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.
18.363 de skill-uri din 637 de depozite · actualizat acum 9 minute
1.259 de skill-uri
- smart-model-routingvibeeval/vibecosystemDynamic model selection based on task complexity scoring. Replaces static model mappings with a weighted signal system that picks Opus, Sonnet, or Haiku-class speed per task. Works with agent-assignment-matrix.md.ProductivitateFără avertismente★ 540↓ —
- session-compressionvibeeval/vibecosystemLossless session context compression for token efficiency. Extracts entities, decisions, and state into compact format before context window fills. 10-30x reduction in context size while preserving all actionable information.ProductivitateFără avertismente★ 540↓ —
- hizirvibeeval/vibecosystemHızır'ın kullanım kılavuzu. Tüm komutlar, agent'lar, workflow'lar, sistemler burada. /hizir yaz, her şeyi gör.ProductivitateFără avertismente★ 540↓ —
- expand-tasksanombyte93/prd-taskmasterExpand all TaskMaster tasks with deep research before coding begins. Reads tasks.json, launches parallel research agents per task in waves using the research-expander agent. Writes findings back to tasks.json. Part of the prd-taskmaster toolkit. Use after PRD is parsed and before implementation. Invoke with /expand-tasks.ProductivitateFără avertismente★ 606↓ —
- task-decompositionrohitg00/skillkitBreaks down complex software, writing, or research tasks into small, atomic, independently completable units with dependency graphs and milestone breakdowns. Use when the user asks to plan a project, decompose a feature, create subtasks, split up work, or needs help organizing a large piece of work into a step-by-step plan. Triggered by phrases like "break down", "decompose", "where do I start", "too big", "split into tasks", "work breakdown", or "task list".ProductivitateFără avertismente★ 1,6 K↓ —
- recallvibeeval/vibecosystemQuery the memory system for relevant learnings from past sessions using semantic search.ProductivitateFără avertismente★ 540↓ —
- nw-command-optimization-workflownWave-ai/nWaveStep-by-step workflow for converting bloated command files to lean declarative definitionsProductivitateFără avertismente★ 622↓ —Apare și în 1 alt depozit
- ctrl-clipdavepoon/buildwithclaude⧉ Copy a message to the system clipboard cleanly formatted — no blockquote pipes, no terminal bars, no Claude commentary. Use whenever you draft a message the user will paste (Slack, Teams, PR comment, email) to add a clickable "⧉ ctrl + click" copy link under it, and when the user says "/ctrl-clip", "copy that", "put it on the clipboard" (in any language). Optional argument picks the target format: slack (default), md, plain.ProductivitateFără avertismente★ 3,7 K↓ —
- nw-deliver-orchestrationnWave-ai/nWaveDELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes *deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.ProductivitateFără avertismente★ 622↓ —Apare și în 1 alt depozit
- tao-analyze-detection-kpiNVIDIA/skillsRun TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP at a fixed IoU. Use when an object detection workflow needs per-class mAP reported after inference, or when the user asks to "run KPI analyze", "compute detection mAP", or "score my OD predictions against ground truth".ProductivitateFără avertismente★ 3,7 K↓ —
- jetson-inference-mem-tuneNVIDIA/skillsPick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.ProductivitateFără avertismente★ 3,7 K↓ —
- iterative-retrievalvibeeval/vibecosystemPattern for progressively refining context retrieval to solve the subagent context problemProductivitateFără avertismente★ 540↓ —
- obsidian-basesanbeime/skill内容创作者与技术写作员在管理海量笔记时，当需要构建 Obsidian 数据库视图、配置过滤器或编写 YAML 公式，使用此技能可自动生成标准 .base 文件，轻松实现笔记的表格/卡片多维展示与数据汇总，让知识库管理效率翻倍。ProductivitateFără avertismente★ 8,6 K↓ —
- obsidian-markdownanbeime/skill技术写作员与内容创作者在构建Obsidian知识库时，当需要编写带双向链接、Callout或Frontmatter的复杂笔记，使用此技能可精准生成标准Markdown文档，完美支持wikilinks与嵌入，大幅提升知识管理与排版效率！ProductivitateFără avertismente★ 8,6 K↓ —
- remembervibeeval/vibecosystemStore a learning, pattern, or decision in the memory system for future recall.ProductivitateFără avertismente★ 540↓ —
