",
  "canonical": "https://top-agent-skills.com/top-skills-for-workflow-orchestration",
  "alternates": {
    "html": "https://top-agent-skills.com/top-skills-for-workflow-orchestration",
    "markdown": "https://top-agent-skills.com/top-skills-for-workflow-orchestration.md",
    "json": "https://top-agent-skills.com/top-skills-for-workflow-orchestration.json"
  },
  "rubricVersion": "1.0",
  "methodology": "https://top-agent-skills.com/about/methodology",
  "contentLastUpdated": "2026-08-31",
  "count": 19,
  "topPick": {
    "slug": "antigravity-awesome-skills",
    "name": "antigravity-awesome-skills",
    "score": 65,
    "tagline": "1,234+ skills in one bundle. Single install across AI coding assistants.",
    "url": "https://top-agent-skills.com/skill/antigravity-awesome-skills"
  },
  "ranking": [
    {
      "rank": 1,
      "slug": "antigravity-awesome-skills",
      "name": "antigravity-awesome-skills",
      "score": 65,
      "tagline": "1,234+ skills in one bundle. Single install across AI coding assistants.",
      "bestFor": "Teams that want a comprehensive starting set rather than picking 30 individually.",
      "notIdealFor": "Lean setups — you will install many skills you never use.",
      "provenance": "community",
      "publisher": "Antigravity",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor",
        "codex",
        "gemini-cli",
        "antigravity"
      ],
      "install": "npx antigravity-awesome-skills --claude",
      "url": "https://top-agent-skills.com/skill/antigravity-awesome-skills",
      "json": "https://top-agent-skills.com/skill/antigravity-awesome-skills.json"
    },
    {
      "rank": 2,
      "slug": "superpowers",
      "name": "superpowers",
      "score": 61,
      "tagline": "Structured multi-step development. Brainstorm → spec → plan → build → review → merge — TDD baked in.",
      "bestFor": "Long-running engineering tasks where you want each phase to handoff cleanly.",
      "notIdealFor": "Quick one-shot tasks — the orchestration overhead is not worth it.",
      "provenance": "community",
      "publisher": "obra",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor",
        "codex"
      ],
      "install": "npx skills add obra/superpowers",
      "url": "https://top-agent-skills.com/skill/superpowers",
      "json": "https://top-agent-skills.com/skill/superpowers.json"
    },
    {
      "rank": 3,
      "slug": "composio-tool-router",
      "name": "composio",
      "score": 54,
      "tagline": "Composio's official skill for connecting agents to 1000+ external apps: auth configs, per-user connections, tool execution, and triggers.",
      "bestFor": "Building a multi-user agent or app that needs per-user OAuth connections to many third-party services (Gmail, Slack, GitHub, Notion) without hand-rolling each integration.",
      "notIdealFor": "A single, deep integration with one provider — a provider-specific skill (e.g. the Stripe or Twilio skills) gives sharper, vendor-authored guidance than a broad tool router.",
      "provenance": "verified-org",
      "publisher": "Composio",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor"
      ],
      "install": "npx skills add composiohq/skills",
      "url": "https://top-agent-skills.com/skill/composio-tool-router",
      "json": "https://top-agent-skills.com/skill/composio-tool-router.json"
    },
    {
      "rank": 4,
      "slug": "education-agent-skills",
      "name": "education-agent-skills",
      "score": 53,
      "tagline": "The pedagogy library: backwards design, rubric generation, formative assessment, learning progressions.",
      "bestFor": "Teachers, instructional designers, and curriculum leads who want unit plans, rubrics, and assessments grounded in named pedagogical research rather than generic prose.",
      "notIdealFor": "Anyone needing a permissive software licence. It ships under CC BY-SA 4.0 — a copyleft content licence, so derivative material inherits ShareAlike. Also a single-maintainer project, and 165 skills is a large metadata footprint to load at once.",
      "provenance": "community",
      "publisher": "Gareth Manning",
      "license": "CC BY-SA 4.0",
      "compatibility": [
        "claude-code"
      ],
      "install": "npx skills add GarethManning/education-agent-skills --skill retrieval-practice-generator",
      "url": "https://top-agent-skills.com/skill/education-agent-skills",
      "json": "https://top-agent-skills.com/skill/education-agent-skills.json"
    },
    {
      "rank": 5,
      "slug": "architecture-adr",
      "name": "architecture",
      "score": 51,
      "tagline": "ADR authoring + design review. Trade-offs, consequences, alternatives.",
      "bestFor": "Choosing between technologies, documenting a design decision, or reviewing a proposal.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor",
        "codex",
        "antigravity"
      ],
      "install": "claude plugin install engineering",
      "url": "https://top-agent-skills.com/skill/architecture-adr",
