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.
46.095 de skill-uri din 2.198 de depozite · actualizat acum 4 minute
9.543 de skill-uri
- tia-devices-generalCzarnak/totally-integrated-claudeC# Openness implementation of device-level operationsAlteleFără avertismente★ 76↓ —
- grace-setup-subagentsosovv/grace-marketplaceCreate GRACE 4 worker and reviewer subagent presets that understand .grace artifacts, scopes, assertions, and verification evidence.AlteleFără avertismente★ 257↓ —Apare și în 1 alt depozit
- variable-rewardsrshankras/claude-code-apple-skillsGenerates a variable reward system with randomized rewards, daily bonuses, mystery box mechanics, and ethical engagement caps. Use when user wants daily spins, mystery boxes, random rewards, or gamification reward systems.AlteleFără avertismente★ 840↓ —
- source-verificationHezaoHezao/poirot验证信源可信度的研究过程知识,指导 agent 在涉及事实声明时交叉核验信源AlteleFără avertismente★ 257↓ —
- spikeHezaoHezao/poirotThrowaway experiments to validate an idea before build.AlteleFără avertismente★ 257↓ —
- svelte-developmenttravisjneuman/.claudeSvelte 5 development with runes ($state, $derived, $effect), SvelteKit full-stack framework, and modern reactive patterns. Use when building Svelte applications, implementing fine-grained reactivity, or working with SvelteKit routing and server functions.AlteleFără avertismente★ 106↓ —
- trend-to-microbetFAIRY123456789/human-edge-agent-skillsTurn a fast-moving AI, product, creator, career, or technology trend into a small evidence-producing bet instead of a vague FOMO reaction. Use when the user says something is suddenly hot, wonders whether to chase a new model, platform, agent, Skill, or plugin, or wants a 48-hour to 7-day experiment with a clear upside, effort cap, proof metric, and stop rule.AlteleFără avertismente★ 108↓ —
- agent-ready-auth-mdfabricioctelles/skillsSub-skill: Implement Auth.md for agent registration discovery. Serve /auth.md with OAuth metadata at /.well-known/oauth-protected-resource and authorization server endpoints.AlteleFără avertismente★ 123↓ —
- grace-refreshosovv/grace-marketplaceDetect drift between observed repository state and durable GRACE 4 .grace current state, then help create reconciliation changes.AlteleFără avertismente★ 257↓ —Apare și în 1 alt depozit
- pm-datakonglong87/superPMUse when: 需要设计产品数据指标、规划数据埋点、建立数据监控体系、进行数据分析和趋势预测 Do NOT use when: 数据指标已明确、仅需简单统计无需指标体系AlteleFără avertismente★ 84↓ —
- model-calibrationcxcscmu/SkillLearnBenchCalculating RMSE metrics and parameter calibration for lake model validationAlteleFără avertismente★ 91↓ —
- portfolio-analysiscxcscmu/SkillLearnBenchAnalyzing fund portfolios including AUM extraction, holdings counts, and portfolio compositionAlteleFără avertismente★ 91↓ —
- pet-friendly-filteringcxcscmu/SkillLearnBenchFiltering accommodations for pet-friendly stays by analyzing house_rules field in accommodation data.AlteleFără avertismente★ 91↓ —
- offline-queuershankras/claude-code-apple-skillsGenerates an offline operation queue with persistence, automatic retry on connectivity, and conflict resolution. Use when user needs offline-first behavior, queued mutations, or pending operations that sync when back online.AlteleFără avertismente★ 840↓ —
- flux-healthtonone-ai/tononeData quality and pipeline health check — freshness, schema drift, null rates, orphaned records, pipeline status. Use when asked about "data quality check", "pipeline health", "is our data fresh", or "schema drift".AlteleFără avertismente★ 76↓ —
- simpo-losscxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.AlteleFără avertismente★ 91↓ —
- zero-audittonone-ai/tononeAudit an existing environment against zero trust principles — find implicit trust and over-privileged access. Use when asked to "audit against zero trust", "find implicit trust", or "find over-privileged access".AlteleFără avertismente★ 76↓ —
- promoted-iaprshankras/claude-code-apple-skillsGenerates Promoted In-App Purchase setup with StoreKit 2 product configuration, paywall integration, and App Store product page display. Use when setting up promoted purchases that appear on the App Store product page.AlteleFără avertismente★ 840↓ —
- 13f-fund-searchcxcscmu/SkillLearnBenchSearch for hedge funds in SEC 13F filings by fuzzy name matching. Use this skill whenever you need to find a fund's accession number by name (e.g., "Renaissance Technologies", "Berkshire Hathaway"). Returns accession_number to use with fund analysis.AlteleFără avertismente★ 91↓ —
- budget-managementcxcscmu/SkillLearnBenchTrack and manage travel budget across accommodations, meals, and activitiesAlteleFără avertismente★ 91↓ —
- hunt-ntlm-infoadriannoes/awesome-agentic-aiAgentic AI knowledge hub: 408 Cursor/Claude/Codex skills, 108 papers, 201 ML notebooks, 9 textbooks, 112 curated repos, 5,380 OpenClaw skills. Vendored skills + link-only catalogs. Start at AGENTS.md.AlteleFără avertismente★ 89↓ —
- lapsed-userrshankras/claude-code-apple-skillsGenerates lapsed user detection and re-engagement screens with personalized return experiences, win-back offers, and inactivity tracking. Use when user wants to re-engage inactive users, detect lapsed users, or build return flows.AlteleFără avertismente★ 840↓ —
- swiftdata-inheritancershankras/claude-code-apple-skillsSwiftData class inheritance patterns for hierarchical models with type-based querying, polymorphic relationships, and when to choose inheritance vs enums. Use when designing SwiftData model hierarchies.AlteleFără avertismente★ 840↓ —
- 13f-searchcxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.AlteleFără avertismente★ 91↓ —
ardot-create-new-file
balabalabalading/huuuuuuho-skills
De la autor
**强制性前置条件** — 每次调用 `create_new_page` 工具之前,必须先调用此技能。 未经加载此技能,绝不能直接调用 `create_new_page`。 当用户想要在 Ardot 设计文件中创建新页面时触发。 关键词:在 Ardot 上下文中的"创建新页面"、"添加页面"、"新画布"。
Instalare
npx skills add balabalabalading/huuuuuuho-skills --skill ardot-create-new-file -a claude-code
Se instalează în .claude/skills/ardot-create-new-file/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 83
Fișiere (1)
- SKILL.md