一键导入
agent-skills
agent-skills 收录了来自 mikecann 的 5 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。
这个仓库中的 skills
Generate Mike-style YouTube thumbnail concepts and final drafts for Convex videos using Mike's local head-and-shoulders photo cutouts and local Convex logo assets. Use when the user asks for thumbnails, YouTube thumbnails, video thumb options, or a thumbnail like the Convex static hosting "NO DASHBOARDS" example.
Create short hand-drawn cartoon B-roll clips for Mike's tech-explainer videos using one raster start frame and a video model such as Seedance or Veo. Use for humorous character moments, object-led physical metaphors, visual jokes, or animated attention resets. Keep code, UI, schemas, and deterministic diagrams in motion graphics or real screen footage.
Generate silent motion-graphic MP4 clips for a tech-explainer YouTube video using Remotion. The clips are overlay B-roll the user drops onto a voiceover timeline. Use when the user is working from a video folder and says "build motion graphics for this video", "make motion graphics", "add a motion graphic for this section", "render this part as a clip", or wants to scaffold a Remotion project from a markdown script.
Drive a branch to merge-ready by ensuring a PR exists, monitoring checks, triaging automated review comments, replying and resolving each handled bot thread, and optionally squash merging when the user asked for it. Use when the user says ship, land this, get this PR ready, babysit CI, handle bot review comments, or wants you to keep a PR green until merge.
Runs a second-pass cleanup over AI-written code using the repo's style guide in style.md. Prefers parallel subagents to simplify recently modified files without changing behavior. Use when the user says "deslop", "clean this up", "make this less AI", "apply my style guide", "second pass", or asks to simplify generated code after implementation.