How do I install the Claude Stack skill?

Run npx skillmds@latest add envoydev/claude-stack in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Claude Stack safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Claude Stack?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Claude Stack free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Claude Stack?

envoydev (@envoydev) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Claude Stack by envoydev — Agent Skill

Name: Claude Stack
Author: envoydev

Claude Stack

Route to the right claude-stack action when unsure which fits - inspects the install state and answers with the exact command to run: /claude-stack:setup (fresh install from scratch), /claude-stack:update (no-questions refresh + prune of upstream removals), /claude-stack:configure (adjust an existing install - add or drop), /claude-stack:validate (reconcile an install against THIS project - prune what its frameworks do not use and add the detected stacks' missing artifacts), /claude-stack:status (read-only per-area tables of what is installed). Trigger by invoking /claude-stack.

envoydev e9f3592 2.3 KB Updated Sep 17, 2026

File contents

/claude-stack - the router

Route by install state, then hand the user the ONE command to run. The five actions are manual-only commands - the user stays at the wheel, so you answer with the command, never run the flow yourself:

Nothing installed here (no populated .claude/skills / .claude/agents, and no global install to target) -> /claude-stack:setup (fresh install from scratch).
The stack is installed and the ask is a plain refresh (no items named) -> /claude-stack:update (refresh everything installed + prune what upstream removed).
The stack is installed and the user wants to adjust it (add or drop items, change the selection) -> /claude-stack:configure.
The stack is installed and the user wants it reconciled TO THIS PROJECT - prune what the project's frameworks do not use (WPF artifacts in a web-only repo, the data vertical with no SQL) AND add the detected stacks' artifacts that are missing -> /claude-stack:validate (project mode only).
The ask is to SEE what is installed - inventory, versions, capture dates, 'what do I have?' - with nothing to change -> /claude-stack:status (read-only tables, per area or all).
The install just finished and the ask is 'what now?' (session reload, gitignore lines, serena setup, which captures in which order) -> not a command: walk them through ${CLAUDE_PLUGIN_ROOT}/references/post-install.md.

Answer with the command plus one line naming the state you found (for example: 'no .claude/skills here - run /claude-stack:setup'). When more than one reading is plausible, put the candidates through AskUserQuestion - one option per plausible command, the likeliest marked Recommended - instead of guessing or asking in prose.

---name: claude-stackdescription: Route to the right claude-stack action when unsure which fits - inspects the install state and answers with the exact command to run: /claude-stack:setup (fresh install from scratch), /claude-stack:update (no-questions refresh + prune of upstream removals), /claude-stack:configure (adjust an existing install - add or drop), /claude-stack:validate (reconcile an install against THIS project - prune what its frameworks do not use and add the detected stacks' missing artifacts), /claude-stack:status (read-only per-area tables of what is installed). Trigger by invoking /claude-stack.---# /claude-stack - the routerRoute by install state, then hand the user the ONE command to run. The five actions aremanual-only commands - the user stays at the wheel, so you answer with the command, never runthe flow yourself:- Nothing installed here (no populated `.claude/skills` / `.claude/agents`, and no global install to target) -> `/claude-stack:setup` (fresh install from scratch).- The stack is installed and the ask is a plain refresh (no items named) -> `/claude-stack:update` (refresh everything installed + prune what upstream removed).- The stack is installed and the user wants to adjust it (add or drop items, change the selection) -> `/claude-stack:configure`.- The stack is installed and the user wants it reconciled TO THIS PROJECT - prune what the project's frameworks do not use (WPF artifacts in a web-only repo, the data vertical with no SQL) AND add the detected stacks' artifacts that are missing -> `/claude-stack:validate` (project mode only).- The ask is to SEE what is installed - inventory, versions, capture dates, 'what do I have?' - with nothing to change -> `/claude-stack:status` (read-only tables, per area or all).- The install just finished and the ask is 'what now?' (session reload, gitignore lines, serena setup, which captures in which order) -> not a command: walk them through `${CLAUDE_PLUGIN_ROOT}/references/post-install.md`.Answer with the command plus one line naming the state you found (for example: 'no `.claude/skills`here - run `/claude-stack:setup`'). When more than one reading is plausible, put the candidatesthrough AskUserQuestion - one option per plausible command, the likeliest marked Recommended -instead of guessing or asking in prose.

Frequently asked questions