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 5 ore
49.409 skill-uri
- openmeld-cliamplifthq/openmeldUse OpenMeld when a task needs Organization knowledge or Skills, Center Agent help, shared Spaces or Files, another Agent or computer, or scheduled cloud work. Also use for OpenMeld setup and Wake replies.InginerieFără avertismente★ 1,4 K↓ —
- minutes-debriefsilverstein/minutesPost-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording.AlteleFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- isca-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the evaluation of an ISCA paper — pinning simulator fidelity to the claims it must carry, documenting gem5-class configurations and sampling choices, selecting workload suites that represent the claim's domain, tuning baselines in good faith, and separating architectural effect from modeling artifact.ȘtiințăFără avertismente★ 1,4 K↓ —
- hf-cloud-sagemaker-iam-preflighthuggingface/skillsEnsure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.OficialDevOpsFără avertismente★ 11,3 K↓ —
- dac-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when deciding what belongs inside the six reviewed pages of an ACM/IEEE Design Automation Conference (DAC) Research Manuscript versus in an external repository, given DAC's tight 6+1 budget, its references-only seventh page, the double-blind constraint on any linked material, and the absence of a formal reviewed-appendix or artifact-badging track.DesignFără avertismente★ 1,4 K↓ —
- vpe-advisoralirezarezvani/claude-skillsUse when delivery is slowing, eng hiring is broken, team structure is unclear or you need to decide when to add an eng manager. Runs delivery_throughput_analyzer.py (DORA), eng_hiring_funnel_calculator.py and eng_team_structure_designer.py.AlteleFără avertismente★ 29,2 K↓ —
- cn-prd-reviewmohitagw15856/pm-claude-skillsPrepare for and run a product requirements review (需求评审 / PRD 评审会) the way Chinese internet teams do it: a pre-read the engineers, testers and designers can challenge, the questions each role will ask, the meeting run sheet and a written conclusion (通过 / 有条件通过 / 不通过). Use when asked 帮我准备需求评审, PRD 评审会怎么开, 评审前检查一下我的 PRD, 研发会问什么问题, or prepare my requirements review in Chinese. Produces a readiness check of the PRD, a role-by-role question bank with answer points, a 60-minute run sheet, and the review minutes template with the conclusion and follow-ups.PlanificareFără avertismente★ 1,5 K↓ —
- icml-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when stress-testing ICML experimental evidence before submission or rebuttal, including strong tuned baselines, mechanism-isolating ablations, seed variance and confidence intervals, compute disclosure, data leakage and split construction, reproducibility, negative results, and fit to ICML soundness, originality, and significance scoring.TestareFără avertismente★ 1,4 K↓ —
- minutes-live-sidekicksilverstein/minutesAct as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.AlteleFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- corl-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing experiments for a CoRL robot-learning paper — seeds and evaluation-episode counts, task-suite breadth, real-robot versus simulation evidence, sim-to-real gap measurement, baseline fairness across BC/RL/VLA families, generalization splits, and statistics for success-rate claims.ȘtiințăFără avertismente★ 1,4 K↓ —
- hri-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when drafting or revising an ACM/IEEE HRI full paper's structure and prose for an interdisciplinary audience — leading with the human-robot contribution and research questions, making hypotheses and measures explicit, describing the robot embodiment, keeping claims proportional to the study within the 8-page acmart budget, and writing so the chosen track's contribution type is unmistakable.RedactareFără avertismente★ 1,4 K↓ —
- manage-desktop-flowsmicrosoft/power-platform-skillsManage and run Power Automate Desktop (RPA) flows and machine groups. Use when the user asks about desktop flows, RPA, or machine groups.AlteleFără avertismente★ 1,1 K↓ —
- plan-campaigngooseworks-ai/goose-skillsCampaign planner: turns a product, offer, goal, budget and date into a plan the marketer can approve and a designer can start from today, with every channel kept or dropped for a reason. Zero paid is a valid answer; it never spends. Use when the ask names a campaign, a launch, drop or season push, a budget or a date: I have this budget and a launch date — what do I run, where?; plan my launch, drop or Black Friday push; plan a campaign; how should I split $5k; plan next month's campaign; our CAC blew up — replan. Not for a broad "grow my brand", "get more customers" or "where do I start" with no campaign, budget or date — use where-to-start; not for pausing ads on a sold-out product — use run-paid-campaigns; not for an email-only send plan — use email-lifecycle; not for reading this week's numbers — use analyze-performance.MarketingFără avertismente★ 1,3 K↓ —
