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.
48.168 de skill-uri din 2.325 de depozite · actualizat acum 24 de minute
47.055 de skill-uri
- 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★ 11,2 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★ 11,2 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★ 11,2 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★ 11,2 K↓ —
- add-opencodenanocoai/nanoclawUse OpenCode as an agent provider. OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per group via `ncl groups config update --provider opencode`; host passes OPENCODE_* and XDG mount when spawning containers.AlteleFără avertismente★ 31,1 K↓ —
- where-to-start-situation-savegooseworks-ai/goose-skillsStep of the where-to-start playbook: saves the founder's answers and the agreed first move with the brand, so later visits and other playbooks don't ask again. Run where-to-start instead; not for direct use.AlteleFără avertismente★ 1,3 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★ 11,2 K↓ —
- managing-upmohitagw15856/pm-claude-skillsWork more effectively with your manager — communicate, align, escalate, and get what you need. Use when asked how to manage up, work better with a boss, get buy-in from your manager, escalate without overstepping, or prepare to raise something with leadership. Produces a managing-up plan — what your manager needs and how they operate, how to frame your ask, what to bring vs. escalate, and the message.PlanificareFără avertismente★ 1,5 K↓ —
- add-oneclinanocoai/nanoclawInstall or refresh OneCLI as NanoClaw's gateway provider. Use when setup selects OneCLI, an existing OneCLI-backed install is migrated to the gateway seam, or its runtime, approval bridge, setup, and agent guidance must be restored from the in-tree package.AlteleFără avertismente★ 31,1 K↓ —
- correctNouhashgraph-online/awesome-codex-pluginsFind mistake classes agents keep repeating in this repository and block each with the strongest mechanism available (structure, then types and lint, then tests, docs last). Use for "/correct", "agents keep making the same mistake here", or after a repeated correction.TestareFără avertismente★ 1,5 K↓ —
- write-outreachgooseworks-ai/goose-skillsCold outreach a person sends to business buyers: email and LinkedIn sequences, a first line per prospect, reply and objection answers, and a read of replies. Use when the marketer says "write a cold email sequence", "what do I send to this list", "write LinkedIn messages for these leads", "how do I reply to this prospect" or "handle this objection", "reply to this demo request", "win back or reconnect with accounts that churned or went quiet", or "why is nobody replying to my outreach". Drafts only; the marketer sends from their own tool. Not for finding the people — use research-audience; not for emails to subscribers or users, or consumer win-back — use email-lifecycle.RedactareFără avertismente★ 1,3 K↓ —
- add-codexnanocoai/nanoclawUse Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).PlanificareFără avertismente★ 31,1 K↓ —
- experiment-designeralirezarezvani/claude-skillsUse when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.TestareFără avertismente★ 29,1 K↓ —
- twitter-cardskostja94/marketing-skillsWhen the user wants to add, audit, implement, or optimize Twitter Card metadata for X link previews, including twitter:card, twitter:title, twitter:description, twitter:image, or X previews. For a full metadata lifecycle use page-metadata; for broader social previews use open-graph.MediaFără avertismente★ 1,1 K↓ —
- deployment-config-guidealibaba/skill-upAsk for missing deployment settings and summarize the requested configuration without deploying it.DevOpsFără avertismente★ 1,4 K↓ —Apare și în 1 alt depozit
- learn-my-brandgooseworks-ai/goose-skillsLearn my brand once and stop asking me every time. Use when someone says learn my brand, set up my brand, here's our brand book, remember how we talk, what can we claim, can we say this, approve our claims, sign off our voice, our price or product changed, the client approved the claims, pick up where we left off, or check our claims are still current. Reads what GooseWorks already found about the brand, asks only the gaps as drafts to confirm, audits every claim (including ones research marked approved) and gets the ones that matter signed off with proof, scope and review date, turns the voice into rules the owner confirms, checks logo, colours and fonts, and saves it all as it goes so every other job loads it instead of asking. Ends with an unknowns list and a read-back. Not for who our customers are and what they say (use research-audience) or writing positioning from scratch (not covered yet).ȘtiințăFără avertismente★ 1,3 K↓ —
- ship-gateActualizatalirezarezvani/claude-skillsUse before deploying or going live ('am I ready to ship', 'can I deploy', 'preflight check'). Scans the codebase with ship_gate_scanner.py across security, database, deploy, AI, dependencies and observability, and blocks on critical items.SecuritateFără avertismente★ 29,1 K↓ —
- carouselkostja94/marketing-skillsDeprecated compatibility entry for Carousel construction. This component is now maintained in Bricks; install and use component-builder to build a new Carousel.AlteleFără avertismente★ 1,1 K↓ —
- senior-fullstackActualizatalirezarezvani/claude-skillsUse when starting a fullstack project, choosing a stack (Next.js, FastAPI, MERN, Django) or auditing a codebase's quality. Picks the stack with fullstack_decision_engine.py, scaffolds with project_scaffolder.py and scores code with code_quality_analyzer.py.InginerieFără avertismente★ 29,1 K↓ —
- oma-recapfirst-fluke/oh-my-agentAnalyze conversation histories from multiple AI tools (Claude, Codex, Gemini, Qwen, Cursor) and generate themed daily/period work summaries. Filter by date or time window.ProductivitateFără avertismente★ 1,4 K↓ —
- youtube-scriptmohitagw15856/pm-claude-skillsWrite a long-form video script for YouTube — an explainer, tutorial, video essay, review, or talking-head — built on the packaging→cold-open→value-stack→retention structure that holds watch-time past the drop-off cliffs. Use when asked to script a YouTube video, write a long-form or explainer/tutorial video script, outline a video essay, or turn a blog post/talk into a video. Produces title + thumbnail concepts, a timed cold open, a segmented body with retention devices and B-roll cues, integrated CTAs, an outro/end-screen, and a description with chapter timestamps. Distinct from [[short-form-script]] (15–60s vertical).MediaFără avertismente★ 1,5 K↓ —
- brandingkostja94/marketing-skillsWhen the user wants to define, audit, or apply brand strategy—purpose, values, positioning, storytelling, voice, narrative (not only visuals). Also use when the user mentions "brand strategy," "brand story," "brand storytelling," "brand voice," "brand identity," "brand guidelines," "brand purpose," "brand values," "origin story," "brand narrative," "brand personality," "brand archetype," "slide deck branding," "PPT brand colors," or "document style guide." For typography, colors, design tokens, and frontend visuals, use brand-visual-generator.DocumenteFără avertismente★ 1,1 K↓ —
- nostr-vpnNoummalmi/nostr-vpnConnect an authorized machine to a Nostr VPN private mesh, review device join requests, and verify access with the nvpn CLI. Use for account-free private networking between agent hosts, people, and servers.InginerieFără avertismente★ 1,2 K↓ —
- wake-traceamplifthq/openmeldUse when diagnosing a Wake that failed, stalled, or produced no visible reply — dispatch, setup handoff, or reply-path issues. Routes to the deterministic trace evidence path.AlteleFără avertismente★ 1,4 K↓ —
finetuning
evo-hq/evo
DesignActualizat 5 oct. 2026
De la autor
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.
Instalare
npx skills add evo-hq/evo --skill finetuning -a claude-code
Se instalează în .claude/skills/finetuning/ · 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 instrucțiuniNu am văzut acces la rețeaLicență: APACHE-2.0
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență78
Întreținere100
Licență100
Adopție51
Fișiere (9)
- SKILL.md
- references/diagnostics.md
- references/false-progress.md
- references/glue.md
- references/observability.md
- references/rl/art.md
- references/serving/vllm.md
- references/sft/tinker.md
- references/trace-schema.md