Loading...
Loading...
Found 2,983 Skills
Guide users through creating high-quality GitHub Copilot prompts with proper structure, tools, and best practices.
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.
Interact with GitLab via the glab CLI. Primary use case is MR review — fetches the diff, runs parallel code review + security review via specialist agents, then posts the result as a Thai comment on the MR. Also supports listing MRs, viewing MR status, checking CI/CD pipelines, approving MRs, and other glab operations. Trigger whenever the user provides a GitLab MR URL or says anything like "review MR", "ช่วย review MR นี้", "ดู MR ให้หน่อย", "review https://gitlab.../merge_requests/42", "check pipeline", "list open MRs", or any GitLab-related task.
Use this skill when generating AI-agent-friendly documentation for a git repo or directory, answering questions about a codebase from existing docs, or incrementally updating documentation after code changes. Triggers on codedocs:generate, codedocs:ask, codedocs:update, "document this codebase", "generate docs for this repo", "what does this project do", "update the docs after my changes", or any task requiring structured codebase documentation that serves AI agents, developers, and new team members.
Triage GitHub issues through a label-based state machine with interactive grilling sessions. Use when user wants to triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
Post-task review. Extract learnings, classify, write to memory layers, and reconcile GitHub issues.
Use this skill when the user asks to commit code, create a commit, or save changes to git
Orchestrate same-repository GitHub issue work from branch setup through local review and PR readiness. Use when the user invokes `/develop-issue #123`, `/develop-issue https://github.com/<owner>/<repo>/issues/123`, or asks to develop exactly one issue end to end.
Creates and executes one coherent git commit from staged or selected working-tree changes. Use when the user asks to commit changes, stage and commit a logical change, or create a git commit with an appropriate message. Do not use for a draft-only message request or an operation that only pushes existing commits.
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders.
Build comprehensive GitHub Actions workflows for CI/CD, testing, security, and deployment. Master workflows, jobs, steps, and conditional execution.