Spielewoy/autoprompt-skill

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

What it solves

Autoprompt is designed to reduce failures in AI-driven coding tasks. It addresses the problem of coding agents often making mistakes or failing to verify their own work, which typically requires the user to manually prompt the agent at every step to fix errors.

How it works

It implements a multi-layered agent workflow that separates coordination, management, execution, and independent judgment. Instead of a single agent doing everything, Autoprompt uses a hierarchy of agents (run coordinators, workers, and independent checkers) to ensure that work is reviewed, fixed, and rechecked before completion.

Users can choose different "work paths" to control the level of planning: direct for focused work, light for a short plan, and roadmap for organizing dependent work. It supports a wide range of providers (such as Claude Code, Codex, and DeepSeek) and allows users to control concurrency limits to manage parallel work.

Who it’s for

Developers who use AI coding agents and want to higher success rates for complex tasks like fixing bugs, building new features, or performing codebase research without having to manually guide the agent through every iteration.

Highlights

  • Reduced Failure Rate: Claims a 45% reduction in failures on Terminal-Bench 2.1 benchmarks.
  • Multi-Agent Hierarchy: Prevents agents from planning, approving, and verifying their own work through structural separation.
  • Independent Verification: Every work path includes a verification step to ensure the goal is met.
  • Broad Provider Support: Compatible with 11 different coding agent providers including Claude Code, Codex, and Grok Build.

Related

  • Project
    vercel-labs/skills

    A CLI that discovers, installs, updates, and runs reusable prompt bundles (“skills”) for many AI coding assistants (Claude Code, Cursor, OpenCode, etc.), pulling them from any Git repository or direct URL.

  • Project
    legeling/PromptHub

    A local-first workbench for managing and distributing AI prompts, skills, and programming rules across multiple AI coding tools like Cursor and Claude Code.

  • Project
    darkrishabh/agent-skills-eval

    agent‑skills‑eval is a TypeScript/Node.js CLI + SDK that runs an Agent Skill both with and without its `SKILL.md` context, grades the two outputs with a separate LLM judge, and produces JSON artifacts plus a static HTML report. It supports OpenAI‑compatible APIs, custom providers, tool‑call assertions, and full agentskills.io spec validation, making it suitable for skill development, CI testing, and comparative analysis.

  • Project
    Significant-Gravitas/AutoGPT

    AutoGPT is an open‑source platform for building, deploying, and managing autonomous AI agents. Users can describe a goal in plain English or assemble a workflow visually; the system creates an LLM‑driven agent that interacts with 45+ integrations (Gmail, Slack, GitHub, etc.) to complete tasks such as drafting reports, triaging incidents, or generating marketing copy. The project offers a paid hosted service and a free self‑hostable Docker appliance, with the core platform under a Polyform Shield license and the classic agent code under MIT.

  • Project
    CyberStrikeus/CyberStrike

    CyberStrike is an open‑source AI agent that turns any LLM (Claude, GPT, Gemini, etc.) into an autonomous penetration‑testing platform. It adds a security‑focused “intelligence layer”, ships 13+ specialised agents and 7,600+ signed security‑skill files, supports 150+ AI providers (including offline models), and can orchestrate real tools locally or on remote Bolt servers. A TUI, optional web UI, and built‑in HackBrowser complete the workflow.