Recently added agent tools.

An advanced data-science skill for debugging and analyzing a-b-testing experiments through visualization, modeling, and statistical validation.

A skill for performing intermediate-level estimation and predictive modeling in a-b-testing using statistical analysis and data-science best practices.

An AI skill for applying classification techniques and visualizing data in A/B testing, supporting hypothesis testing and predictive modeling for data-driven decision making.

An intermediate-level data-science skill specializing in a-b-testing analysis, enabling hypothesis testing, outcome prediction, and data visualization for research and industry applications.

An AI skill that performs fundamental-level calculations and analyses for a-b-testing data, including data visualization and predictive modeling, designed for research and industry applications.

A B Testing Based Characterization Skill provides research-level expertise in performing characterization and visualization related to a-b-testing methodologies for data-science applications.

An advanced AI skill for performing research-level statistical analysis and visualization in A/B testing to support data-driven decision making.

An advanced AI skill for performing research-level statistical analysis and visualization in A/B testing using machine learning frameworks.

A tool that manages and provisions cloud infrastructure using declarative, version-controlled configuration files with support for Terraform, Pulumi, AWS CDK, and similar frameworks.

An AI skill for performing fundamental-level A/B testing analysis, including hypothesis testing, feature extraction, and outcome prediction using data-science best practices.

An AI assistant designed to support software engineering tasks such as coding, debugging, and managing codebases.

A tool focused on designing, optimizing, and troubleshooting 3D printing and additive manufacturing processes for prototyping and production.

1Password CLI enables secure management and automation of password vaults and secrets via command-line interface within development environments.

Qgoal is a tool for creating and managing explicit single-goal plans within a broader planning framework, ensuring formal verification and execution aligned with client goals.

Qupdate is a developer tool that updates QE framework components, plugins, marketplace metadata, and synchronization assets via command-line interface.

Qplan is an AI agent tool designed to manage and advance project plans by intake of knowledge, creating and updating roadmaps, and verifying goals one at a time to ensure structured progress.

Qversion is a developer tool that displays the current version of the QE Framework plugin to users upon request.

Qresume is an automation tool that restores and resumes previous work sessions by loading saved context and session state after breaks or compactions.

Qcritical-review is a Dev Tools AI agent that performs adversarial verification and critical thinking evaluation at various software development stages to stress-test specifications, implementations, and readiness for merging.

Qexecute is a unified execution engine that automates the controlled execution and quality verification of routed pipeline tasks based on detailed task specifications and dependencies.

Qdashboard provides a local read-only dashboard to inspect and visualize the state of the QE project database including tasks, sessions, and verification results.

Qgenerate-spec is an internal document generation tool for transforming project roadmap phases into detailed task request and verification checklist documents within a project planning ecosystem.

Qcompact is an automation tool that preserves session context and manages session handoffs by saving snapshots and generating detailed handoff documents automatically under context pressure or upon user request.

Qcc-setup manages installation and inspection of safe shell shortcuts (aliases) for Claude Code and Codex command-line tools across various shells, ensuring user confirmation and preserving existing configurations.

QcommitViolation is a development tool for generating git commits while enforcing specific commit policies.

A test fixture tool designed to detect Korean-inversion exploits in commit message policies to enforce proper commit rules.

Qcommit is a tool that generates natural, human-style git commit messages and automates the staging and committing process without any AI-attributable traces.

QcommitViolationPreHeading is a test fixture tool designed to detect forbidden phrases in commit messages, ensuring compliance with commit policies during development.

An AI agent that automates git commit creation ensuring compliance with project commit policies and natural messaging without AI traces.

A tool that checks for naming mismatches between the name field and directory name to ensure consistency in development.

quoted-name is a developer tool that ensures correct YAML scalar formatting for quoted names and descriptions.

Good-skill is a developer tool that ensures control fixtures are properly named and documented for valid testing setups.

no-frontmatter is a developer tool designed to work without requiring YAML front matter in SKILL.md files.

This tool appears to be a placeholder or test agent designed to validate input requirements, particularly checking for empty name violations.

dupe is a development tool designed to identify and handle duplicate skill names to prevent naming conflicts.

Qissue streamlines creating, reviewing, and filing GitHub issues by integrating with the GitHub CLI while ensuring secure authentication and content sanitization.

An AI tool designed to perform tasks automatically, though its description is not provided.

Shipmail-mcp is a Model Context Protocol server for Shipmail, providing email services with REST API, webhooks, and custom-domain inboxes designed for AI agents in business operations.

An AI tool that automates the creation of MCP-Use applications with a single command.

Comprehensive marketing expertise combining campaign execution, strategy frameworks, psychological principles, and 140+ marketing tactics. Use when planning campaigns, developing content strategy, applying behavioral science, generating marketing ideas, or building go-to-market strategies. Covers email, social, SEO, paid ads, content, and psychology-driven optimization.

网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。

Local-first memory, hybrid RAG, and agent personalization for AI coding agents (OpenCode, Claude Code, Codex, Gemini CLI, Antigravity). MCP server + CLI with persistent context, document ingestion, vector + SQLite FTS5 retrieval, sync, setup, and safe uni

|

Interactive API key configuration guide — checks current .env state and walks you through Semantic Scholar, DeepXiv, and Review LLM setup

Use when creating or refining WebGL-heavy landing pages and you need to steer toward a specific visual outcome (premium, technical, playful, cinematic) while balancing conversion clarity, performance, and implementation complexity.

Comprehensive project planning standards for plans/ directory including folder structure (ideas/, backlog/, in-progress/, done/), stage-aware naming convention (done uses YYYY-MM-DD__identifier/; backlog and in-progress use identifier/ with no date prefix), five-document file organization (README.md, brd.md, prd.md, tech-docs.md, delivery.md for multi-file default; single README.md for trivially-small single-file exception), BRD/PRD content-placement rules, Gherkin acceptance criteria, and the m

Designs and maintains build tooling — bundlers (Vite, Webpack, Rollup, esbuild, Parcel, tsup), package managers (npm, pnpm, yarn, Pipenv, Poetry, uv), lockfile hygiene, pre-commit hooks, runtime pinning, build cache, module resolution, monorepo workspaces, reproducibility. Audits for non-deterministic builds, lockfile drift, mixed package managers, unpinned runtimes, broken caches, and hooks that mutate without staging. Use when adding a bundler, switching package managers, debugging slow or non

Planu — MCP Server for Spec Driven Development with native Rust acceleration for hot paths. Cross-platform (Linux/macOS/Windows, x64/arm64, glibc/musl).

Your AI writes code that doesn't exist. Tribunal Kit stops it. The governance layer for AI coding agents — 52 specialists, 28 parallel reviewers, 183 skills, Rust core, MCP server. Works with Cursor, VSCode, Windsurf, Claude Code, and Aider.

Model Context Protocol (MCP) server for Firefox DevTools automation