.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

home/blog/ai-agent-workflows
home/blog/ai-agent-workflows

Explainers

Agent workflows: when one prompt isn't enough

aaaa.fyi · 2026-07-02 · 5 min read

Explainers

A single agent with a good prompt handles most tasks. Workflows exist for the rest: work that needs structure, repetition or more than one pair of hands.

When a workflow earns its keep

  • The task repeats. Weekly release notes, dependency updates, triage rotations — anything you'd otherwise re-prompt from scratch.
  • The task fans out. Reviewing 40 files, migrating 200 call sites. One agent per unit of work, results merged at the end.
  • The task needs checkpoints. Generate, then verify, then apply — with a human or a stricter agent between steps.
  • Patterns that keep showing up

    Pipeline: each item flows through fixed stages (find → transform → verify). Fan-out/fan-in: split work across parallel agents, merge results. Generator + critic: one agent produces, another tries to break the output before it ships.

    Where to find them

    You'll find these packaged as skills and plugins — most are a config file plus instructions, installable in minutes. As with everything on the site, ranking is by real GitHub activity, not editorial choice.