      "json": "https://top-agent-skills.com/skill/architecture-adr.json"
    },
    {
      "rank": 6,
      "slug": "system-design",
      "name": "system-design",
      "score": 51,
      "tagline": "System design from requirements. APIs, data, boundaries, scale.",
      "bestFor": "Greenfield service design or designing a new feature that crosses service boundaries.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor",
        "codex",
        "antigravity"
      ],
      "install": "claude plugin install engineering",
      "url": "https://top-agent-skills.com/skill/system-design",
      "json": "https://top-agent-skills.com/skill/system-design.json"
    },
    {
      "rank": 7,
      "slug": "productivity-start",
      "name": "start",
      "score": 50,
      "tagline": "One-command productivity bootstrap. Memory, tasks, dashboard.",
      "bestFor": "Setting up the productivity plugin for the first time.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "antigravity"
      ],
      "install": "claude plugin install productivity",
      "url": "https://top-agent-skills.com/skill/productivity-start",
      "json": "https://top-agent-skills.com/skill/productivity-start.json"
    },
    {
      "rank": 8,
      "slug": "deep-research",
      "name": "deep-research",
      "score": 50,
      "tagline": "Cited research reports from fanned-out web search with adversarial verification.",
      "bestFor": "Any deep, multi-source, fact-checked research request — competitive analysis, technical surveys, market sizing.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "antigravity"
      ],
      "install": "Built into Claude Code. Invoke with /deep-research.",
      "url": "https://top-agent-skills.com/skill/deep-research",
      "json": "https://top-agent-skills.com/skill/deep-research.json"
    },
    {
      "rank": 9,
      "slug": "consolidate-memory",
      "name": "consolidate-memory",
      "score": 50,
      "tagline": "Memory hygiene. Merge, fix, prune.",
      "bestFor": "Periodic maintenance of the memory directory when entries accumulate and start to drift.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "antigravity"
      ],
      "install": "Built into Claude Code. Invoke with /consolidate-memory.",
      "url": "https://top-agent-skills.com/skill/consolidate-memory",
      "json": "https://top-agent-skills.com/skill/consolidate-memory.json"
    },
    {
      "rank": 10,
      "slug": "setup-cowork",
      "name": "setup-cowork",
      "score": 50,
      "tagline": "Bootstrap the right plugin stack for your role in one guided pass.",
      "bestFor": "New teams onboarding to Claude Code or Cowork who want a role-fitted plugin bundle.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "antigravity"
      ],
      "install": "Built into Claude Code. Invoke with /setup-cowork.",
      "url": "https://top-agent-skills.com/skill/setup-cowork",
      "json": "https://top-agent-skills.com/skill/setup-cowork.json"
    },
    {
      "rank": 11,
      "slug": "loop",
      "name": "loop",
      "score": 48,
      "tagline": "Recurring task runner. Self-paced or interval-based.",
      "bestFor": "Polling for status, monitoring a deploy, repeating a check at intervals.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code"
      ],
      "install": "Built into Claude Code. Invoke with /loop.",
      "url": "https://top-agent-skills.com/skill/loop",
      "json": "https://top-agent-skills.com/skill/loop.json"
    },
    {
      "rank": 12,
      "slug": "schedule",
      "name": "schedule",
      "score": 48,
      "tagline": "Cron for remote Claude Code agents. Set it and forget it.",
      "bestFor": "Automated daily/weekly tasks — standup, status reports, monitoring, batch jobs.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code"
      ],
      "install": "Built into Claude Code. Invoke with /schedule.",
      "url": "https://top-agent-skills.com/skill/schedule",
      "json": "https://top-agent-skills.com/skill/schedule.json"
    },
    {
      "rank": 13,
      "slug": "alirezarezvani-skills",
      "name": "alirezarezvani-skills",
      "score": 47,
      "tagline": "232+ skills across engineering, marketing, product, compliance, advisory.",
      "bestFor": "Mixed-discipline teams looking for one source.",
      "notIdealFor": null,
      "provenance": "community",
      "publisher": "alirezarezvani",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor",
        "codex",
        "gemini-cli"
      ],
      "install": "npx skills add alirezarezvani/claude-skills",
      "url": "https://top-agent-skills.com/skill/alirezarezvani-skills",
      "json": "https://top-agent-skills.com/skill/alirezarezvani-skills.json"
    },
    {
      "rank": 14,
      "slug": "memory-management",
      "name": "memory-management",
      "score": 47,
      "tagline": "Workplace memory that actually understands your team's shorthand.",