- minutes-recordsilverstein/minutesStart or stop recording a meeting, call, or voice memo. Use this whenever the user says "record", "start recording", "capture this meeting", "stop recording", "I'm in a meeting", "take notes on this call", or wants to transcribe live audio. Also use when they ask about recording status or want to know if something is being recorded.MediaFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- rekallhashgraph-online/awesome-codex-pluginsCompact the current Codex VS Code extension thread through Rekall with a verified handoff and optional one-time continuation. Use on an explicit compaction request or after a substantial completed stage; standalone Codex CLI sessions are unsupported.InginerieFără avertismente★ 1,5 K↓ —
- osdi-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the evaluation of an OSDI submission — choosing mature baselines and realistic workloads, structuring the section around research questions, measuring scalability and tail behavior, quantifying the design's costs, and fitting the evidence into the 12-page reviewed body.DesignFără avertismente★ 1,4 K↓ —
- uai-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when revising a UAI manuscript for probabilistic-inference readers, enforcing precise notation for distributions, graphs, and interventions, explicit assumption and identifiability statements, an 8-page main part that carries the whole argument while proofs sit in the appendix, and claims calibrated to what the theory and experiments show.RedactareFără avertismente★ 1,4 K↓ —
- soda-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when deciding whether and how experiments belong in a SODA (ACM-SIAM Symposium on Discrete Algorithms) paper — SODA's scope includes experimental validation but theorems carry the decision, so this skill designs supporting numerics honestly and routes implementation-led work to co-located ALENEX or to SEA.ȘtiințăFără avertismente★ 1,4 K↓ —
- edbt-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing EDBT empirical evaluations for database-systems work, covering real workloads and datasets, fair and tuned baselines, honest measurement across realistic scales, reproducible harnesses, and the higher bar of the Experiments & Analysis paper where the measurement itself is the contribution.DateFără avertismente★ 1,4 K↓ —
- cscw-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the empirical work behind a CSCW paper — interview and ethnographic rigor, trace and log analysis, surveys, deployments, and mixed methods — matching each method's own validity standard and the ethics of studying real communities.DevOpsFără avertismente★ 1,4 K↓ —
- iclr-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing ICLR experiments, including baselines, ablations, scaling laws, robustness, statistics, benchmarks, human evaluation, and compute reporting. Use when a reviewer questions whether a representation-learning or model gain is real, when you must isolate one mechanism with an ablation, or when preparing a small compute-matched control that can be posted inline during the public discussion period.AlteleFără avertismente★ 1,4 K↓ —
- varg-tryon-videoNouhashgraph-online/awesome-codex-pluginsTurns a flat-lay or product photo of clothing into a try-on video on varg: clean the garment photo, dress a model photo in it with Bria Virtual Try-On (or a Nano Banana / GPT Image edit for harder garments), keep the same model across shots, then animate fit-check motions that sell clothes (slow turn, tug and let fall, walk to camera, mirror selfie, fabric close-up) on Kling 4 or Seedance 2.5 with the garment kept intact, and add size captions so the fit is honest. Use when a fashion or apparel seller (Shopify, TikTok Shop, Amazon, dropshipping) asks for a try-on video, "my clothes on a model", an AI model wearing their product, a fit-check or outfit video, a try-on haul, or virtual try-on from flat-lays. Not for accessories that need no body (use product-photo-to-video) or for consistent characters across a story (varg-character-design).MediaFără avertismente★ 1,5 K↓ —
- plan-campaign-channel-decisiongooseworks-ai/goose-skillsStep of the plan-campaign playbook: marks each candidate channel Run, Test, Later or No with a brand-fact reason and founder hours. Run plan-campaign instead; not for direct use.MarketingFără avertismente★ 1,3 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↓ —
02-rl-reward
agentscope-ai/OpenJudge
ProductivitateActualizat acum 19 ore
De la autor
Build 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.
Instalare
npx skills add agentscope-ai/OpenJudge --skill 02-rl-reward -a claude-code
Se instalează în .claude/skills/02-rl-reward/ · 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 (3)
- SKILL.md
- pairwise.md
- pointwise.md