- 22-personal-brand-contextminhnv0807/ai-business-skillsDung khi bat dau xay thuong hieu CA NHAN cho mot con nguoi cu the — founder, coach, creator: skill nay tao file .agents/personal-brand-context.md gom dinh vi ca nhan, niche, story arc, content pillar, chan dung nguoi theo doi, brand voice, visual identity va kho anh reference. Chay MOT LAN truoc moi skill personal brand 23-28. Kich hoat khi user nhac 'thuong hieu ca nhan', 'personal brand', 'ho so ca nhan', 'founder context', 'coach context', 'creator context', 'muon xay hinh anh ca nhan', 'bat dau lam personal brand'. Khong dung cho — thuong hieu DOANH NGHIEP hoac san pham thi dung skill product-marketing-context; dinh vi cong ty tren thi truong thi dung skill 58-positioning.ProductivitateFără avertismente★ 624↓ —
- 49-html-email-templateminhnv0807/ai-business-skillsDung khi can FILE HTML email chay duoc tren moi email client — cau truc table, CSS inline, be ngang 600px, dark mode, spec rieng cho Gmail, Outlook, Apple Mail va checklist test truoc khi gui. Mau va font lay tu brand guideline. Kich hoat khi user nhac 'email HTML', 'code email', 'template email', 'email responsive', 'email vo bo cuc tren Outlook', 'anh trong email khong hien', 'paste vao Brevo bi vo'. Khong dung cho — noi dung va chuoi gui email thi dung skill 14-email-marketing; trang web dat sau nut CTA thi dung skill 12-brief-landing-page; quy dinh mau va font thuong hieu thi dung skill 46-brand-guideline.ProductivitateFără avertismente★ 624↓ —
- tracing-patternsvibeeval/vibecosystemOpenTelemetry setup, span context propagation, sampling strategies, Jaeger queriesProductivitateFără avertismente★ 540↓ —
- tao-analyze-gaps-vlm-bcqNVIDIA/skillsExtract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ gaps", "extract VLM false positives and false negatives", or identify failure cases from a predictions JSON for DEFT root-cause analysis on a binary-classification VLM workflow.ProductivitateFără avertismente★ 3,7 K↓ —
- 22-personal-brand-context-globalminhnv0807/ai-business-skillsUse when starting work on a PERSONAL brand — a founder, coach, or creator, not a company: creates `.agents/personal-brand-context-global.md` covering story, expertise, audience, positioning, platforms, visual identity, and the asset inventory of style refs, face refs, logo, palette, and background, with region variants for US, EU, SEA, and LATAM. Skills 23 to 28 read it first. Trigger on 'personal brand setup', 'set up my founder brand', 'coach personal brand context', 'creator profile setup', 'the AI does not know my story', 'build my personal brand from zero'. Not for — a company or product brand, see `00-marketing-plan-global` and `product-marketing-context-global`; the 12-month strategy built on this, see `23-personal-brand-strategy-global`.ProductivitateFără avertismente★ 624↓ —
- 01-content-calendar-globalminhnv0807/ai-business-skillsUse when the user needs a monthly or weekly content calendar — posting schedule per channel, funnel ratio, content pillars, repurposing matrix, and an owner per slot. Trigger on 'content calendar', 'posting schedule', 'what should we post this month', 'editorial calendar', 'social media plan', 'we post randomly with no plan'. Also use when the user only says the team keeps running out of things to post. Not for — the brief for one specific post, see `36-content-brief-global`; the caption text itself, see `37-social-caption-global`; deciding next period content from last period data, see `40-next-content-plan-global`; a paid campaign timeline, see `02-campaign-brief-global`.ProductivitateFără avertismente★ 624↓ —
- reputation-patternsvibeeval/vibecosystemAgent reputation scoring, performance tier system, trust calibration, and task affinity matchingProductivitateFără avertismente★ 540↓ —
- 33-b2b-lead-genminhnv0807/ai-business-skillsDung khi can tim va tiep can khach hang doanh nghiep — xac dinh ICP, dung danh sach prospect co nguon va ngay verify, cham diem Hot/Warm/Cold, va viet outreach qua Zalo, dien thoai, email. Kich hoat khi user nhac 'tim khach hang B2B', 'danh sach prospect', 'lead gen B2B', 'tiep can doanh nghiep', 'cold outreach', 'ban cho cong ty'. Khong dung cho — khach hang o NUOC NGOAI thi dung skill 29-xuat-khau-b2b; tai lieu ban hang va quan ly pipeline thi dung skill 71-sales-enablement; khach hang le B2C thi dung skill 09-insight-khach-hang.ProductivitateFără avertismente★ 624↓ —
- memory-palacevibeeval/vibecosystemHierarchical memory organization for multi-session context retention. Wings (projects) > Rooms (domains) > Drawers (decisions). Semantic search across all memories with zero cloud dependency.ProductivitateFără avertismente★ 540↓ —