Ask about your website traffic, funnels, SEO and AI agent costs. Sign in with OAuth, no key paste.

Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can pe

A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield. EN/ES.

Multi-agent workflows with full observability and time travel: watch every step live, rewind, fork, and replay any run. Claude Code, Codex, Gemini, any model or harness.

deja-vu memory for DeepSeek Harness: the session history of forty-two other coding agents, searchable and recalled before each step — a local index, no LLM.

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 files only. Explicit session-catchup.py --metadata reads same-project local agent

Enables AI agents to build launch websites from a brief or authorized reference, make focused page edits, review saved designs, run pre-share site checks, publish or take down sites at a free name.iter0.app address, and read and reply to canvas comments. Paid steps return a price quote that must be confirmed before any credits are spent.

Session handoffs for Claude Code: skills that capture decisions, failed approaches and next steps, plus a Claude Code mod (/compact-handoff) that replaces the conversation with a validated handoff and keeps going. A better /compact.

Web step blocked? Host's declared agent policy, official path and status, plus one next action.

DeepSeek Harness 的执行迷宫——看 Agent 真实怎么干活：迷宫时间轴 · 数据轨道 · 确定性执行分析 · 多会话对比 | The execution maze for DSH agents: maze timeline, per-step data tracks, deterministic execution analysis, multi-session comparison. Formerly dsh-trace-compare.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

Give an AI a research direction: it runs literature synthesis, gap validation, hypothesis formation and experiment design itself. 267 markdown skills form a research graph: 51 operations built from 216 atomic steps, any order, explicit backtracking; the plan is approved before it runs and interrupted runs resume. npx install, no runtime, no API key

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry

DSH 模型管理层：网关可达性探测、模型目录拉取、DeepSeek + MiniMax/智谱/Moonshot/StepFun 余额与配额、本月用量统计、余额预警、Provider 健康看板，再把本机装好的 codex / claude / agy 注册成子代理（装了才出现）。零运行时依赖，不改动 DSH 安装。

Claude Code plugin for multi-step workflow orchestration — automatic task decomposition, parallel agent execution, and specialized agent delegation with native plan mode integration.

Claude Code scaffolding and first steps for complex brownfield projects

Brainstorm the design with your coding agent, approve it, and it builds. The brainstorming step from Superpowers, for frontier models.

x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

SRE thinking applied to Claude Code, based on Boris Cherny's Q&A. It enforces a strict 4-stage pipeline with gates between each step. You literally cannot skip verification. You cannot ship without approval.

Drives the local Doubao desktop client through its DevTools interface, letting an agent read and send chats, run task-mode work, hand off a project directory and take it back, and call Doubao-only capabilities like image generation and step traces. Also borrows Doubao's built-in skill set for cross-checking and project handoff, with a UI badge showing which side currently owns the work.

Enables agents to reach pump.fun's full API surface — official developer routes, bonding-curve reads, Solana RPC, and unsigned trade building — by writing JavaScript against one merged OpenAPI document, using just two tools (search and execute). Model-authored code runs in a network-less sandbox, so multi-step questions resolve in a single round trip while credentials stay on the host Worker.

Enables AI agents to reach enterprise apps such as Jira, Microsoft 365, Salesforce, FedEx and Dell TechDirect, or your own REST APIs, through a single self-hosted MCP endpoint. Each agent gets its own key with per-app, per-value grants and a confirmation step for deletes, so calls are scoped and audited without exposing app credentials.

Enables agents to execute shell commands and upload/download files on remote Linux hosts over SSH/SFTP with just two tools, returning structured, verifiable results such as exit codes, separated stdout/stderr, timeout and truncation flags, and the current working directory. Supports connection reuse, host alias resolution, host-key verification, and cross-call session state so multi-step work needs fewer calls.