Dot Cowork — AI skill for Claude Code
Reusable AI–human collaboration frameworks for project‑level context engineering.
How to install Dot Cowork
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lim8603/dot-cowork and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Dot Cowork does
Reusable AI–human collaboration frameworks for project‑level context engineering.
Alternatives in AI
- Context Engineering Agent Skills — Context engineering patterns for agent skills 13.9k ★
- Context Engineering Intro — GitHub Repo stars Context engineering - the new way of AI coding assistants Context engineering guide 12.8k ★
- Omnara — by Ishaan Sehgal - A command center for AI agents that syncs Claude Code sessions across terminal, web, and mo 2.6k ★
README
Cowork Context Framework
[](https://github.com/lim8603/cowork-context-framework/releases/latest)
A project-level context framework for AI-Human collaboration across sessions, tools, and project phases.
AI chat is disposable. Project context should not be.
This framework stores intent, requirements, design decisions, implementation notes, verification records, and delivery artifacts as structured files in the repository so work can survive session boundaries, tool switches, and project handoffs.
The new `cowork-context-framework` repository starts from a clean `1.x.x` baseline. `frameworks/ko` remains the Korean authoring baseline, and `frameworks/en` is the published English install variant kept on the same release line.
Why This Exists
AI tools lose working memory when a session ends.
- Decisions agreed on yesterday often need to be re-explained today.
- The reason behind "why was this done this way?" disappears into chat history.
- Switching tools usually means rebuilding project context from scratch.
This framework keeps that context in persistent files so any compatible tool can restore the project state and continue from where the previous session stopped.
Key Features
- Tool-agnostic: Codex, Cursor, Claude Code, Gemini, and Copilot can all read the same
.cowork/workspace. - Structured lifecycle: The workflow follows Define -> Design -> Build -> Verify -> Evolve -> Deliver.
- Persistent project memory: Intent, milestones, ADRs, tasks, and session logs stay in versioned files instead of chat history.
- Progressive enrichment: Important details are harvested into the right documents as work proceeds.
- Verification evidence index: Review, test, NFR, and release-readiness evidence can accumulate in a dedicated canonical verification document.
- Quality gates: Phase transitions can check for missing artifacts before the
Related Skills
Aria Knowledge
Applied reasoning, persistent agent memory, context engineering, and human-governed trust for AI coding agents
Stack Ia Dev
Tool-agnostic AI software engineering stack: deterministic safety guardrails, project-context profiling, multi
Context Engineering Protocol
Portable AI coding-agent skills for source-attributed, human-approved context packages.
Claude Equity Research Skills
Institutional-quality equity research skills for Claude AI — systematizing the fundamental analysis playbook f
TencentDB Agent Memory
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into f
LLM Base Prompts
Collection of LLM system prompts, agentic personas, cognitive frameworks & prompt engineering experiments
Related Agents
Creator Book Writer
Genre master for creator economy, AI-human collaboration, and generative creator empowerment books - leads vis
Prompt Engineering Expert
Designs, improves, converts, debugs, and operationalizes prompts, system prompts, agent instructions, and reus
Senior Code Architect
Use this agent when you need expert-level code review, architecture decisions, or framework guidance. This age