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.
49.105 skill-uri din 2.358 de depozite · actualizat acum 18 ore
10.562 de skill-uri
- pm-donewei63w/pm-managerPM Manager /pm-doneAlteleFără avertismente★ 89↓ —
- alice-assistalicewe1/alice_skill技能指令渐进路由（技能路由 / 评分 / 吸收 / 迁移 / 自动化 / 文档与平台集成）。触发词：技能创建/吸收/评分/迁移/自动化/文档/平台指令；先选领域索引，再按任务匹配度与评分选模块，禁止一次读取全部领域。AlteleFără avertismente★ 60↓ —
- alice-mcpalicewe1/alice_skillMCP 热启动网关（不写客户端 config，agent 经网关直接调用 MCP 工具；自检/添加/移除/热开关/目录包装/工具目录发现）。触发词：mcp自检/添加mcp/移除mcp/mcp管理/mcp工具/包装工具目录。AlteleFără avertismente★ 60↓ —
- configure-eccmturac/everything-openai-codexInteractive installer for Everything OpenAI Codex — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.AlteleFără avertismente★ 83↓ —
- macmini-discord-reminderbam-bam-2/solo-skillsUse when the user asks for a one-time or recurring reminder that should run on the mac-mini and arrive by Discord DM.AlteleFără avertismente★ 434↓ —
- alice-absorbalicewe1/alice_skill技能包吸收手册（AI 读 md 判类与领域、拟描述，脚本落库并刷新渐进路由）。触发词：吸收、新技能、加技能、入库、absorb。AlteleFără avertismente★ 60↓ —
- alice-migratealicewe1/alice_skill技能包迁移/路径修复（技能已就位 → agent 探测真实 skills 根 → 刷新生成物内嵌路径 → 只读检查全局路由 → 自检 → 询问用户是否注入；不拷贝文件）。触发词：迁移/换电脑/新机器/搬技能包/路径修复/部署技能包/alice迁移自检AlteleFără avertismente★ 60↓ —
- nanoclaw-replmturac/everything-openai-codexOperate and extend NanoClaw v2, ecc's zero-dependency session-aware REPL built on codex -p.AlteleFără avertismente★ 83↓ —
- tickmembranedev/application-skillsTick integration. Manage data, records, and automate workflows. Use when the user wants to interact with Tick data.AlteleFără avertismente★ 272↓ —
- binary-diffalicewe1/alice_skill跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用。 适用场景：内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、应用更新后快速定位新偏移。 核心方法：用 LLM 做结构化差异比对，程序化输入输出，成本极低（200 函数 ~1 元）。 触发关键词：符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary diff、版本对比。AlteleFără avertismente★ 60↓ —
- edr-bypass-realicewe1/alice_skill逆向防御方实现 → 红队针对性绕过。把 EDR / Defender / AV 的 hook 表、ETW provider、AMSI 实现先逆向出来， 再写针对性的 unhook / 间接 syscall / ETW patch / call stack spoof。对照 MITRE ATT&CK T1562 防御规避。 触发关键词：EDR 绕过、AV bypass、免杀、unhook、direct syscall、indirect syscall、Hell's Gate、Halo's Gate、 Tartarus Gate、ETW patch、AMSI patch、call stack spoofing、hardware breakpoint Blindside、MITRE T1562、 ntdll unhook、kernel callback、CrowdStrike 绕过、Defender 绕过、Sentinel One 绕过、Elastic Defend、 Sysmon 规避、PPID spoof、Sleep mask、Process Hollowing、Reflective DLL。AlteleFără avertismente★ 60↓ —
- travel-journal-creatorJourniOne-ai/JourniOne-Planning-Skills当用户提出旅行需求时自动使用，包括找旅行灵感、推荐目的地、安排或调整行程、规划主题路线、整理旅行照片回忆或已有路书。无需用户点名 Skill；用 JourniOne 逐步规划每天怎么玩，确认后生成带地图、能分享的 Travel Journal，日期机酒按需补充。AlteleFără avertismente★ 1,2 K↓ —
- rust-patternsmturac/everything-openai-codexIdiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.AlteleFără avertismente★ 83↓ —
- threads-reply-voicebam-bam-2/solo-skills밤밤 개인 스레드 계정(@bam.bam_2)의 "내 글에 달린 댓글"에 답글을 대신 쓸 때 읽을 것. 답글 22,560건 실측으로 역산한 문체 기준표, 댓글 유형별 대응, 대량 발행 절차와 안전장치를 담고 있다.AlteleFără avertismente★ 434↓ —
- fixermembranedev/application-skillsFixer integration. Manage Organizations, Users. Use when the user wants to interact with Fixer data.AlteleFără avertismente★ 272↓ —
- lanomembranedev/application-skillsLano integration. Manage data, records, and automate workflows. Use when the user wants to interact with Lano data.AlteleFără avertismente★ 272↓ —
- skill-statusXBuilderLAB/cheat-on-skillcheat-on-skill 的陪跑进度 skill。用户问“今天该干嘛”“我现在做到哪了”“继续学”“打卡”“我卡住了”“下一步是什么”时触发。读取 .skill-state.json 的 active.progress 和 learning_plan，给当天任务、检查完成情况、记录进度、根据快慢调整计划。前置：已有 .skill-state.json 且 active.learning_plan 存在。AlteleFără avertismente★ 197↓ —
- perl-patternsmturac/everything-openai-codexModern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.AlteleFără avertismente★ 83↓ —
- mendmembranedev/application-skillsMend integration. Manage data, records, and automate workflows. Use when the user wants to interact with Mend data.AlteleFără avertismente★ 272↓ —
- u301membranedev/application-skillsU301 integration. Manage data, records, and automate workflows. Use when the user wants to interact with U301 data.AlteleFără avertismente★ 272↓ —
- kafka-topic-auditlensesio/agentic-engineering-for-apache-kafkaAudit all Kafka topic configurations against production best practices using the Lenses MCP server. Checks replication factor, retention, partitions, compaction, naming conventions, orphaned topics and missing metadata. Use when user says "audit my topics", "check topic configs", "topic health check" or asks about retention, replication or partition settings. Do NOT use for creating, deleting or modifying topics.AlteleFără avertismente★ 67↓ —
- homekitdpearson2699/swift-ios-skillsControl smart-home accessories and commission Matter devices using HomeKit and MatterSupport. Use when managing homes/rooms/accessories, creating action sets or triggers, reading accessory characteristics, onboarding Matter devices, or building a third-party smart-home ecosystem app.AlteleFără avertismente★ 1,3 K↓ —
- metrickitdpearson2699/swift-ios-skillsUse when collecting or analyzing production iOS or iPadOS performance telemetry with MetricKit, including iOS 27 MetricManager async metric or diagnostic reports, hang or crash triage, custom signposts, extended launch measurement, durable export, or iOS 26 MXMetricManager compatibility.AlteleFără avertismente★ 1,3 K↓ —
- alpha-evolvegaasher/Agent-Loop-SkillsUse when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel proposers each apply one small SEARCH/REPLACE diff to a parent, scored by a cascade-evaluated training run, and children are kept in a MAP-Elites archive across islands (with migration + checkpointing) so diverse high performers survive. A finite, bounded-parallelism re-creation of AlphaEvolve/OpenEvolve, bent for ML autoresearch. Runs to a fixed compute budget or until interrupted. Not for the sequential single-thread autoresearch loops (one change → measure → keep/revert), and not for verifying a known bug or external claim — this is parallel, diversity-preserving search over a program.AlteleFără avertismente★ 178↓ —