Github Actions Workflow

Creates high-quality Instagram carousels as swipeable HTML previews with export-ready slides (1080×1350px PNG). Handles the full workflow: brand setup, slide copy, visual design system (colors, fonts, components), HTML generation, and Playwright-based export. Use this skill whenever the user asks to create, design, or generate an Instagram carousel, carrossel, slides para Instagram, or any Instagram multi-image post — even if they don't explicitly say "carousel" or "skill". Also trigger for requests to "create a post with multiple slides", "fazer carrossel", or "exportar slides para o Instagram".

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Valuation analysis for a single stock via Longbridge — current PE / PB / PS / EV-EBITDA snapshot, historical percentile (1–3 years), industry median + relative premium, industry rank. Triggers: "估值贵不贵", "是不是被低估", "PE 历史百分位", "PB 分位", "行业溢价", "行业折价", "X 现在适合买不", "估值水平", "估值貴不貴", "是否被低估", "PE 歷史分位", "行業溢價", "行業折價", "is X expensive", "is X undervalued", "PE percentile", "industry valuation premium", "valuation snapshot".

A comprehensive starting point for AI agents to work with Capacitor. Covers core concepts, CLI, app creation, plugins, framework integration, best practices, storage, security, testing, troubleshooting, upgrading, and Capawesome Cloud (live updates, native builds, app store publishing). Pair with the other Capacitor skills in this collection for deeper topic-specific guidance.

Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the smallest atomic, independently-mergeable PRs and builds the independent ones concurrently via one worktree per PR driven by parallel subagents or a team. Unbounded loop: any failing gate sends you back to fix-and-re-QA inside that PR's worktree. Use whenever implementation work needs to land as a PR. Triggers: 'create a PR', 'implement and PR', 'work on this and make a PR', 'implement issue', 'land this as a PR', 'split into atomic PRs', 'parallel PRs', 'work-with-pr', 'PR workflow', 'implement end to end', even when user just says 'implement X' if the context implies PR delivery.

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).