A-H-911

Tamheed — Development skill for Claude Code

Development community

تمهيد — ground work for execution: turn a project description into a validated, execution-ready planning & handoff package for Claude Code.

How to install Tamheed

This entry records only its repository, not the path inside it, so there is no exact command to give. Open A-H-911/tamheed and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tamheed does

تمهيد — ground work for execution: turn a project description into a validated, execution-ready planning & handoff package for Claude Code. Relational package store (SQLite ⇄ canonical JSONL), MCP-only writes, schema-enforced quality gates, HTML review surface. Successor of Keystone.

Alternatives in Development

Epic Publish — Publish a validated epic update back to the issue and local cache 243.5k ★
/factory-status - Check Factory Build Progress — See what you've built, what's validated, what's installed, and what's next 618 ★
Maestro Ralph — Closed-loop policy over the canonical Session/Run chain 530 ★

README

Tamheed

Turn a project description into a validated, traceable, execution-ready planning & handoff package for Claude Code to implement.

Claude Code plugin + MCP-backed agent skill · v4.10.0 · MIT · Install · Migrate from Keystone · Skill spec

**An independent, reusable capability.** Tamheed is vendor-, provider-, and stack-neutral and carries no domain assumptions from any particular project — it is meant to be reused on *any* project. It targets **Claude Code** as the downstream execution agent; the plans it produces carry no vendor or stack lock-in. This repository is the home of the Tamheed capability itself, not of any project Tamheed happens to plan.

What Tamheed is

Tamheed at a glance: a project brief flows through Understand, Explore, and Plan & hand off (with human gates) into an execution-ready package that Claude Code executes, writing progress back — all on top of the MCP server, the only write path, backed by SQLite ⇄ JSONL

Tamheed is a reusable agent **skill** that transforms a long-form project description into a complete, internally consistent, **execution-ready handoff package**: the planning, research, architecture, governance, and execution artifacts Claude Code needs to implement the project with discipline.