Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
49.493 de skill-uri din 2.407 depozite · actualizat acum 32 de minute
10.672 de skill-uri
- 高级感解说词润色ECNU-ICALK/AutoSkill扮演电视台资深编导，对用户提供的解说词或文案进行润色和语法修正，确保文字风格高级、简洁且专业。AlteleFără avertismente★ 610↓ —
- 电影预告片字卡生成ECNU-ICALK/AutoSkill根据指定电影类型生成预告片字卡，要求无画面描述、语言精炼、情节连贯，并能根据类型调整风格（如喜剧需含蓄表达幽默）。AlteleFără avertismente★ 610↓ —
- ledgersimota/agent-skillsOptimizing FinOps and cloud cost: IaC-based estimation, right-sizing, RI/SP recommendations, anomaly detection, budget alerts, AI/GPU workload economics. Use to forecast or cut cloud spend.AlteleVerifică întâi★ 98↓ —
- 五维度文献综述撰写ECNU-ICALK/AutoSkill根据特定主题，按照理论、应用、对象、结论、方法五个维度撰写文献综述，采用先述后评的逻辑，字数控制在1000字左右。AlteleFără avertismente★ 610↓ —
- 历史辨析题进阶回答ECNU-ICALK/AutoSkill针对历史辨析题或争议性问题，以学生身份回答，并严格遵循“进阶要求”中指定的立场（如肯定或否定某方观点），同时列出数据和文献进行佐证。AlteleFără avertismente★ 610↓ —
- 強制使用繁體中文ECNU-ICALK/AutoSkill用戶要求所有回應必須嚴格使用繁體中文，禁止簡體字、英文或其他語言，並保持專業自然的語氣。AlteleFără avertismente★ 610↓ —
- evo-output-serializationOpenLAIR/OpenSkillSerializes egomotion labels to JSON with frame-interval keys and binary masks to NPZ in CSR sparse format using only NumPy.AlteleFără avertismente★ 97↓ —
- evo-egomotion-dynamic-analysisOpenLAIR/OpenSkillFor consecutive sampled frame pairs, computes sparse optical flow, estimates camera egomotion via partial affine transform, and detects dynamic objects via homography-based motion compensation and frame differencing.AlteleFără avertismente★ 97↓ —
- 都市悬疑-设计标题lornshrimp/Lorn.NovelWriteSkills用于【都市悬疑】题材下的书名设计、筛选、重排与多平台适配。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口名，补充都市现实压迫、证据异常、职业切口与系统性危险感，并明确要求优先强制加载并使用 `通用-设计标题`。支持今日头条平台。AlteleFără avertismente★ 249↓ —
- evo-pcap-feature-extractionOpenLAIR/OpenSkillReads PCAP via Scapy PcapReader, extracts per-packet features into numpy arrays.AlteleFără avertismente★ 97↓ —
- evo-invoice-fraud-detectorOpenLAIR/OpenSkillImplements fraud detection pipeline with fuzzy vendor matching via rapidfuzz, priority-ordered fraud checks, and JSON report generation.AlteleFără avertismente★ 97↓ —
- evo-lake-factor-attributionOpenLAIR/OpenSkillTrains Random Forest to determine feature importances of environmental predictors on water temperature, maps features to categories (Heat/Flow/Wind/Human), and identifies the dominant driving factor category.AlteleFără avertismente★ 97↓ —
- evo-semantic-hierarchical-clusteringOpenLAIR/OpenSkillGenerate sentence embeddings and build a balanced 5-level hierarchy via recursive top-down clustering.AlteleFără avertismente★ 97↓ —
- evo-dubbing-tts-synthesisOpenLAIR/OpenSkillSynthesizes target-language speech from text using Kokoro TTS, with speed/duration control to fit precise time windows. Handles SRT parsing, text extraction, and produces WAV segments.AlteleFără avertismente★ 97↓ —
- evo-acopf-report-generatorOpenLAIR/OpenSkillExtracts ACOPF solution values, computes derived quantities, and produces structured report.json.AlteleFără avertismente★ 97↓ —
