Agentic Workflow

Agentic Workflow is an AI Engineering skill for Claude Code, published by vibeeval in vibecosystem.

528 stars44 forkson vibeeval/vibecosystemAdded 2026/08/26Repository updated 2026/08/08

ai-agentsai-software-teamanthropicautomationclaudeclaude-codeclaude-skillsdeveloper-toolsdevtoolshooksmulti-agentopen-sourceself-learningvibe-codingvibecoding

Install in seconds

Install Agentic Workflow

Copy Agentic Workflow into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/vibeeval/vibecosystem/tree/main/skills/agentic-workflow ~/.claude/skills/agentic-workflow

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/vibeeval/vibecosystem.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/agentic-workflow/SKILL.md in vibeeval/vibecosystem
Installs to: ~/.claude/skills/agentic-workflow
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agentic Workflow does

Agentic Workflow standardizes a multi-agent pipeline for implementation tasks. It uses background agents for research, planning, validation, implementation, and review with file-based handoffs and test-first execution.

Agentic Workflow is cataloged under AI Engineering on DirSkills. Agentic Workflow comes from a repository tagged ai-agents, ai-software-team, anthropic, automation and claude.

Documentation

README

Excerpt

Agentic Workflow Pattern

Standard multi-agent pipeline for implementation tasks.

Architecture Principles

Use run_in_background: true for all agents to keep main context minimal
Use Task tool (never TaskOutput) to avoid receiving full agent transcripts
Agents write outputs to .claude/cache/agents/<stage>/ for injection into subsequent agents
Main conversation is pure orchestration — no heavy lifting, only coordination

Workflow Stages

1. Research Agent

Task(subagent_type="oracle", run_in_background=true, prompt="""
Query NIA Oracle (via /nia-docs skill) to verify approach and gather best practices.

Output to: .claude/cache/agents/oracle/<task>-research.md
""")

Enforce NIA as the research layer
Output: Research findings

This is the opening of the README. Read the full README on GitHub.

Commands Agentic Workflow provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/nia-docs

Frequently asked about Agentic Workflow

What else does vibeeval publish alongside Agentic Workflow?
Agentic Workflow is one of 25 skills that DirSkills catalogs from vibeeval/vibecosystem, the repository it ships in. Its siblings there include AI Slop Cleaner, API Patterns and API Versioning Patterns. Each one is a separate skill with its own page in this directory, installs the same way Agentic Workflow does, and is maintained by vibeeval in that same repository. The rest of the collection is listed on the vibeeval/vibecosystem page.
How does Agentic Workflow compare to other AI Engineering skills?
Agentic Workflow ranks #2103 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agentic Workflow against them. Open each page to compare what they document and how they install.