热门 Agent Skills
2104 个技能Look up conventions, patterns, and concrete implementations from your own GitHub repositories checked out locally under ~/projects/referenzen/.
GSAP 官方技能，涵盖 gsap.utils 工具集，包括 clamp、mapRange、normalize、interpolate、random、snap、toArray、wrap、pipe 等实用函数。
通过将偶然的栈、供应商、模型、CLI、路径、配额或工具名词替换为其所指的机制，使持久化工件可移植，同时保持来源、运行手册和工具主题声明的具体性。
Product Hunt launch optimization with specific specs, timing, and gallery strategy.
Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn.
Film and video storyboarding with shot vocabulary, continuity rules, and panel layout.
AI product photography with studio lighting, lifestyle shots, and packshot conventions.
App Store and Google Play screenshot creation with exact platform specs.
YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization.
Still-to-video conversion guide: model selection, motion prompting, and camera movement.
Character consistency across AI-generated images with reference sheets and LoRA techniques.
Structured competitive analysis with feature matrices, SWOT, positioning maps, and UX review.
Use when a claim depends on an agent taking a real action.
Landing page conversion optimization with layout rules, hero section design, and CTA psychology.
在 re0-loop 首次迭代前，为 paperthin 迭代打开一个案例簿，并在创建文件夹的同时写入真实内容，确保目录从不为空。
Landing page conversion optimization with layout rules, hero section design, and CTA psychology.
Use when a vague idea, stray thought, remembered fragment, or uncertain direction needs to become a concrete outcome, tested design, decision record, artifact, or executable handoff.
re0-loop 通过重复的构建、QA、re0-memo 和 re0-work 循环，在保留学习成果的同时让代码消亡，适用于长期代理项目。
Use when one exact callable tool and a user-authored behavior configuration must become a tool-specific Agent Skill, or when that behavior must be integrated into one exact existing Agent Skill.
YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization.
Structured competitive analysis with feature matrices, SWOT, positioning maps, and UX review.
Use when a request prescribes a method, tool, metric, or artifact that may not reach the result the user described, or when doing the request as written would leave that result unproved: "A/B test the signup button color" for a conversion problem, "add a cache" for a slow page, "the focused tests passed, announce the release".
Still-to-video conversion guide: model selection, motion prompting, and camera movement.
Product Hunt launch optimization with specific specs, timing, and gallery strategy.
Refactor selected code while preserving behavior, then verify.
Use when a workflow, recipe, or capability needs to be packaged as an agent skill, or when an existing skill needs scaffolding, validation, linting, or evals.