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.
48.622 de skill-uri din 2.355 de depozite · actualizat acum 11 ore
6.143 de skill-uri
- light-review-rebuttalLight0305/Light-skillsBuild auditable peer-review revision and author-response packages for Light stage 13. Use after receiving reviewer comments, a decision or meta-review; when drafting a rebuttal or response letter; when triaging major/minor revisions; when simulating a pre-submission review; or when a rejection may require a user-chosen 13→3 novelty, 13→5 experiment, or 13→8 writing back-edge. Consumes the selected venue/context and real PDF facts, preserves reviewer wording, atomizes issues, binds claims/evidence/actions/provenance, separates PLANNED from DONE, checks current venue limits without borrowing another venue's rules, and emits the stage-13 gate without changing venue, manuscript, evidence, citations, figures, PDF, or passport automatically.InginerieFără avertismente★ 842↓ —
- light-experiment-codingLight0305/Light-skillsLight 科研主线 stage 6：把冻结的 question/estimand、experiment matrix、pre-registration 与 data lineage 落成最小可运行、测试先行、无泄漏、可复现且能交给 result-analysis 的实验代码。用于实现或复现训练/预处理/评测， 设计 gold/property/metamorphic 测试，控制 Python/NumPy/框架/CUDA/DataLoader 随机性，审查 train/test 或 CV fit 穿越，记录 config/code/environment/input hashes、stdout/stderr、raw metrics、patient/entity predictions 与 failure artifacts，以及运行 stage-6 checkpoint。数据泄漏或不可复现是 critical；静态扫描和同 seed 两次一致都不证明跨硬件 绝对复现。InginerieFără avertismente★ 842↓ —
- light-idea-critiqueLight0305/Light-skillsLight 科研主线第 4 步·审 idea：以**顶会审稿人标准严审** idea，**撞车/无创新 fatal flaw 一票否决**(critical 门)， 逼出真能发表的 idea。何时用：用户问"这 idea 行不行/够不够新/能不能发""帮我严审/挑刺/找致命问题" / idea 定稿前把关 / 收到 idea-generation 的候选要审 / 怀疑撞车(被人做过)。触发词：审 idea / 评审 / 严审 / 挑刺 / 这 idea 行不行 / 够不够新 / 创新性 / 撞车 / 被做过了吗 / 致命问题 / 能投顶会吗 / 拒稿风险 / critique my idea / review this idea / is this novel / fatal flaw / 一票否决。核心纪律：**撞车/无创新的 critical 一票否决在本技能**(不被其他高维度平均救回)； **硬性反谄媚**(不被作者反复反驳顺从放行弱 idea)；撞车判定**target/background 可追溯分解**非"感觉像"；judge 不靠裸 自评(用可计算否决闸门 + 密度先验 + pairwise)。**消费上游 idea-generation 的撞车 findings + facet 槽位**。InginerieFără avertismente★ 842↓ —
- labarchive-integrationKalarisLabs/research-agent-skillsSecurely integrate with the official LabArchives ELN REST-like API and Inventory API v1. Use for regional endpoint selection, signed-request construction, user authorization and UID flows, local LA container validation, and verified LabArchives integration workflows.InginerieFără avertismente★ 84↓ —
- payt-webhooksNouhookdeck/webhook-skillsReceive and verify Payt webhooks. Use when setting up a Payt webhook endpoint, debugging X-PAYT-SIGNATURE verification, or handling accounts-receivable events like invoice_created, invoice_paid, invoice_payment_created, case_created and bundled_reminder_sent.InginerieFără avertismente★ 97↓ —
- detecting-shadow-api-endpoints26zl/cybersec-toolkitDiscover and inventory shadow API endpoints that operate outside documented specifications using traffic analysis, code scanning, and API discovery platforms.InginerieFără avertismente★ 87↓ —
- analyzing-api-gateway-access-logs26zl/cybersec-toolkitParses API Gateway access logs (AWS API Gateway, Kong, Nginx) to detect BOLA/IDOR attacks, rate limit bypass, credential scanning, and injection attempts. Uses pandas for statistical analysis of request patterns and anomaly detection. Use when investigating API abuse or building API-specific threat detection rules.InginerieFără avertismente★ 87↓ —
- hunting-for-cobalt-strike-beacons26zl/cybersec-toolkitDetect Cobalt Strike beacon network activity using default TLS certificate signatures (serial 8BB00EE), JA3/JA3S/JARM fingerprints, HTTP C2 profile pattern matching, beacon jitter analysis, and named pipe detection via Zeek, Suricata, and Python PCAP analysis.InginerieFără avertismente★ 87↓ —
- performing-api-fuzzing-with-restler26zl/cybersec-toolkitUses Microsoft RESTler to perform stateful REST API fuzzing by automatically generating and executing test sequences that exercise API endpoints, discover producer-consumer dependencies between requests, and find security and reliability bugs. The tester compiles an OpenAPI specification into a RESTler fuzzing grammar, configures authentication, runs test/fuzz-lean/fuzz modes, and analyzes results for 500 errors, authentication bypasses, resource leaks, and payload injection vulnerabilities. Activates for requests involving API fuzzing, RESTler testing, stateful API testing, or automated API security scanning.InginerieFără avertismente★ 87↓ —
- push-preflight0xDarkMatter/claude-modsSecret-scans the commits a git push would send (gitleaks + regex layer; never history), then checks clean tree, forbidden files and fast-forward, with size and open-issue advisories. Refuses on any secret hit, no bypass. Triggers on: push to origin, push to github, push to remote, git push, can we push, safe to push, ready to push, pre-push check, /push-preflight (formerly push-gate).InginerieFără avertismente★ 80↓ —
