Instructions for theonedev/onedev: Do not add Co-authored-by: or other co-author / AI attribution footers to commit messages unless the user explicitly asks for them. If such a trailer is injected into a commit you just created (and it is not pushed), rewrite the commit message to remove it before finishing.
Claude Code instructions for asklokesh/loki-mode, covering loki mode - claude code skill, quick start, launch claude code with autonomous permissions, then invoke and "loki mode" or "loki mode with prd at path/to/prd".
AGENTS.md instructions for redwoodjs/local-ci, a project described as: Run GitHub Actions locally — pause on failure, retry in place, and keep caches on your machine.
Instructions for gotempsh/temps, covering agents.md, add attribution to every new source file, do not hand-edit changelog.md, use the generated openapi sdk in web/ and restart the server when you change the openapi surface.
Instructions for devopness/devopness, a project described as: Devopness: AI DevOps on your cloud. Deploy apps, infra and CI/CD. Any cloud and any stack, one MCP. Deterministic API, opinionated and fully configurable. No cloud credentials in AI chats. Free plan.
AGENTS.md instructions for RapierCraftStudios/ForgeDock, covering forgedock for codex, codex entry model, runtime rules, scope boundaries and first references.
Instructions for petrkindlmann/qa-skills, a project described as: 50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.
Instructions for limboo-ai/limboo, covering claude.md, 1. what is limboo?, 2. tech stack (current), 3. project structure and the three electron contexts (critical mental model).
Instructions for ThreeMoonsLab/agents-shipgate, covering agents shipgate · agent instructions, what this project is, naming (canonical), install (canonical) and run (canonical).
Instructions for ThreeMoonsLab/agents-shipgate, covering claude code instructions, running the cli in this repository, permissions, output handling and slash command.
Instructions for bhvbhushan/vibecop: When the user's request matches an available skill, ALWAYS invoke it using the Skill tool as your FIRST action. Do NOT answer directly, do NOT use other tools first. The skill has specialized workflows that produce better results than ad-hoc answers.