dundas

29 mods across 2 repositories, 1 stars between them.

thinkbrowse-cli

01

dundas/thinkrun

Skill Claude CodeCodex

Control browsers via the ThinkBrowse CLI (the thinkbrowse / thinkrun command) — navigate pages, interact with elements, extract content, take screenshots. Use ONLY when the user explicitly names the thinkbrowse or thinkrun CLI, or asks to drive the browser from shell scripts / terminal commands. For general browse…

1 1mo ago A 98 tokens original MIT

thinkbrowse-mcp

02

dundas/thinkrun

Skill Claude CodeCodex

Control browsers via ThinkBrowse MCP tools — navigate pages, interact with elements, extract content, take screenshots. Use ONLY when the user explicitly references the thinkbrowse/thinkrun MCP server or its MCP tools. For general browse, scrape, or automation asks that don't name MCP, prefer the web-browse skill. Do…

1 1mo ago A 81 tokens original MIT

ux-audit

03

dundas/thinkrun

Skill Claude CodeCodex

Walk through a product UI as a real user — take screenshots, find broken flows, and produce a structured report with every fix listed. Use when: audit the UI or UX, do a UX review, QA a feature, check if something looks right, verify a user flow or onboarding, walk through a journey, 'is X broken?', 'check how X…

1 1mo ago A 114 tokens original MIT

web-browse

04

dundas/thinkrun

Skill Claude CodeCodex

Browse the web programmatically with ThinkRun — drive a real or cloud browser to navigate, interact, extract, and screenshot, from the CLI or any MCP client. Use when: visit or open a URL, check a webpage, interact with a browser, verify something works live, take screenshots of a page, scrape or extract content…

1 1mo ago A 96 tokens original MIT

thinkrun

05

dundas/thinkrun

MCP server Claude CodeCodexCursor

Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome. Runs locally from the @thinkrun/mcp npm package.

1 1mo ago A tokens not measured original MIT

coach

06

dundas/liveport

Agent Claude Code

Adversarial critique agent that validates implementation against requirements. Never implements; only validates, questions, and requires proof.

0 5mo ago A 25 tokens

config-task-writer

07

dundas/liveport

Agent Claude Code

Generate step-by-step configuration/installation/deployment tasks from an implementation plan, with prerequisites, deterministic commands, validation, and rollback.

0 5mo ago A 31 tokens

dundas/liveport

Agent Claude Code

Break down high-level goals into minimal, verifiable sub-tasks with clear dependencies, checkpoints, and acceptance criteria.

0 5mo ago A 28 tokens

dundas/liveport

Agent Claude Code

Validate features work end-to-end in production conditions. Never mark complete until the full user flow works.

0 5mo ago A 23 tokens

dundas/liveport

Agent Claude Code

Implement safety-critical features with focus on edge cases, constraints, error handling, and defensive programming.

0 5mo ago A 25 tokens

spec-writer

11

dundas/liveport

Agent Claude Code

Write precise specifications (OpenAPI, contracts, interface specs) from PRDs and plans with examples and constraints.

0 5mo ago A 26 tokens

tdd-developer

12

dundas/liveport

Agent Claude Code

Implement tasks with a strict red→green→refactor test-first workflow and small, reviewable commits.

0 5mo ago A 26 tokens

technical-planner

13

dundas/liveport

Agent Claude Code

Turn a decomposed plan into a concrete technical approach, selecting patterns, modules, and interfaces that fit the repo.

0 5mo ago A 27 tokens

dev-pipeline

14

dundas/liveport

Command Claude Code

Run the Windsurf workflow /dev-pipeline. If not in Windsurf, follow skills/generate-workflow-tasks.md to orchestrate PRD → tasks → processing with confirmation gates.

0 5mo ago A 0 tokens

dialectical

15

dundas/liveport

Command Claude Code

Run dialectical autocoding for the specified task or feature.

0 5mo ago A 0 tokens

generate-tasks

16

dundas/liveport

Command Claude Code

Run the Windsurf workflow /generate-tasks. If not in Windsurf, follow skills/tasklist-generator/SKILL.md to generate parent tasks (pause), then sub‑tasks and "Relevant Files", and save to /tasks/tasks-[prd-file-name].md.

0 5mo ago A 0 tokens

prd-writer

17

dundas/liveport

Command Claude Code

Run the Windsurf workflow /prd-writer. If not in Windsurf, follow skills/prd-writer/SKILL.md to create a PRD and save to /tasks/[n]-prd-[feature-name].md.

0 5mo ago A 0 tokens

process-tasks

18

dundas/liveport

Command Claude Code

Run the Windsurf workflow /process-tasks. If not in Windsurf, follow skills/task-processor/SKILL.md to process one sub‑task at a time with pause/confirm gates and test/commit protocol.

0 5mo ago A 0 tokens

dundas/liveport

Skill Claude CodeCodex

Guides Claude Code through a structured, four-phase workflow to extract a visual style from a reference UI screenshot and codify it into a reusable design system for this project. It.

0 5mo ago A 0 tokens

dundas/liveport

Skill Claude CodeCodex

Build or update frontend components and pages that strictly adhere to the project design system defined in design/design-system.json (and design/design.json when present).

0 5mo ago A 34 tokens

dundas/liveport

Skill Claude CodeCodex

Orchestrate PRD creation, task generation, and gated task processing with user confirmations between phases.

0 5mo ago A 27 tokens

dundas/liveport

Skill Claude CodeCodex

Orchestrate adversarial player-coach loop for high-quality code synthesis. Based on dialectical autocoding methodology.

0 5mo ago A 29 tokens

dundas/liveport

Skill Claude CodeCodex

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

0 5mo ago A 45 tokens

prd-writer

24

dundas/liveport

Skill Claude CodeCodex

Create a clear, actionable PRD with clarifying questions and a junior-friendly structure.

0 5mo ago A 21 tokens