Skill To Workflow — Data skill for Claude Code
Compile any Claude Agent Skill into a multi-agent Workflow — a meta-workflow that recovers the parallelism hidden in a skill's prose and emits a fan-out · pipeline · adversarially-verified Workflow.
How to install Skill To Workflow
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open democra-ai/skill-to-workflow and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Skill To Workflow does
Compile any Claude Agent Skill into a multi-agent Workflow — a meta-workflow that recovers the parallelism hidden in a skill's prose and emits a fan-out · pipeline · adversarially-verified Workflow.
Alternatives in Data
- Agentlas Storm — Run a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion 1.1k ★
- Book Translation Skill — You are a book translation assistant 489 ★
- Team Tasks — Multi-agent pipeline coordination: Linear, DAG, and Debate modes for AI agent orchestration 446 ★
README
skill-to-workflow
Compile any Claude Agent Skill into a multi-agent Workflow — automatically.
A meta-workflow that reads a Skill, recovers the parallelism hidden in its prose,
and emits a fan-out · pipeline · adversarially-verified Workflow that runs in a fraction of the wall-clock.
What it does · The upgrade · Install · Usage · How it works · Docs
There's a `skill-creator` skill — a skill for making skills. This is its sibling one layer up: a **workflow that makes workflows**, by *compiling* the skills you already have.
[**Agent Skills**](./docs/SKILL-SPEC.md) are how you teach Claude a procedure: a `SKILL.md` of instructions, optionally with bundled `references/`, `scripts/`, and `
Related Skills
The Swarm
Claude Code plugin for multi-pattern multi-agent orchestration, using CC's built in Agent Swarm as the engine
Fanout Loop
Execute ONE iteration of an effort's fan-out loop — pick-up, derive the run, dispatch a tier-laddered pipeline
OSICBench
Operating Scientific Instruments via Code — a benchmark for AI agents. Physics goal + instrument manual in; an
Code Review Pipeline
Run the full code review pipeline on your changes. Creates an agent team of parallel reviewers covering both t
Rewriter
Four-stage editorial pipeline that rewrites raw content into clean business prose. A Claude Code skill.
Fixer Plan
You are triaging a single pull-request review comment for an automated pipeline. Your ONLY job is to decide wh
Related Agents
Doc Impact Verifier Light
Verifies whether a single documentation file still matches a described source-code/config change. Report-only;
Integration Critic
Adversarially reviews the COMBINED (union) tree of a multi-node ATLAS-WEAVE run through the SEAM lens — the cr
Founder
founder orchestrator — plans, delegates, and stewards long sessions. Spawns coding subagents instead of writin