Skill Detail

Run Autoprompt coordination loops across coding agents

Use Autoprompt when an operator wants a coding agent to turn one goal into a planned, delegated, reviewed, and verified execution loop across supported agent runtimes.

Developer ToolsMulti-Framework
Developer Tools Multi-Framework Security Reviewed
โญ 293 GitHub stars โฌ‡ 122/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill run-autoprompt-coordination-loops-across-coding-agents Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
Node.js 20+, Python 3.11+ with PyYAML exposed as python, Bash 4.3+ on macOS or Linux, Git for source checkout installs, and one supported coding-agent runtime such as Claude Code, Codex, OpenCode, Kilo Code, VS Code Copilot, or Prime Agent
Install & setup
Install with npm install -g autoprompt-skill, run autoprompt, choose the target coding agent, confirm its path, and install. After installation, invoke /autoprompt in supported slash-command hosts or $autoprompt in Codex, optionally adding controls such as mode=wide or agents= where the host supports them.
Author
Spielewoy
Publisher
Individual
Last updated
Aug 20, 2026
Quick brief

Use Autoprompt when the operator has a coding task that needs more structure than a single ad hoc prompt. The workflow is concrete: install the Autoprompt CLI, choose a supported coding-agent provider, invoke /autoprompt or $autoprompt with a goal, set controls such as mode= and agents= where supported, and let the installed skill coordinate planning, implementation lanes, independent review, tests, repair, and sign-off. Invoke this instead of using the product normally when the user wants a repeatable maker-checker operating loop for larger coding tasks, not just a direct conversation with Claude Code, Codex, OpenCode, Kilo Code, VS Code Copilot, or Prime Agent. The scope boundary is coding-agent workflow orchestration inside already installed agent runtimes; Autoprompt is not a generic CLI listing, model provider, benchmark claim, or standalone development environment.

How it works

What this skill actually does

Inputs and prerequisites: Node.js 20+, Python 3.11+ with PyYAML exposed as python, Bash 4.3+ on macOS or Linux, Git for source checkout installs, and one supported coding-agent runtime such as Claude Code, Codex, OpenCode, Kilo Code, VS Code Copilot, or Prime Agent.

Setup notes: Install with npm install -g autoprompt-skill, run autoprompt, choose the target coding agent, confirm its path, and install. After installation, invoke /autoprompt in supported slash-command hosts or $autoprompt in Codex, optionally adding controls such as mode=wide or agents= where the host supports them.

Source and verification boundary: use https://github.com/Spielewoy/autoprompt-skill#readme as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.