Geekstack Flow — Testing skill for Claude Code
A structured AI workflow for planning, coding, reviewing, testing and shipping software — LLM wiki memory, a task lifecycle, risk-tiered governance, and a local cockpit that runs your agents (Claude C.
How to install Geekstack Flow
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open bibennurbani/geekstack-flow and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Geekstack Flow does
A structured AI workflow for planning, coding, reviewing, testing and shipping software — LLM wiki memory, a task lifecycle, risk-tiered governance, and a local cockpit that runs your agents (Claude Code, Codex, Copilot).
Alternatives in Testing
- Factory — Dark Factory Mode - Spec-in, software-out autonomous pipeline 2.8k ★
- AI Contribution Skills (Engram) — branch-pr: clean branch and PR workflow 2.5k ★
- Spec Kitty — Spec-Driven Development for serious software developers 1.6k ★
README
Creative GeekStack Flow
[](https://github.com/bibennurbani/geekstack-flow/actions/workflows/ci.yml) [](https://www.npmjs.com/package/geekstackflow) [](https://www.npmjs.com/package/geekstackflow) [](LICENSE) [](https://nodejs.org) [](package.json) [](CONTRIBUTING.md)
**A structured AI workflow for planning, coding, reviewing, testing, and shipping software — with project memory, task tracking, governance, and a local cockpit that runs your agents.**
[](docs/images/cockpit.jpg)
`geekstackflow ui` — every project's ready work, grouped by the agent role that comes next. Press **▶** and the Orchestrator launches that agent, streams the run live, and pauses for your approval on anything HIGH or CRITICAL. *(Shown with a demo workspace.)*
`geekstackflow` scaffolds a `.tcgstackflow/` workspace inside any project that gives your AI coding tools (Claude Code, Codex, GitHub Copilot) a shared brain: a Karpathy-style LLM wiki for memory (searched via mandatory [qmd](https://github.com/tobi/qmd) hybrid search), a strict two-file task system, six agent roles with a clear lifecycle, governance with risk levels, and a local web **Cockpit** that is also the **Orchestrator** — launch agents on tasks from the browser, watch the run stream live, approve HIGH/CRITICAL actions, and track token spend.
Why this exists
Every AI coding tool ships its own instructions fi
Related Skills
Claude Engineer Toolkit
AI-powered toolkit for Claude Code that provides structured workflows, commands, and agents to automate planni
Cleargate
Planning framework for Claude Code agents — sprint/epic/story protocol, four-agent loop (architect/developer/q
Dual Gate Moa
Dual-Gate-MoA: harness-enforced dual gates for LLM agents (recon before acting, QA before shipping) + MoA mult
GAAI Framework
95+ Drop-in governance layer (.gaai/ folder) -- backlog authorization, cross-session memory, decision tracking
Add
ADD — Agent Driven Development. Coordinated AI agent teams that ship verified software. Spec-driven TDD, trust
Outlook LLM Tests
Run make crud-test from the repository root via the Bash tool. This is the primary, canonical way to execute t
Related Agents
Worker Lint
Runs lint.py against the wiki, parses tiered output, returns severity summary. Use before quarterly reviews or
Vision
GSD-2 is the orchestration layer between you and AI coding agents. It handles planning, execution, verificatio
Price Comparison
Compares prices across vendors and markets, calculates markups, and factors in import costs (shipping, VAT, cu