Loading...
Loading...
Found 13,656 Skills
Use when the user invokes $nerd-memory (Codex) or /nerd-memory (Claude/Cursor), or when Nerd Smart auto-enables it to learn, recall, inspect, deny, refine, correct, split, or forget recurring goal, task, action, result, boundary, verification, or agent-skill-tool-MCP routing patterns across tasks.
Use when explicitly invoked, when reducing agent-workflow cost, or when a concrete deliverable requires no narration, final only, code only, findings only, or minimal output.
Create, improve, or audit Vapi voice agent and Squad system prompts for production phone and web based voice agents. Use when the user wants help designing a Vapi assistant prompt, multi-assistant Squad prompt set, refining an existing prompt, creating prompt sections, building an intake or handoff workflow, improving tool-use instructions, adding guardrails, or optimizing voice-agent behavior for brevity, turn-taking, error handling, caller data collection, escalation, handoffs, and spoken formatting.
Render independent questions in an Agent workflow into a local interactive form, mark recommended answers, collect optional supplementary notes for each question, save responses as portable JSON, and return the submitted results directly to the waiting Agent command. Suitable for grill-me, grill-with-docs, brainstorming, requirement clarification, configuration, planning, and any workflow requiring user confirmation or question collection; explicitly call Ask UI when a round contains more than two questions. When a user says "submitted", "done submitting", or "finished answering" during an Ask UI round, follow this skill's manual recovery path.
Used for installing, updating, reinstalling or repairing the official qiqi, OAuth authorization, or separately accessing Qiqi Skills for the current Agent. Verify CLI, authorization, continuous invocation and Skills results respectively; test environment, joint debugging or acceptance are handled by internal test runtime adaptation.
WAVES — Workers · Aggregate · Verify · Extend — wave-based orchestration for Cursor. Decompose a big goal into independent slices, fan them out to isolated parallel subagents via parallel Task tool calls as a bounded "wave", verify each structured handoff, then synthesize, and extend into another wave only when warranted. Invoke explicitly with /waves; bounded by design to avoid runaway token loops. For big research, analysis, audits, and codebase or data exploration where one linear pass is slow. Formerly parallel-orchestrate; also fan out, parallelize, orchestrate subagents, multi-agent.
Set up, adopt, refresh, or audit a repository's agent instructions (the AGENTS.md block) so AI agents work well in that repo. Also records observed agent mistakes as pitfalls. Use when invoked by name
Accept a vague instruction, automatically conduct investigation, classification, break it down into XML phase plans, select skills, define completion criteria, then execute it fully in unattended mode via loop/goal + agent-mode — including automatic deployment, automatic E2E testing, automatic code review, without skipping any phases. Activate proactively when the user provides a broad task — such as "fix the bug", "add tests", "optimize performance", "finish this feature", "scan the code", "investigate why XX happens". It also triggers when the user says "autopilot", "auto", "help me plan", "handle it yourself", "run directly", "break it down for me", "don't ask me how to do it". Even if the user doesn't use these keywords, it should activate proactively if the input is clearly an unbroken broad intent. Calling autopilot = authorizing fully automatic unattended execution, no mid-process confirmation required.
Review AI-agent-implemented code specifically, in four ordered passes for convention-fit, agent-slop signatures, requirement-completeness, then correctness, against the working tree or the branch diff, findings ranked by severity and backed by quoted evidence. Use when the user says "review this code", "review my changes", "review this diff", "check the agent's work", "/reviewkit", or wants a self-review of AI-written changes before commit or PR, even if they don't name the passes.
Security-first skill vetting for AI agents. Use before installing any skill from community, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Deploy an agent built with the eve framework (eve.dev / Vercel) onto Zavu, or import it straight from GitHub with `npx zavudev import`. Use this skill when the user has an eve-layout project (agent/instructions.md, agent/tools/*.ts) and wants it answering on Zavu's messaging channels, or asks whether an eve capability works on Zavu.
Multi-agent shared blackboard: The current directory is .yomi/boards/<feature>.md, one board per feature, allowing parallel agents/subagents under the same feature to see each other's tasks, progress, and findings. Use when multi-agent collaboration requires peer visibility, sharing progress/findings, wanting to know what peers are doing before starting work, or when terms like "blackboard / board / peer progress" are mentioned. Task assignment/sign-off/state machine/acceptance are handled via task-tickets, not blackboard.