Loading...
Loading...
Found 12,004 Skills
验证研究报告中所有声明的引用准确性、来源质量和格式规范性。确保每个事实性声明都有可验证的来源，并提供来源质量评级。当最终确定研究报告、审查他人研究、发布或分享研究之前使用此技能。
Enforces Supabase access patterns and service boundaries. Use only when working with Supabase projects. Centralizes Supabase in a dedicated layer and forbids calling Supabase from outside that boundary.
Use when implementing motion design, timeline animations, visual animation editors, animating Three.js/R3F scenes, creating keyframe animations, or using Theatre.js, @theatre/core, @theatre/studio, @theatre/r3f, theatric, or building animation tooling for the web.
Maintain a wiki-style world bible for collaborative fiction. Use for long-running story worlds, shared universes, membership sites, or any fiction requiring persistent canonical reference.
Diagnose genre problems and generate genre-specific elements. Use when genre promise is unclear, when elements feel misplaced, when secondary genres compete with primary, or when you need genre-specific entropy. Covers all 11 elemental genres from the Writing Excuses framework.
Analyze how competitors would rank in AI search results for a given topic or query. Triggers on "analyze competition", "competitor analysis", "what ranks for", "who would rank", "competitive landscape".
Unified skill that guides spec creation through structured, interactive process.
Master fine-tuning of large language models for specific domains and tasks. Covers data preparation, training techniques, optimization strategies, and evaluation methods. Use when adapting models for specialized applications, reducing inference costs, or improving domain-specific performance.
End-to-end data science and ML engineering workflows: problem framing, data/EDA, feature engineering (feature stores), modelling, evaluation/reporting, plus SQL transformations with SQLMesh. Use for dataset exploration, feature design, model selection, metrics and slice analysis, model cards/eval reports, experiment reproducibility, and production handoff (monitoring and retraining).
Create and work with Meta SAM 3 (facebookresearch/sam3) for open-vocabulary image and video segmentation with text, point, box, and mask prompts. Use when setting up SAM3 environments, requesting Hugging Face checkpoint access, generating inference scripts, integrating SAM3 into Python apps, fine-tuning with sam3/train configs, running SA-Co or custom evaluations, or debugging CUDA/checkpoint/prompt pipeline issues.
Design or refactor skills by separating deterministic and non-deterministic steps. Use when creating or improving skills, especially to move repeatable workflows into scripts/ and update SKILL.md to call them.
OODA loop decision framework (Observe, Orient, Decide, Act). Use for complex decisions, problem-solving, unclear situations, or when someone is jumping to solutions without analysis.