Flow Experiment — Development skill for Claude Code
Experiment flow backed by manifests, experiment summary state, and shared middleware.
How to install Flow Experiment
Installs to ~/.claude/skills/th3vib3coder-vibe-research-environment-flow-experiment/SKILL.md
mkdir -p ~/.claude/skills/th3vib3coder-vibe-research-environment-flow-experiment && curl -fsSL https://raw.githubusercontent.com/th3vib3coder/vibe-research-environment/HEAD/commands/flow-experiment.md -o ~/.claude/skills/th3vib3coder-vibe-research-environment-flow-experiment/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Flow Experiment does
description: Experiment flow backed by manifests, experiment summary state, and shared middleware argument-hint: "--register | --update | --blockers" allowed-tools: Read, Bash model: sonnet
/flow-experiment
This command is a thin entrypoint over:
environment/control/middleware.jsenvironment/flows/experiment.js
Subcommands
- no args: list experiments
--register: create a new experiment manifest--update: update manifest-backed experiment status
Alternatives in Development
- Notebooklm Skill — Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks 5.9k ★
- Openwolf — Sharper context 699 ★
- Experiment — Experiment — Setup + Code Generation + Execution 613 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Flow Results
Package a completed experiment into a typed results bundle through shared middleware
Flow Literature
Literature flow backed by environment/flows/literature.js and shared middleware
Workspace Codemap Pro
Build evidence-backed repository and workspace code maps with rendered diagrams, provenance, integrity manifes
Site Pin Gate
Agent Skill: put a shared-PIN gate in front of a whole Next.js site from proxy.ts or middleware.ts — one env v
Lab Nt
The discoverer — shape a research idea into a contract (question · falsifiable metric · fence · budget), then
Tui
Open or snapshot the read-only terminal dashboard backed by shared Thoth providers.
Related Agents
Experiment Runner
ML/empirical experiment design specialist — pre-registration, Fisher-style design, reproducibility manifests
Project Advisor
Use proactively for project history, architecture, experiment findings, codebase navigation, or evidence-backe
Deployment Metadata Analyst
Identifies metadata dependencies, builds deployment manifests, and produces the exact sf CLI commands and pre/