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.
11.036 de skill-uri din 323 de depozite · actualizat acum 16 minute
963 de skill-uri
- registry-default-mirrorcisco-ai-defense/skill-scannerPin the npm registry to the public default and fetch published release notesProductivitateFără avertismente★ 2,6 K↓ —
- schema-optimization-orchestratorjeremylongshore/tons-of-skills-marketplaceMulti-phase schema optimization workflow orchestrator. Creates session directories, spawns phase agents sequentially, validates outputs, aggregates results. Trigger: "run schema optimization", "optimize schema workflow", "execute schema phases"ProductivitateFără avertismente★ 2,9 K↓ —
- skill-adapterjeremylongshore/tons-of-skills-marketplaceExecute analyzes existing plugins to extract their capabilities, then adapts and applies those skills to the current task. Acts as a universal skill chameleon that learns from other plugins. Activates when you request "skill adapter" functionality. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.ProductivitateFără avertismente★ 2,9 K↓ —
- memory-kitjeremylongshore/tons-of-skills-marketplacePersistent context management for Claude Code sessions. Save, load, update, share, and audit session memory via MEMORY.md. Prevents context loss on compaction or session restart. Use when starting a session, before compaction, syncing context across teammates, or pruning stale memory entries. Trigger with "save memory", "load memory", "memory audit", "memory share".ProductivitateFără avertismente★ 2,9 K↓ —
- memoryjeremylongshore/tons-of-skills-marketplaceExecute extract and use project memories from previous sessions for context-aware assistance. Use when recalling past decisions, checking project conventions, or understanding user preferences. Trigger with phrases like "remember when", "like before", or "what was our decision about".ProductivitateFără avertismente★ 2,9 K↓ —
- meeting-notes-and-actionscomposio-community/awesome-codex-skillsTurn meeting transcripts or rough notes into crisp summaries with decisions, risks, and owner-tagged action items; use for Zoom/Meet/Teams transcripts, call notes, or long meeting chats to generate share-ready outputs.ProductivitateFără avertismente★ 17 K↓ —
- email-draft-polishcomposio-community/awesome-codex-skillsDraft, rewrite, or condense emails with target tone, length, and audience; use for cold outreach, replies, status updates, or escalations where clarity and brevity matter.ProductivitateFără avertismente★ 17 K↓ —
- rememberparcadei/Continuous-Claude-v3Store a learning, pattern, or decision in the memory system for future recallProductivitateFără avertismente★ 3,9 K↓ —
- recallparcadei/Continuous-Claude-v3Query the memory system for relevant learnings from past sessionsProductivitateFără avertismente★ 3,9 K↓ —
- resume-handoffparcadei/Continuous-Claude-v3Resume work from handoff document with context analysis and validationProductivitateFără avertismente★ 3,9 K↓ —
- natural-japanesecoji/natural-japanese仕事の日本語文書を、自然で読みやすく、わかりやすい日本語で書く・直すためのスキル。議事録、調査レポート、顧客向けのレポート、社内ガイド、技術記事、PR の説明文、リサーチメモ、企画書、メール、スライド構成などの作成や推敲と、note やブログ、エッセイの執筆に使う。文字起こしから議事録を作るときにも使う。自然な日本語にしたい、読みやすくしたい、簡潔にしたい、結論から書きたいといった依頼のほか、読みづらい、わかりにくい、何を言っているかわからない、AI っぽい、AI 臭い、英語の直訳っぽい、日本語として不自然、違和感があるといった指摘にも使う。書き換えずに AI らしさを判定・採点してほしいという依頼や、自分の文体を学ばせたいという依頼にも対応する。ProductivitateFără avertismente★ 1,9 K↓ —
- weekly-account-summaryirinabuht12-oss/marketing-skillsClaude skills for marketing: 49 free marketing skills for Claude Code and claude.ai (Google Ads, Meta Ads, SEO, AI visibility) + the Ryze Google Ads MCP / Meta Ads MCP: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcpProductivitateFără avertismente★ 5,2 K↓ —
- workflow-routerparcadei/Continuous-Claude-v3Goal-based workflow orchestration - routes tasks to specialist agents based on user goalsProductivitateFără avertismente★ 3,9 K↓ —
- motparcadei/Continuous-Claude-v3System health check (MOT) for skills, agents, hooks, and memoryProductivitateFără avertismente★ 3,9 K↓ —
- agentic-workflowparcadei/Continuous-Claude-v3Agentic Workflow PatternProductivitateFără avertismente★ 3,9 K↓ —
- implement_taskparcadei/Continuous-Claude-v3Implementation agent that executes a single task and creates handoff on completionProductivitateFără avertismente★ 3,9 K↓ —
- agent-context-isolationparcadei/Continuous-Claude-v3Agent Context IsolationProductivitateFără avertismente★ 3,9 K↓ —
- xiaohongshu-note-detailbrowser-act/skillsFetch Xiaohongshu (RedNote / xhs) note detail and comments by note ID, returning title, description, author info, engagement stats, tags, and paginated comment list. Use when user mentions note detail xiaohongshu, get rednote post, xhs note content, xiaohongshu comment scrape, fetch post comments, scrape xhs comments, rednote note details, xiaohongshu post engagement, xiaohongshu note content, rednote post data, xhs post detail, get xiaohongshu comments, rednote comment list, xiaohongshu note metadata, xhs note scrape, fetch rednote note.ProductivitateFără avertismente★ 6,2 K↓ —
- ql-workflowmaxritter/pilot-shellProfessional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.ProductivitateFără avertismente★ 2,1 K↓ —
- seedance-production-workflowLearnPrompt/awesome-seedancePlan and carry a Seedance video from brief through references, storyboard, generation handoff, shot-level review, and targeted repair. Use for an end-to-end Seedance production request; use a narrower prompt skill for a single prompt.ProductivitateFără avertismente★ 2,2 K↓ —
- youtube-channel-business-emailbrowser-act/skillsYouTube channel business email and contact extractor: accepts a channel id (UCxxx), handle (@name), or URL; navigates the channel About view; extracts the business email from the description text plus full channel metadata (name, id, country, subscriber count, view count, video count, joined date, external links classified as social/aggregator/personal). When the description has no email, follows non-social outbound links (personal site, business site, link aggregator) and scans those pages for an email so creators who place their inquiry email on their own site are still covered. Use when user mentions youtube channel email, youtube business email, youtube creator email, youtube contact email, youtube channel contact, youtube channel scraper email, youtube email finder, youtube influencer email, youtube outreach, youtube sponsorship contact, youtube partnership email, scrape email from youtube, get email from youtube channel, find youtube creator contact, extract youtube channel emails in bulk, youtube channProductivitateFără avertismente★ 6,2 K↓ —
- build-perf-baselinedotnet/skillsEstablish MSBuild/.NET build performance baselines before optimizing. USE FOR: unranked slow builds; cold, warm, incremental or no-op measurements; before/after comparisons; CI output caching; static graph, artifacts output and dependency graph trimming. Start here before build-perf-diagnostics, incremental-build or build-parallelism. DO NOT USE FOR: known repeated-restore fixes (use eliminate-redundant-restores), non-MSBuild builds. For measured target/task/analyzer bottlenecks, use build-perf-diagnostics.ProductivitateVerifică întâi★ 5,7 K↓ —
- no-task-outputparcadei/Continuous-Claude-v3Never Use TaskOutputProductivitateFără avertismente★ 3,9 K↓ —
- skill-optimizerrohitg00/pro-workflowSkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.ProductivitateFără avertismente★ 2,9 K↓ —