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.
49.409 skill-uri din 2.375 de depozite · actualizat acum 30 de minute
48.362 de skill-uri
- hephaestus-buildagentlas-ai/Agentlas-OSUse when the user types /prompts:hep-build or /agentlas-build, mentions @Hephaestus for build work, asks to create a single Agentlas agent, create a multi-agent team, or package an existing local/external agent into Agentlas architecture.PlanificareFără avertismente★ 1,6 K↓ —
- agentlas-stormagentlas-ai/Agentlas-OSRun a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion.AlteleFără avertismente★ 1,6 K↓ —
- mode-classificationagentlas-ai/Agentlas-OSUse before routing a /meta-agent request to choose single-agent-creator, team-builder, or agentlas-packager from the user's wording and available files.AlteleFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- openmeld-changelogamplifthq/openmeldMaintain the official OpenMeld Changelog from repository evidence. Use when deciding whether a change needs a Changelog entry, writing or publishing an entry, preparing release notes, validating generated Changelog files, or historically backfilling missing changes.RedactareFără avertismente★ 1,4 K↓ —
- webmcp-genfcakyon/claude-codex-settingsBuild and validate experimental WebMCP tools for an existing web page. Use when an agent needs to expose a site's real workflows as page tools, create webmcp.init.js, define deterministic checks, or compare WebMCP with accessibility-tree automation.AlteleFără avertismente★ 1,2 K↓ —
- hf-cloud-sagemaker-production-defaultshuggingface/skillsCreate a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.OficialDevOpsFără avertismente★ 11,3 K↓ —
- orchestrating-agent-relayAgentWorkforce/relayThe canonical way to run agent-relay - self-bootstrap the local broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, message-based reading via the relay MCP, and team coordination.DevOpsFără avertismente★ 1,1 K↓ —
- creating-claude-agentsAgentWorkforce/relayUse when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.InginerieFără avertismente★ 1,1 K↓ —
- implementing-command-palettesAgentWorkforce/relayUse when building Cmd+K command palettes in React - covers keyboard navigation with arrow keys, keeping selected items in view with scrollIntoView, filtering with shortcut matching, and preventing infinite re-renders from reference instabilityMediaFără avertismente★ 1,1 K↓ —
- clean-gone-branchesfcakyon/claude-codex-settingsThis skill should be used when user asks to "clean gone branches", "remove deleted local branches", "prune branches removed from remote", or explicitly invokes "clean-gone-branches".AlteleFără avertismente★ 1,2 K↓ —
- app-authNoufcakyon/claude-codex-settingsThis skill should be used when the user asks to "standardize app authentication", "share login across web, mobile and TV", "reuse the Google login flow", "simplify signup", "fix password recovery", or "fix popup-blocked login". Use shared account/session contracts, email and Google web adapters, and an optional auth panel. Native and TV flows are integration contracts awaiting device validation.ProductivitateFără avertismente★ 1,2 K↓ —
- hf-cloud-python-env-setuphuggingface/skillsSet up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.OficialInginerieFără avertismente★ 11,3 K↓ —
- huggingface-vision-trainerhuggingface/skillsTrains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.OficialMediaFără avertismente★ 11,3 K↓ —
- huggingface-community-evalshuggingface/skillsRun evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.OficialAlteleFără avertismente★ 11,3 K↓ —
- huggingface-paper-publisherhuggingface/skillsPublish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.OficialȘtiințăFără avertismente★ 11,3 K↓ —
- train-sentence-transformershuggingface/skillsTrain or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.OficialProductivitateFără avertismente★ 11,3 K↓ —
- senior-backendActualizatalirezarezvani/claude-skillsBuild and fix backend services: REST or GraphQL APIs, auth, microservices, PostgreSQL queries, migrations and load tests. Use whenever the user's API is slow or broken, needs login or auth added, a schema change, or a new endpoint or service scaffolded.TestareFără avertismente★ 29,2 K↓ —
- planning-with-filesActualizatOthmanAdi/planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; agent instructions read selected project planning context when invoked. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. This adapter registers no lifecycle or Stop hook, never requests continuation, and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.PlanificareFără avertismente★ 27,9 K↓ —
- signup-flow-croalirezarezvani/claude-skillsUse when signup, registration or trial-start conversion is low or a signup flow is being designed. Finds the drop-off step with funnel_drop_analyzer.py and removes friction field by field.MarketingFără avertismente★ 29,2 K↓ —
- git-worktree-manageralirezarezvani/claude-skillsUse when running several branches or agents in parallel on one repo. Creates worktrees with isolated ports and env via worktree_manager.py and removes stale ones with worktree_cleanup.py.InginerieFără avertismente★ 29,2 K↓ —
- agentlas-networkagentlas-ai/Agentlas-OSStaff a task from registered Local, owner Cloud, and public Hub agents.ProductivitateFără avertismente★ 1,6 K↓ —
- session-agent-builderagentlas-ai/Agentlas-OSTurn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit terminal and automation runs.AlteleFără avertismente★ 1,6 K↓ —Apare și în 5 alte depozite
- threat-detectionalirezarezvani/claude-skillsUse when hunting threats, sweeping IOCs or looking for anomalies in logs and telemetry. Ranks ATT&CK-mapped signals and z-score anomalies with threat_signal_analyzer.py.AlteleFără avertismente★ 29,2 K↓ —
- nda-analysermohitagw15856/pm-claude-skillsAnalyses a Non-Disclosure Agreement clause by clause and flags unusual terms, one-sided provisions, and negotiation points. Use when reviewing an NDA, mutual NDA, confidentiality agreement, or non-disclosure deed before signing or countering. Produces a plain English verdict, clause-by-clause risk analysis, and a prioritised negotiation checklist — always with a disclaimer that qualified legal advice is required before signing.JuridicFără avertismente★ 1,5 K↓ —
02-ref-hallucination-arena
agentscope-ai/OpenJudge
ȘtiințăActualizat acum 13 ore
De la autor
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
Instalare
npx skills add agentscope-ai/OpenJudge --skill 02-ref-hallucination-arena -a claude-code
Se instalează în .claude/skills/02-ref-hallucination-arena/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniFolosește rețeauaLicență: APACHE-2.0
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență76
Întreținere100
Licență100
Adopție49
Fișiere (1)
- SKILL.md