@garrytan
Writes software, dreams.
148 skills3 repositories 168.7K
Find and fix bugs in websites, APIs, command-line tools, and background processes. Choose from three testing depths, verify fixes, and receive evidence of the changes plus a summary of readiness for release.
Test SwiftUI apps on a real iPhone or iPad by repeatedly capturing screens, analyzing them, taking actions, and verifying results. An embedded HTTP server enables interaction, with optional remote access through Tailscale.
Review a UI/UX plan before implementation, score its design dimensions, and identify missing decisions. Through discussion, the skill adds concrete improvements directly to the plan so the review produces an updated plan.
Review plans for APIs and developer tools through the eyes of their users. Explore developer needs, compare competitors, and identify onboarding friction, with modes for competitive differentiation, detailed refinement, or critical gaps.
Review a week of engineering work using commit history, work patterns, and code quality measures. It tracks trends across retrospectives and breaks down each team member’s contributions, highlighting strengths and areas for growth.
Limit file edits to a chosen directory and block Edit, Write, and NotebookEdit operations outside it. Keep debugging or module changes within scope, with the restriction remaining active until explicitly removed.
Extract information from web pages through Aside using existing signed-in sessions. Collect lists, tables, prices, or links and receive one JSON document, a structured data format, without changing the page.
Merge an existing pull request, wait for automated checks and deployment, then verify production health with canary checks, targeted checks for problems. Continue the release workflow after /ship has created the pull request.
Use OpenAI Codex CLI to review code changes, challenge an implementation by looking for ways it could fail, or discuss technical questions. Three modes provide an independent opinion, with follow-up questions supported in ongoing consultations.
Convert Markdown files into formatted PDFs with page numbers, controlled page breaks, optional covers, clickable contents, and watermarks. Render diagrams and local images within the document, preview the layout, or export to HTML and Word.
Review proposed code changes before merging them. Compare changes with the base branch to find structural issues, including unsafe SQL, misplaced trust in large language model inputs, and unintended effects within conditional code.
Monitor a live app after deployment for console errors, slower performance, and page failures. Periodic screenshots and comparisons with pre-deployment baselines help identify anomalies and check whether the release is behaving as expected.
Create missing documentation for a feature, module, or whole project. Use Diataxis, a framework that separates tutorials, practical guides, reference information, and explanations, to organize documents around what readers need to learn or accomplish.
Import cookies from a regular Chromium browser into a headless testing session, which runs without a visible window. Choose the browser profile and domains to prepare for testing pages that require sign-in.
View release versions claimed by open pull requests, proposed code changes, alongside work in related Conductor workspaces. Get a read-only snapshot showing queued work and the version slot that /ship would choose next.
Generate several AI design options, view them on a comparison board, and collect organized feedback. Use the results to explore visual directions and refine designs when a feature’s appearance is undecided or an existing interface needs improvement.
Compare Claude, GPT, and Gemini on the same skill or prompt. Get a table of response times, token usage, and costs, with optional AI scoring to help choose a model for the task.
Set up gbrain so a coding agent can call it. Install its command-line tool, initialize a local PGLite or Supabase brain, register MCP, the agent connection mechanism, and record trust policies for each remote.
Run sequential reviews of a plan from business, design, engineering, and developer experience perspectives. Apply six principles to intermediate decisions, then bring close choices, scope questions, and reviewer disagreements to a final approval step.
Save the current Git state, decisions made, and remaining work so a future agent session can resume with context. Use it before pausing work, then pair it with /context-restore when returning.
Measure web page loading times, rendering milestones, and resource sizes in a real browser. Save baseline measurements, compare results before and after code changes, and inspect historical trends to spot performance regressions.
Audit a developer product by trying its documentation and setup flow, measuring onboarding time, capturing errors, and reviewing command-line help. Produce an evidence-backed scorecard and compare results with earlier planning scores when available.
Open web pages, follow navigation, and check form flows in a browser. Capture screenshots at different screen sizes, compare pages before and after actions, and collect console errors, the technical messages that can reveal page problems.
Clean up an iOS app after /ios-qa by removing the DebugBridge package and its debug wiring. The cleanup covers StateServer, DebugOverlay, generated accessor code, and hooks added to the app.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)