Loading...
Loading...
Found 10,429 Skills
Use this skill when automating LinkedIn tasks via Rube MCP (Composio): create posts, manage profile, company info, comments, and image uploads. Always search tools first for current schemas.
Check for and apply updates to installed skill branches from upstream.
Automatically resolve merge conflicts in the current PR. Fetches the base branch, attempts a merge, identifies conflicting files, analyzes both sides, resolves conflicts, verifies locally, and pushes. Use when PR has merge conflicts detected by poll-pr-status.sh.
What are crypto funds and VCs holding right now? Cross-chain fund portfolios and net accumulation signals.
Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Supports push-only (webhook) and interactive (bidirectional) modes. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.
Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
Use KWC CLI (kd) to translate user requirements into deliverable KWC projects, components, page metadata, environment configurations, deployment and debugging results. This Skill is used when an Agent needs to initialize or extend a KWC project via scaffolding, split functions into KWC components, create or update *.page-meta.kwp, configure kd env, deploy metadata to the target environment, or guide the full process from requirements to KWC page rendering.
Perses project lifecycle management: create, list, switch, and configure projects. Manage RBAC with roles and role bindings per project. Uses MCP tools when available, percli CLI as fallback. Use for "perses project", "create project", "perses rbac", "perses roles", "perses permissions". Do NOT use for dashboard creation (use perses-dashboard-create).
Persistent markdown files as working memory for complex tasks: plan, track progress, store findings. Use when tasks have 3+ phases, require research, span many tool calls, or risk context drift. Use for "plan", "break down", "track progress", "multi-step", or complex tasks. Do NOT use for simple lookups, single-file edits, or questions answerable in one response.
Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.
Creates missing instruction files (CLAUDE.md, AGENTS.md, GEMINI.md), audits token budget, prompt cache safety, cross-agent consistency. Use after setup or when instruction files need alignment.
Use when addressing open PR review comments from any reviewer (human or bot) within the current agent session. For a fresh-context-per-comment approach, use ralph-wiggum-loop instead.