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 2 ore
49.409 skill-uri
- metric-designagentscope-ai/OpenJudgeUse when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.DesignFără avertismente★ 1 K↓ —
- 02-rl-rewardagentscope-ai/OpenJudgeBuild RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.ProductivitateFără avertismente★ 1 K↓ —
- greploop-appsmichaelshimeles/rstackRun the greploop workflow with the @greptile-apps trigger when the normal trigger refuses a large PR. Requires the greploop skill installed alongside this entrypoint.ProductivitateFără avertismente★ 1,4 K↓ —
- planning-with-filesOthmanAdi/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↓ —
- documenthashgraph-online/awesome-codex-pluginsRecord a decision, document existing code, or file a supplied research material. Modes: document decision (ADR, RFC, or rule), document code (spec, doc, guide, or scenario for existing behavior), document research (only when a finished report or one external material is already in hand). Use for 'we decided', 'record this decision', 'document why we chose X', 'make it our standard', 'draft an RFC', 'should we switch to Y' proposals, 'resolve the RFC', 'we accepted the proposal', 'document the auth module', 'capture how the payment system works', reference material, how-to instructions, or a user flow with examples over an existing spec. Name the type inside the subject to skip the type question. Planning a feature or an intended user journey → /archcore:plan. Checking docs against code or docs health → /archcore:review.ȘtiințăFără avertismente★ 1,5 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↓ —
- seohashgraph-online/awesome-codex-pluginsFix SEO problems Loomaly ranks first: status → todo (fix is on the top item) → change code on a branch → check target fix with the PR link. For solo and developers.MarketingFără avertismente★ 1,5 K↓ —
- 02-ref-hallucination-arenaagentscope-ai/OpenJudgeBenchmark 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.ȘtiințăFără avertismente★ 1 K↓ —
- minutes-lintsilverstein/minutesHealth-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history.AlteleFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- ai-model-nodejsActualizatTencentCloudBase/CloudBase-AI-ToolkitUse this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration. The only SDK supporting image generation (ai.createImageModel + generateImage). Text via ai.createModel with groups cloudbase, the legacy hunyuan-v3 / hunyuan-exp, or custom-*; model ids (e.g. deepseek-v4-flash, glm-5, kimi-k2.6) go in the `model` field of generateText/streamText. MUST run two-step preflight before code — see body. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).BrowserFără avertismente★ 1,2 K↓ —Apare și în 5 alte depozite
- 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↓ —
- 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↓ —
- brooks-sweephyhmrright/brooks-lintFull-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user wants to "fix everything", "sweep the codebase", "auto-fix all issues", "clean up the whole project", or asks for a single command that both diagnoses and remediates quality problems. Do NOT trigger for: read-only audits or health reports where the user only wants findings without code changes; single-dimension reviews (use the focused skill instead: brooks-review / brooks-audit / brooks-debt / brooks-test); server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime.TestareFără avertismente★ 1,6 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↓ —
- unslopmichaelshimeles/rstackCut AI tells from text you write or edit for a human reader (commit messages, PR titles and bodies, docs, code comments, replies). Apply before committing, posting, or sending; leave prose you didn't touch alone.RedactareFără avertismente★ 1,4 K↓ —
- cost-reporthoangsonww/Claude-Code-Agent-MonitorProduce a scoped CCAM cost and token report by model, provider, source, and session. Use for spend reviews, model-mix analysis, unpriced usage detection, or export-friendly cost summaries.ProductivitateFără avertismente★ 1,1 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↓ —
- flaky-skillalibaba/skill-upA skill with potentially flaky behavior for testing retryTestareFără avertismente★ 1,4 K↓ —
- transcreationmohitagw15856/pm-claude-skillsTranscreate marketing/brand copy for another language and culture — recreate the impact, not the words. Use when asked to adapt a tagline, ad, slogan, campaign, or brand message for a new market, or when a translation is 'correct but flat'. Produces a transcreated version that lands emotionally in-culture, with the strategic rationale, 2-3 options, and notes on what was changed and why.MarketingFără avertismente★ 1,5 K↓ —
- minutes-release-notessilverstein/minutesDraft user-facing Minutes release notes for a version from the commit range, recent GitHub releases, and the repository release checks. Use when the user asks to write, generate, prepare, revise, or review release notes or a changelog for a Minutes version.ProductivitateFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- one-pagermohitagw15856/pm-claude-skillsDistil anything — a startup, product, project, or idea — into a single persuasive page. Use when asked to make a one-pager, a one-page summary, a leave-behind, a startup/product one-sheet, or a tl;dr brief. Produces a structured single page — headline + tagline, the problem, the solution, why-now/proof, and a clear ask/CTA — designed to be skimmed and remembered, ready to export as a typeset PDF.DocumenteFără avertismente★ 1,5 K↓ —
- aamas-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an AAMAS main-track submission for OpenReview readiness, the 8-page-plus-references limit, the full-paper versus 2-page extended-abstract choice, double-blind anonymity, the supplementary zip cap, track fit across the AAAI/JAAMAS/Blue Sky tracks, dual-submission rules, and desk-reject triggers before upload.ȘtiințăFără avertismente★ 1,4 K↓ —
- clone-briefmohitagw15856/pm-claude-skillsSend your position to a meeting instead of your body — a one-page brief carrying your stances, fallbacks, red lines, tradables, and delegation limits, readable by the colleague (or agent) representing you. Use when you can't attend a decision-making meeting, when double-booked, when briefing someone to negotiate for you, or 'what would you need from me to represent me?'. Produces the clone brief plus a 60-second verbal version for the person carrying it.AlteleFără avertismente★ 1,5 K↓ —
- returner-cvmohitagw15856/pm-claude-skillsWrite a CV for someone returning to work after a career break (caring, health, parenting, travel, redundancy or anything else), presenting the gap honestly and briefly and leading with current, relevant evidence. Use when asked how do I explain a gap on my CV, write my CV after a career break, returning to work after maternity or caring, or my CV has a two-year gap. Produces a CV with the break stated in one plain line, recent evidence brought forward, a short spoken answer for interviews, and a list of returnship programmes and refreshers worth checking.RedactareFără avertismente★ 1,5 K↓ —
auto-research
huytieu/COG-second-brain
ȘtiințăActualizat 23 oct. 2026
De la autor
Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis
Instalare
npx skills add huytieu/COG-second-brain --skill auto-research -a claude-code
Se instalează în .claude/skills/auto-research/ · 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: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență77
Întreținere100
Licență100
Adopție50
Fișiere (1)
- SKILL.md