Loading...
Loading...
Found 1,195 Skills
Create a new task in the configured backend.
Browse and review open learning PRs in the configured groovebook repo. Use to participate in the shared groove commons.
Publish a workflow learning to the groovebook shared commons as a GitHub PR. Use after groove-work-compound when a learning is worth sharing.
Log a workflow mistake, fix its root cause, and graduate the lesson to learned memory. Use when the agent makes an error you want to prevent recurring.
Graduate a workflow insight from learned/<topic>.md into AGENTS.md as a permanent constraint. Use when a lesson is stable enough to apply to every future session.
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.
Create and manage Obsidian notes for projects, companies, technical challenges, brag documents, daily logs, AI conversations, and quick captures using the Obsidian CLI. Use when documenting projects, tracking job applications, recording interview challenges, maintaining brag documents, creating daily notes, or saving AI conversations. Triggers on "create project", "new project note", "document company", "job application", "technical challenge", "brag document", "daily note", "today's log", "obsidian note", "save conversation", "chat summary", "session summary", "save this", "capture this", "quick note".
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
Use DingTalk Workspace CLI (dws) to manage DingTalk contacts, calendar, todos, attendance, approvals, and more from the command line or AI agent workflows.
GitHub data collection patterns for workflow agents. Covers search query construction by intent, date range handling, repository scope narrowing, preferences.md integration, cross-repo intelligence, parallel stream collection model, and auto-recovery for empty results. Use when building agents that search GitHub for issues, PRs, discussions, releases, security alerts, or CI status.