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.
49.395 de skill-uri din 2.375 de depozite · actualizat acum 18 minute
6.335 de skill-uri
- prp-core-runnerMicrock/ordinary-claude-skillsOrchestrate complete PRP workflow from feature request to pull request. Run create branch, create PRP, execute implementation, commit changes, and create PR in sequence. Use when implementing features using PRP methodology or when user requests full PRP workflow.InginerieFără avertismente★ 409↓ —
- cookbook-auditMicrock/ordinary-claude-skillsAudit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.InginerieFără avertismente★ 409↓ —
- geminiMicrock/ordinary-claude-skillsExecute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for complex reasoning tasks.InginerieFără avertismente★ 409↓ —
- Hook Developmenttzachbon/smart-ralphThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.InginerieFără avertismente★ 566↓ —Apare și în 1 alt depozit
- reviewheliohq/shipStatic code review of the active diff: trace changed paths and report concrete P1/P2/P3 correctness, security, or spec bugs with file:line evidence. Use for code review or bug checks. Not runtime QA.InginerieFără avertismente★ 93↓ —
- reviewtance-mang/chinese-webnovel-skills中文网文审稿与追读诊断。当用户要审稿、检查剧情漏洞、查伏笔有没有回收、人设是否前后一致、爽点密度够不够、或想知道"读者为什么追读会掉/这章为什么留不住人"时使用。产出数据化诊断报告和可执行的修改建议。InginerieFără avertismente★ 96↓ —
- Hooks AutomationMicrock/ordinary-claude-skillsAutomated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.InginerieFără avertismente★ 409↓ —Apare și în 1 alt depozit
- receiving-code-reviewjamditis/claude-skills-journalismVerifies review feedback with technical rigor, not blind agreement. Use when receiving review before implementing suggestions.InginerieVerifică întâi★ 444↓ —
- code-reviewJasonxzWen/harness-hubLoad when a task needs a deep, report-only review across independent Standards and Spec axes, using bounded read-only native Subagents when available and adding risk lenses only when the diff warrants them.InginerieFără avertismente★ 71↓ —
- creating-kboaustegard/claude-skillsBuilds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained `.skill` bundle (BM25 index + bundled searcher + query protocol). Use when a user wants to turn uploaded files, a folder, or a corpus into a searchable knowledgebase they can hand to any agent — phrased as "make a knowledgebase", "build a KB skill", "package these docs for retrieval", "create a searchable bundle", or references to a `.skill` KB. The output runs anywhere with Node or Python — no model, no install, no network. Distinct from `bm25` (ephemeral in-session search) and `building-github-index` (markdown project-knowledge index).InginerieFără avertismente★ 158↓ —Apare și în 1 alt depozit
- post-incident-reviewUnitOneAI/SecuritySkillsConducts a structured post-incident review following NIST SP 800-61 Rev 2 Post-Incident Activity guidance. Auto-invoked when an incident has been resolved and the team needs to conduct a blameless retrospective, reconstruct the timeline, perform root cause analysis, document lessons learned, and track remediation actions. Produces a PIR report with metrics (MTTD, MTTR, MTTC), control failure mapping, and actionable improvement plan.InginerieFără avertismente★ 97↓ —
- hardenComeOnOliver/skillshub🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.InginerieFără avertismente★ 65↓ —
- pci-dss-reviewUnitOneAI/SecuritySkillsPerforms a PCI DSS v4.0 compliance review across all 12 requirements and their sub-requirements. Auto-invoked when discussing payment card security, cardholder data protection, PCI compliance validation, or merchant/service provider assessment. Covers scope reduction strategies, SAQ vs ROC determination, compensating controls, customized approach, and the new targeted risk analysis requirements introduced in v4.0.InginerieFără avertismente★ 97↓ —
- explore-codelllllllama/RigorPilot-SkillsRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.InginerieFără avertismente★ 488↓ —
- discordComeOnOliver/skillshub🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.InginerieFără avertismente★ 65↓ —
- roller-webhookshookdeck/webhook-skillsReceive and authenticate ROLLER webhooks. Use when setting up a ROLLER venue or attraction ticketing webhook endpoint, verifying the x-roller-apikey header, debugging 401s, or handling booking, customer, redemption and payment-link events (body `type` plus `eventType`, e.g. type Booking with eventType Created).InginerieFără avertismente★ 97↓ —
- hunting-for-dns-based-persistence26zl/cybersec-toolkitHunt for DNS-based persistence mechanisms including DNS hijacking, dangling CNAME records, wildcard DNS abuse, and unauthorized zone modifications using passive DNS databases, SecurityTrails API, and DNS audit log analysis.InginerieFără avertismente★ 87↓ —
- uber-webhookshookdeck/webhook-skillsReceive and verify Uber Eats webhooks. Use when setting up Uber webhook handlers, debugging X-Uber-Signature verification, or handling order events like orders.notification, orders.cancel, store.provisioned, or store.status.changed.InginerieFără avertismente★ 97↓ —
- jobber-webhookshookdeck/webhook-skillsReceive and verify Jobber webhooks. Use when setting up Jobber app webhook handlers, debugging X-Jobber-Hmac-SHA256 signature verification, or handling field service topics like CLIENT_CREATE, INVOICE_UPDATE, APP_CONNECT, and APP_DISCONNECT.InginerieFără avertismente★ 97↓ —
- whop-webhookshookdeck/webhook-skillsReceive and verify Whop webhooks. Use when setting up Whop webhook handlers, debugging Standard Webhooks signature verification (webhook-id, webhook-timestamp, webhook-signature), or handling payment.succeeded, payment.failed, membership.activated, membership.deactivated, and refund.created events.InginerieFără avertismente★ 97↓ —
- mv-generatoraAAaqwq/AGI-Super-TeamAn installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters.InginerieFără avertismente★ 112↓ —
- repo-renamePaulRBerg/agent-skillsPreview or rename a GitHub repo, or move a local repo to another parent directory. Preserve Codex CLI and Claude Code continuity references.InginerieFără avertismente★ 104↓ —
- key-rotationaAAaqwq/AGI-Super-TeamAPI key rotation manager — rotate provider keys across all agent workspacesInginerieFără avertismente★ 112↓ —
- waha-webhookshookdeck/webhook-skillsReceive and verify WAHA (WhatsApp HTTP API) webhooks. Use when setting up a WAHA webhook endpoint, verifying the X-Webhook-Hmac header (HMAC-SHA512 hex of the raw body), debugging WAHA signature verification failures, or handling events like message, message.any, message.ack, message.reaction, session.status, group.v2.join and presence.update.InginerieFără avertismente★ 97↓ —