- 异能志怪-正文润色lornshrimp/Lorn.NovelWriteSkillsUse when: 正文润色、章节精修、文风精修、语言提纯、节奏打磨、起点风格润色、中段回报强化、章末钩子强化、镜头感提升、人物情绪细修。常见说法：帮我润这章、把这段写顺一点、别改信息只提质感、把中段打磨得更抓人、把钩子和回报润出来。AlteleFără avertismente★ 249↓ —
- 女性化横版名片设计ECNU-ICALK/AutoSkill根据用户提供的个人信息，按照女性化、柔和色调、简洁优雅的风格要求，设计标准横版名片。AlteleFără avertismente★ 610↓ —
- 生成双字艺术作品名ECNU-ICALK/AutoSkill根据用户提供的主题或画作描述，生成具有艺术气息且严格限制为两个字的作品名称，需准确表达主题含义。AlteleFără avertismente★ 610↓ —
- evo-geospatial-antimeridian-platesOpenLAIR/OpenSkillLoad and process PB2002 tectonic plate boundaries and polygons with antimeridian-safe coordinate normalization (0-360 longitude shift) using Shapely 2.0 transform and GeoPandas 1.0 APIs.AlteleFără avertismente★ 97↓ —
- taishang-laojunliuhaisi2026212-maker/taishang-laojun太上老君炼丹炉总控台。用柳爷做自媒体的思路帮创作者把别人的爆款和自己的经历炼成自己的视频：读懂用户此刻在哪、这次要交出什么，再按需调用访谈、找对标拆爆款、选题、系列策划、开头结构、成稿、标题、复盘、变现承接。用户想拍视频但不知道拍什么、手里有参考不知怎么用、有题没稿、要改标题或开头、发了效果不对、替老板或客户做号时使用。AlteleFără avertismente★ 495↓ —
- evo-fuzzy-matchOpenLAIR/OpenSkillFuzzy string matching and confidence calibration for mapping normalized text segments against codebook entries. Implements SequenceMatcher, Levenshtein, Jaccard, cosine similarity, ensemble scoring, and UNKNOWN thresholding.AlteleFără avertismente★ 97↓ —
- evo-geospatial-earthquake-distanceOpenLAIR/OpenSkillParse USGS earthquake GeoJSON, spatially filter earthquakes within a tectonic plate, compute projected distances to plate boundaries using EPSG:3832, and output the furthest earthquake as formatted JSON.AlteleFără avertismente★ 97↓ —
- evo-trend-anomaly-causal-inferenceOpenLAIR/OpenSkillComplete pipeline for identifying anomalous product category spending patterns in e-commerce data using Prophet counterfactual forecasting, and explaining anomalies through demographic factors via Difference-in-Differences causal inference.AlteleFără avertismente★ 97↓ —
- evo-crystallography-fraction-formatOpenLAIR/OpenSkillConverts floating-point fractional coordinates to clean rational fraction strings with bounded denominators (<=12), handling edge cases like near-zero/near-one wrapping and integer values.AlteleFără avertismente★ 97↓ —
AI科幻-多平台小说适配
lornshrimp/Lorn.NovelWriteSkills
AlteleActualizat 4 sept. 2026
De la autor
用于【AI科幻】题材下的多平台适配策略。作为题材包装层与兼容入口，负责保留AI科幻入口名、补充异常数据、系统摩擦、数字压迫感与长期谜团在各平台的保真边界，并明确要求优先强制加载并使用 `通用-多平台小说适配`。关键词：AI科幻多平台适配、平台差异、改写前推演、平台保真。
Instalare
npx skills add lornshrimp/Lorn.NovelWriteSkills --skill 'AI科幻-多平台小说适配' -a claude-code
Se instalează în .claude/skills/AI----------/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Fără descărcare: licența acestui skill (Fără licență) nu ne permite să-i redistribuim fișierele. Comenzile de instalare le iau direct de pe GitHub.
La ce are acces
Doar instrucțiuniNu am văzut acces la rețeaLicență: fără licență
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 75
Securitate100
Proveniență69
Întreținere85
Licență25
Adopție40
Fișiere (2)
- SKILL.md
- references/AI科幻平台适配优先级矩阵.md