Explorar skills

Execute an approved ops plan — research, write, review, update state, archive. Use after /plan approval. Not for code.

Authoring discipline for new AZIMUTH reference files and templates. Use when adding a new domain reference file, extending an existing one, or creating a new template. Covers: (1) EXTEND vs. CREATE decision heuristic, (2) the Module 7 vocabulary header pattern that prevents domain-gap recurrence, (3) the sourcing caveat pattern for narrow-evidence-base files, (4) pre-verdict gate structure for tem

Analyze debt payoff software — avalanche vs snowball strategy engines, interest calculation accuracy, amortization schedules, payment scheduling automation, credit score impact modeling, hardship accommodation workflows, and progress visualization. Audit personal finance apps, debt management platforms, and loan repayment calculators for correctness and completeness.

Run an app walkthrough — launch a Flutter app on a simulator or emulator, generate and run exhaustive integration tests that exercise every screen, button, form, and user flow, then self-heal failures. Triggers: app walkthrough, integration test, test on simulator, exercise every screen, Flutter integration tests.

Invoque quando o usuário quiser praticar inglês. Corrige gramática, ortografia e expressão em cada resposta, adaptando-se ao nível do usuário ao longo do tempo. Não é para revisões de código ou documentos técnicos.

Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.

把本地 HTML 文件或目录部署到飞书妙搭（Miaoda），生成一个公网可访问的应用及其链接（URL）。当用户要创建 HTML 或要把 HTML、静态网站或 Web demo 发布成公网可访问的链接 / 可分享链接、设置应用共享范围，或提到妙搭 / Miaoda 时使用。凡产出可独立访问的 HTML 产物都属本 skill 的潜在归宿，是否真要部署由 skill 内部协议判断。不用于：上传普通文件到云空间/云盘/云存储（用 lark-drive）、编辑飞书云文档内容（用 lark-doc）、创建飞书原生幻灯片 / 演示文稿（用 lark-slides）。

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Set up visual regression testing with baseline screenshots across breakpoints. Auto-detects frontend framework (Next.js, React, Vue, Angular, Flutter, Storybook), configures Playwright screenshot comparison, BackstopJS, or Flutter golden tests, captures every page at mobile/tablet/desktop/wide viewports plus interactive states (hover, focus, error, empty, loading), stabilizes dynamic content to pr

Comprehensive guidance for planning, executing, and optimizing B2B paid media campaigns across search, social, display, CTV, OOH, and ABM channels — trigger when a user needs help with paid advertising strategy, channel selection, budget allocation, creative approach, audience targeting, or campaign measurement.

Planejando mudanças na API e decidindo a abordagem de versionamento.

Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.