All authors
Claude Skills by dundas
github.com/dundas6 skills0 installs3 views
- Thinkbrowse CliControl 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, scrape, or automation asks that don't name the CLI, prefer the web-browse skill. Do NOT use for simple URL fetching (use WebFetch tool instead).Votes: 0GitHub stars: 2
- Thinkbrowse McpControl 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 NOT use for simple URL fetching (use WebFetch tool instead).Votes: 0GitHub stars: 2
- Ux AuditWalk 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 works'. Do NOT use for: proving that a specific change works with pass/fail evidence for a PR, fixing a specific known bug, reading a component's code, deploying, writing tests, or an...Votes: 0GitHub stars: 2
- Web BrowseBrowse 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, take screenshots of a page, scrape or extract content, automate a browser task. Do NOT use for structured UX audits with scoring and fix reports (use ux-audit), or for proving that a change works with pass/fail evidence for a PR.Votes: 0GitHub stars: 2
- Before AfterProduce a | Before | After | screenshot table for a pull request — two revisions, two URLs, or two existing PNGs, captured at the same viewport with ThinkRun and attached without a public paste host. Use when: before/after screenshots, show the visual diff of this change, the PR needs a before-and-after table, the ship step of a software-factory workflow for a change with a visible surface. Do NOT use for: proving that behaviour works with pass/fail evidence (that is prove-it); a UX review or...Votes: 0GitHub stars: 2
- Prove ItProve that a change works with captured evidence — named test targets in, a pass/fail table with a screenshot, console output and network requests per target out, posted to the PR. Use when: prove this works, attach evidence to the PR, verify the feature we shipped, show it working before merge, 'did the agent actually test this?', a numeric before/after for a perf fix, the prove step of a software-factory workflow. Do NOT use for: an open-ended UX review or 'find what looks wrong' (ux-audit)...Votes: 0GitHub stars: 2