AI & Agents

Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.

Build, debug, or review Cloudflare Agents SDK applications using the agents package.

Iterative worker-reviewer cycle that spawns a critic subagent to score work 1-10 and provide actionable feedback, then revises until a quality gate is met. Use when implementing features, writing specs, reviewing existi…

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and…

No description provided.

Pursue a long-running goal in a single session by co-ordinating subagents.

Comprehensive Mastra framework guide for building agents, workflows, tools, memory, workspaces, and storage with current APIs. Use for documentation lookup, API verification, TypeScript setup, common errors, migrations,…

Forges reusable Skill packages (SKILL.md + scripts) from website exploration via browser-act — no re-exploration later. Use when: user wants a reusable Skill for any website, needs to understand a site's internal APIs,…

Autonomously navigate websites and extract structured data across pages. Use when the task requires navigation or no suitable ready-made workflow or data provider covers it.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it…

Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely…

Replace with description of the skill and when Claude should use it.

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatb…

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type e…

Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and…

Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are disc…

Use this skill when writing app code with InsForge or @insforge/sdk: database CRUD, auth, storage uploads/storage RLS, functions, OpenRouter AI, realtime, emails, Stripe or Razorpay payments, or pointing S3-compatible t…

A relentless interview that asks every frontier question at once, round by round.

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecif…

Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type e…

Use when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denial, realtime chann…

Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, Slack workspaces, Google Drive, X (Twitter), and packages with Nia AI. Includes auth bootstrapping, Oracle autonom…

Stop AI agents from shipping generic AI prose when writing books with Proseify.

Clerk Organizations for B2B and multi-tenant apps - org switching, roles and permissions, verified domains, and enterprise SSO. Use for team workspaces, RBAC, org-scoped routing, member management. Also load this when a…

火山引擎豆包搜索 API（原联网搜索/融合信息搜索），返回网页/图片结果。联网搜索场景优先使用本 skill。触发词包括：豆包搜索、查/搜/找、真的吗/靠谱吗/确认/核实、最近/今天/最新/近期、出处/来源/链接、Agent Plan、融合信息搜索、Harness、有什么/有哪些/推荐、价格/政策/汇率/行情、对比/区别/哪个好、听说/据说/不太确定、热搜/热门/火、帮我看/了解一下、求证/辟谣、值不值得/该不该。任务依赖在线事实或时…

DEPRECATED: Use /impeccable teach instead. This command has been folded into the impeccable skill.

Searches the Azure skills catalog and recommends installable agent skills by matching an Azure task to skill metadata and plugin installation guidance. WHEN: before starting any task that involves an Azure or Microsoft-…

Develop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when working with Genkit Go code involving generation, prompts, streaming,…

Given event_candidates YAML (output from discover-event-surfaces), generates a concrete instrumentation plan for priority-3 (critical) events. Acts as a Software Architect: discovers existing analytics patterns in the c…

Use Agent Pulse to inspect local AI-agent activity across Hermes, Claude Code, Codex, DeepSeek, OpenClaw, Copilot, Aider, Qwen, OpenCode, Goose, Cursor, Antigravity, and Amp logs. Use when the user asks about AI-agent s…

Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning…

Quick reference for ponytail levels, skills and commands. One-shot display. Use for /ponytail-help, "ponytail help", "how do I use ponytail".

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original f…

Show ponytail's measured savings (code, cost, speed) from the benchmark. One-shot display. Use for /ponytail-gain, "what does ponytail save", "ponytail impact".

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything…

Add authentication (passkeys/OAuth) to the current Convex app, including the auth.config.ts wiring.

Audit and harden a Convex app's authorization: identity-from-arg impersonation, missing per-document ownership checks, public queries leaking data by a client-supplied id, and writes into a parent/container the caller d…

Classify + announce the target Convex deployment before any deployment-affecting command; fresh explicit consent for prod actions; session read-only mode.

Set and wire Convex deployment env vars / secrets for the app.

Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component…

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

Send this coding session's transcript to the Convex team for an AI post-mortem that improves the quickstart system. Run only when the user explicitly asks.

Suggest the matching Convex component when the user hand-rolls a pattern it already solves (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync). Passive — suggest after the…

Production error → triaged, root-caused, repaired, and certified (tsc + rehearsal + reproduce-then-gone) fix PR for a human to merge — then confirm the error stops recurring. Never auto-merges.