Loading...
Loading...
Found 2,424 Skills
Autonomous ML experimentation framework by Andrej Karpathy. AI agent autonomously modifies train.py, runs 5-minute GPU experiments, evaluates with val_bpb, and commits only improvements via git ratcheting — so you wake up to 100+ experiments and a better model. Use when setting up autoresearch, writing program.md directives, interpreting results, configuring hardware, or running overnight autonomous ML experiments. Triggers on: autoresearch, autonomous ml experiments, overnight gpu experiments, karpathy autoresearch, train.py experiments, val_bpb, program.md research directives, ai runs experiments.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Check if a newer version of groove is available on GitHub.
Install groove's Claude Code native shell hooks into .claude/settings.json. Enables deterministic session-end reminders, git activity capture, and managed-path protection.
Publish a workflow learning to the groovebook shared commons as a GitHub PR. Use after groove-work-compound when a learning is worth sharing.
Install a rich Claude Code statusline into ~/.claude/hooks/ and ~/.claude/settings.json. Displays model, git context, token usage, effort level, 5h/7d usage limits, and active /loop count with next-fire time.
Install groove's Cursor native hooks into .cursor/hooks.json. Enables compaction-safe re-priming, session-end reminders, git activity capture, and managed-path protection.
Run a simulated meeting with multiple expert personas to analyze a subject from diverse perspectives, reach a decision, and propose a solution before implementation. Optionally posts the meeting analysis to a linked GitLab or GitHub issue.
Review local git changes and perform a light code review. If no issues are found, commit the changes. Does NOT write or modify code — only reviews and commits. Optionally accepts a commit message header as an argument.
Download and install Claude Code skills from various sources. Supports GitHub repositories, compressed archives (.zip, .tar.gz, .skill), and direct URLs. Use when user wants to download, install, or add a skill from GitHub, URL, or archive file. Triggers on "download skill", "install skill", "add skill from", "get skill".
Configures and customizes Claude Code statuslines with multi-line layouts, cost tracking via ccusage, git status indicators, and customizable colors. Activates for statusline setup, installation, configuration, customization, color changes, cost display, git status integration, or troubleshooting statusline issues.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.