- alterlab-pubmedAlterLab-IEU/AlterLab-Academic-SkillsProvide direct REST API access to PubMed via the NCBI E-utilities API, supporting advanced Boolean/MeSH queries, batch processing, and citation management. Use when searching biomedical literature by MeSH terms, retrieving abstracts or PMIDs in bulk, or scripting custom PubMed queries over raw HTTP/REST — for Python workflows prefer biopython (Bio.Entrez) instead, use this for direct REST work or custom API implementations. Part of the AlterLab Academic Skills suite.InginerieFără avertismente★ 82↓ —
- clerk-webhookshookdeck/webhook-skillsReceive and verify Clerk webhooks. Use when setting up Clerk webhook handlers, debugging signature verification, or handling user events like user.created, user.updated, session.created, or organization.created.InginerieFără avertismente★ 97↓ —
- stable-baselines3KalarisLabs/research-agent-skillsProduction-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.InginerieFără avertismente★ 84↓ —
- python-cli-ops0xDarkMatter/claude-modsCLI application patterns for Python. Triggers on: cli, command line, typer, click, argparse, terminal, rich, console, terminal ui.InginerieFără avertismente★ 80↓ —
- copy-transcript-pathPaulRBerg/agent-skillsCopy the active Claude Code or Codex CLI chat transcript path to the macOS clipboard.InginerieFără avertismente★ 104↓ —
- nango-webhookshookdeck/webhook-skillsReceive and verify Nango webhooks. Use when setting up Nango webhook handlers, debugging X-Nango-Hmac-Sha256 signature verification (HMAC-SHA256 hex of the raw body, keyed with the environment's webhook signing key, not the API key), or handling Nango webhook types: auth (connection creation, override, refresh, deletion), sync (sync run succeeded or failed), forward (external API webhooks forwarded through Nango), and async_action.InginerieFără avertismente★ 97↓ —
- ada-webhookshookdeck/webhook-skillsReceive and verify Ada (ada.cx) AI customer service webhooks, delivered through Svix. Use when setting up an Ada webhook endpoint, getting the per-endpoint whsec_ signing secret, debugging svix-id / svix-timestamp / svix-signature verification, or handling events like v1.conversation.created, v1.conversation.message, v1.conversation.ended, v1.conversation.handoff.ended, v1.end_user.created, v1.end_user.updated, v1.audit_log.emitted and v1.proactive_call.* voice outreach events.InginerieFără avertismente★ 97↓ —
- box-webhooksNouhookdeck/webhook-skillsReceive and verify Box V2 webhooks. Use when setting up Box webhook handlers, debugging BOX-SIGNATURE-PRIMARY verification, or handling events like FILE.UPLOADED, FILE.DOWNLOADED, FILE.TRASHED, FOLDER.CREATED, COMMENT.CREATED, COLLABORATION.CREATED, and SIGN_REQUEST.COMPLETED.InginerieFără avertismente★ 97↓ —
- claude-api-ops0xDarkMatter/claude-modsBuilding applications ON Claude - the Anthropic API and Claude Agent SDK. Use for: anthropic api, claude api, messages api, tool use, function calling, prompt caching, agent sdk, claude-agent-sdk, structured output, json schema output, batches api, extended thinking, adaptive thinking, model selection, claude pricing, build claude agent, anthropic sdk, stop_reason handling, streaming claude, token counting, cache_control, output_config, tool_choice, agentic loop, rate limits anthropic, context engineering, context window budget, compaction, context editing, context_management, clear_tool_uses, memory tool, context rot, tool result bloat, subagent context isolation.InginerieFără avertismente★ 80↓ —
- minimax-ttsaAAaqwq/AGI-Super-TeamText-to-speech synthesis via MiniMax WebSocket APIInginerieFără avertismente★ 112↓ —
- ebay-webhookshookdeck/webhook-skillsReceive and verify eBay Notification API webhooks (Platform Notifications / Event Notifications). Use when setting up an eBay webhook endpoint, passing the endpoint challenge validation, debugging the x-ebay-signature ECDSA verification, fetching the public key with getPublicKey, or handling events like MARKETPLACE_ACCOUNT_DELETION.InginerieFără avertismente★ 97↓ —
- lago-webhookshookdeck/webhook-skillsReceive and verify Lago webhooks in HMAC mode. Use when setting up Lago webhook handlers, debugging X-Lago-Signature verification, or handling usage billing events like invoice.created, subscription.started, or wallet.depleted_ongoing_balance.InginerieFără avertismente★ 97↓ —
- skills-searchaAAaqwq/AGI-Super-TeamSearch skills.sh registry from CLI. Find and discover agent skills from the skills.sh ecosystem.InginerieFără avertismente★ 112↓ —
- make-webhooksNouhookdeck/webhook-skillsReceive and authenticate requests sent by Make (formerly Integromat) scenarios through the HTTP > Make a request module. Use when building an endpoint that a Make scenario calls, securing it with an API key keychain header, debugging 401s from Make, or routing scenario payloads by an event field such as order.created or scenario.failed.InginerieFără avertismente★ 97↓ —