Webapp Testing
A portable Playwright workflow for verifying local web apps, debugging UI behavior, and capturing visual evidence.
Category · 27 plugins
Reviewed Testing Agent Plugins with source provenance, installation guidance, repository README snapshots, and safely rendered plugin documentation.
A portable Playwright workflow for verifying local web apps, debugging UI behavior, and capturing visual evidence.
Epistemic message composer with 30 Bayesian rationality criteria (LessWrong Sequences). Socratic interview before writing, draft generation with epistemic diagnosis, 4-tier scoring from recipient's perspective. Supports any message type (email, Slack, WhatsApp, etc.). Companion tool to email-triage: one filters what you receive, the other optimizes what you send.
Build, run, debug, profile, and ship Apple 27-era apps across macOS, iOS, iPadOS, watchOS, tvOS, and visionOS with Swift, SwiftUI, Xcode 27, and XcodeBuildMCP.
Extrae las skills de un repositorio con un plugin de Claude, audita su portabilidad y las empaqueta para ChatGPT, Perplexity Computer y Mistral Vibe Work. Conforme a Agent Plugins 1.0.0.
Connect your agent to CloudPeek, the AI security teammate. Triage the 5% of alerts that matter, run investigations, and manage incidents through the hosted CloudPeek MCP gateway.
Experimental Codex workflow for planning, bounded delegation, review, and verification.
End-to-end guidance for full-stack applications, from focused context, requirements, and planning through architecture, data, APIs, source-verified implementation, React and frontend delivery, and launch.
Safe, automated GitHub releases with supply chain security. Prevents dangerous gh release commands, orchestrates version bumps, signed tags, and CI-driven releases across ecosystems (TYPO3, PHP, Node.js, Go, Python, Rust, skill repos).
Drive the Godot engine over the published @coding-solo/godot-mcp server: launch its own headless Godot to open the editor, run projects in debug mode, inspect scene and project structure, edit scenes and nodes, and stream back runtime errors and debug output. It does not attach to an already-open editor — point it at your Godot 4 executable and iterate.
A full Google Cloud delivery team for your coding agent: vendor-objective solution designer, GCP architect, agentic-systems architect (ADK / Agent Runtime / MCP / A2A / AP2), plus security, SRE, and QA — wired into a design-first, security-first delivery gate. Eleven service skills (Cloud Run, GKE, IAM, BigQuery, Cloud Storage, Vertex AI, networking, observability), MCP server setup, and a self-validating research pipeline that keeps every reference current.
Production-grade Go programming skills for AI coding agents.
Agent Skills for academic paper work: training-pipeline diagnosis, drafting and review, publication figures, and getting a manuscript through a journal — source, packet, and response to reviewers.
Run AI-Readiness and Marketing Signal website scans from your coding agent, read prioritized findings, and apply fixes with a re-scan for proof.
Agent-safe version control with Jujutsu (jj): jj as the local change layer, Git as the canonical remote/PR/CI/audit interface
Patent mining and invention disclosure workflows on Lightbringer: harvest patentable problem-solution pairs from company data, author and submit disclosures, and handle report and priority-draft reviews.
End-to-end smoke test for Agent Skills and MCP loading in Pi.
Generates a consistent pull request (or merge request) title and description from the commits on the current branch, and provides a ready-to-use creation link for Azure DevOps, GitHub, or GitLab.
Audit crawler-visible HTML and discovery files with local Prerender Buddy MCP tools.
Read-only repository audit for choosing between a rebuildable remote-agent task and a persistent development workspace.
LLM-driven session retrospection. Detects friction in agent sessions and materializes learnings into correct destinations (user memory, project rules, skill PRs, checkpoints, harness artefacts).
Project-agnostic security skills for repository audits, diff review, deterministic scanning, supply chain, threat modeling, smart contracts, and AI systems.
Seudonimiza casos clínicos y jurídicos para estudio, supervisión o formación: conserva la utilidad analítica y elimina identificadores directos, reduciendo los indirectos hasta un nivel auditado. Cuatro modos (clínico, jurídico, generalización extrema y auditoría). No sustituye la anonimización formal que exigen el RGPD y la LOPDGDD.
Software development skills: deep planning, root-cause analysis, agent-oriented repo docs, spec-aware rebasing, and PR review.
Risk-first PR/branch review: blast radius, agent-authored checks, call-graph pincer, structure.
Operate a live Unity Editor over MCP: build scene hierarchies, add components, author C# scripts, manage assets, and smoke-test in Play Mode. The bundled skills' guardrails stop a build from wiping its own scene.
Operate a live Unreal Editor over MCP through Unreal Engine 5.8's native in-editor MCP server: spawn actors, build and compile Blueprints, compose levels, configure lighting, inspect Slate widgets, and run automation tests. Connects to the editor's local HTTP endpoint — no third-party server to install. The bundled skills lean into list-first, compile-then-spawn discipline because editor writes silently no-op more than any other DCC.
Gates every Edit/Write in this session against vord's Agent Permission Policy (vord-policy.toml) before the bytes reach disk.