      "bestFor": "Anyone who works inside a company with its own jargon, project codenames, and internal language.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "antigravity"
      ],
      "install": "claude plugin install productivity",
      "url": "https://top-agent-skills.com/skill/memory-management",
      "json": "https://top-agent-skills.com/skill/memory-management.json"
    },
    {
      "rank": 15,
      "slug": "task-management",
      "name": "task-management",
      "score": 47,
      "tagline": "Lightweight task tracking in a single markdown file.",
      "bestFor": "Individuals and small teams who want task tracking without yet another SaaS subscription.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "antigravity"
      ],
      "install": "claude plugin install productivity",
      "url": "https://top-agent-skills.com/skill/task-management",
      "json": "https://top-agent-skills.com/skill/task-management.json"
    },
    {
      "rank": 16,
      "slug": "productivity-update",
      "name": "update",
      "score": 47,
      "tagline": "Periodic memory + task refresh from real activity.",
      "bestFor": "Daily or weekly sync to keep working memory fresh and tasks current.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "antigravity"
      ],
      "install": "claude plugin install productivity",
      "url": "https://top-agent-skills.com/skill/productivity-update",
      "json": "https://top-agent-skills.com/skill/productivity-update.json"
    },
    {
      "rank": 17,
      "slug": "cowork-plugin-customizer",
      "name": "cowork-plugin-customizer",
      "score": 45,
      "tagline": "Tailor a plugin to your org's stack in one pass.",
      "bestFor": "Teams that have installed a plugin but need it to match their tools, naming and workflows.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code"
      ],
      "install": "claude plugin install cowork-plugin-management",
      "url": "https://top-agent-skills.com/skill/cowork-plugin-customizer",
      "json": "https://top-agent-skills.com/skill/cowork-plugin-customizer.json"
    },
    {
      "rank": 18,
      "slug": "research-hub",
      "name": "research-workspace",
      "score": 44,
      "tagline": "Zotero plus Obsidian plus NotebookLM as one agent-operable research workspace.",
      "bestFor": "Researchers with a reference library and a note vault who want triage, synthesis, and topic selection driven from the agent rather than by hand.",
      "notIdealFor": "Anyone not already using Zotero or Obsidian — the value is in orchestrating those tools, not replacing them. Shares a maintainer with the zotero-skills entry.",
      "provenance": "community",
      "publisher": "Wenyu Chiou",
      "license": "MIT",
      "compatibility": [
        "claude-code"
      ],
      "install": "claude plugin marketplace add WenyuChiou/ai-research-skills",
      "url": "https://top-agent-skills.com/skill/research-hub",
      "json": "https://top-agent-skills.com/skill/research-hub.json"
    },
    {
      "rank": 19,
      "slug": "loki-mode",
      "name": "loki-mode",
      "score": 38,
      "tagline": "Multi-agent orchestration. Spawn parallel subagents and merge their outputs reliably.",
      "bestFor": "Greenfield startup explorations, parallel work that benefits from specialization.",
      "notIdealFor": null,
      "provenance": "community",
      "publisher": "asklokesh",
      "license": "MIT",
      "compatibility": [
        "claude-code"
      ],
      "install": "npx skills add asklokesh/claudeskill-loki-mode",
      "url": "https://top-agent-skills.com/skill/loki-mode",
      "json": "https://top-agent-skills.com/skill/loki-mode.json"
    }
  ],
  "faqs": [
    {
      "question": "What is a Workflow vs a Skill?",
      "answer": "A Skill teaches one agent how to do one kind of task. A Workflow scripts multiple agent calls deterministically — fan-out, pipelines, judges, verifiers. Workflows compose Skills."
    },
    {
      "question": "When should I use a multi-agent workflow?",
      "answer": "When the work is too large for one context, when independent perspectives are valuable (adversarial verification, judge panels), or when the structure of the process should be deterministic rather than model-decided."
    },
    {
      "question": "Are these Skills expensive?",
      "answer": "Yes — they fan out across many agents and consume meaningful tokens. The right use case is when correctness or coverage justifies the cost."
    },
    {
      "question": "Do workflow Skills work with the Claude Agent SDK?",
      "answer": "Yes — the SDK exposes the Workflow primitive directly. Several Skills here target SDK-based custom runtimes."
    },
    {
      "question": "What does ultrareview do?",
      "answer": "It runs a multi-agent cloud review of the current branch — multiple reviewers across security, correctness, and reuse dimensions, then synthesizes. Billed; user-triggered."
    }
  ],
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "attribution": "Top Agent Skills (https://top-agent-skills.com)"
}