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 14 ore
47.055 de skill-uri
- app-iconNoudaveebbelaar/bamaLiquid Glass macOS app icon made as an Icon Composer file (Icon/AppIcon.icon, JSON plus SVG layers), compiled with actool, and reviewed in every look with ictool. Use when the user wants an app icon, a better icon, or a Dock icon.AlteleFără avertismente★ 1 K↓ —
- minutes-cleanupsilverstein/minutesManage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage meeting storage", or asks about disk space from minutes.AlteleFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- popl-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a POPL campaign calendar — backward-scheduling theory and mechanization from the July deadline, riding the October notification into the conditional-acceptance revision and artifact evaluation, landing the January conference, and retargeting across the SIGPLAN/PACMPL deadline wheel if July slips.ProductivitateFără avertismente★ 1,3 K↓ —
- gohashgraph-online/awesome-codex-pluginsCarry out the intent approved in `ready`, as meant, and prove it with checks that actually ran. Comes back to you if the work would change what you approved, keeps the project docs in step, and never merges on its own. Use when the user invokes the `go` skill after `ready`. Requires git.InginerieFără avertismente★ 1,5 K↓ —Apare și în 3 alte depozite
- openmeld-cliamplifthq/openmeldUse OpenMeld through its public CLI to work in Spaces, reply to a Wake, consult the Center Agent, connect this computer, manage Agent Profiles, or diagnose delivery.InginerieFără avertismente★ 1,4 K↓ —
- scenario-skyboxesscenario-labs/skillsUse when a task involves generating or iterating on skyboxes, 360 panoramas, equirectangular images, environment maps, HDRI-style backdrops, or VR backdrops through the Scenario MCP. Triggers include text-to-skybox, turning a photo into a 360 environment, restyling a panorama's mood, upscaling a skybox without breaking the seam wrap, or exporting equirectangular or cubemap layouts for game engines such as Unity, Unreal, or Godot.MediaFără avertismente★ 1,4 K↓ —
- year-in-reviewmohitagw15856/pm-claude-skillsRun an honest personal year-in-review and set next year's direction — wins, misses, an energy audit, and one theme, not a resolution list that dies in February. Use when asked for a personal year in review, a yearly reflection, to reflect on the past year, or plan next year. Produces the structured retrospective (what worked, what didn't, what you learned), an energy audit of what gave vs. drained you, the honest misses, and a single theme with a few concrete commitments. Personal, not corporate.InginerieFără avertismente★ 1,5 K↓ —
- graphifyhashgraph-online/awesome-codex-plugins将 Graphify 作为可选知识图谱能力接入，用于 brownfield 结构扫描、依赖路径分析与架构问答。 不替代 `/team-*` 主链；输出统一回落到 handoff 与 artifacts 证据。AlteleFără avertismente★ 1,5 K↓ —
- ux-designNoudaveebbelaar/bamaUX pass for one feature of a macOS app, covering names, flow, where it opens (inline, popover, sheet, window, alert), states, words, hover help, accessibility, and AI features. Use before coding a story that adds a screen, an action, or text, when user-stories or improve-loop call it, or when the user asks for a UX review, clearer wording, better names, or whether something should be a modal.DesignFără avertismente★ 1 K↓ —
- deep-researchjezweb/claude-skillsDeep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems, investigates technical options, and produces a comprehensive research brief. Three depths: focused (30 min), wide (1-2 hours), deep (3-6 hours). Triggers: 'research this', 'discovery', 'explore the space', 'what should I build', 'competitive analysis', 'before I start building', 'research before coding'. Not for cited fact-checking research reports (a separate harness does those); this is pre-build product discovery.ȘtiințăFără avertismente★ 1,1 K↓ —
- dac-related-workbrycewang-stanford/Awesome-Journal-SkillsUse when writing or auditing the related-work and positioning of an ACM/IEEE Design Automation Conference (DAC) Research Manuscript, covering the EDA literature lanes (DAC/ICCAD/DATE/ASP-DAC/TCAD/TODAES), delta-first positioning against the strongest prior tool, honest benchmark-suite lineage, and third-person self-citation under double-blind review within the six-page budget.DesignFără avertismente★ 1,3 K↓ —
- run-paid-campaigns-health-gategooseworks-ai/goose-skillsChecks that ads are safe to spend on: conversion tracking recording, landing pages loading on mobile with the right product, price and offer, enough stock behind promoted products, no disapproved ads, and no account or payment stop. Marks each pass, fail or unknown and turns fails into fixes. Use alone when you already have the live or planned ads and their landing pages; otherwise run run-paid-campaigns.FinanțeFără avertismente★ 1,3 K↓ —
- vis-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an IEEE VIS full-paper submission for PCS readiness, covering the abstract-then-paper two-deadline structure under the VGTC society, the IEEE VGTC/TVCG 9+2 page budget, author-optional double-blind anonymization, the supplemental-material one-week window, and desk-reject triage before the AoE cutoff for a paper that will publish in IEEE TVCG.ȘtiințăFără avertismente★ 1,3 K↓ —
- package-healthmohitagw15856/pm-claude-skillsCheck a package's health before you depend on it — npm and PyPI registry APIs via keyless curl: downloads, release recency, maintenance signals, and the dependency-decision read. Use when asked is this npm package maintained, check this PyPI library before we adopt it, compare these two packages, or is this dependency abandoned. Produces the health read with the signals interpreted (not just listed), the numbers with their commands, and the adopt/avoid/vendor recommendation framing.AlteleFără avertismente★ 1,5 K↓ —
- uai-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a UAI submission for OpenReview readiness, covering the February paper deadline, the 8-page main part with unlimited appendices in one PDF, the 15 MB file cap, the optional 50 MB supplementary ZIP, double-blind rules, the reviewer-volunteer agreement, dual-submission checks, and desk-reject triage before upload.DocumenteFără avertismente★ 1,3 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★ 11,2 K↓ —
- oma-designfirst-fluke/oh-my-agentDefine or review a visual system, DESIGN.md, or redesign direction. Use for typography, layout, color, motion, and interaction design decisions.DesignFără avertismente★ 1,4 K↓ —Apare și în 1 alt depozit
- writing-relayflowsAgentWorkforce/relayInfrastructure for coding agentsRedactareFără avertismente★ 1,1 K↓ —
- colt-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a COLT (Conference on Learning Theory) submission for CMT readiness, the 12-page PMLR-format main body, single-PDF assembly with unlimited appendix, double-anonymous formatting, the parallel-submission ban covering journals and proceedings venues, and the ordered final-week checks before the AoE deadline.DocumenteFără avertismente★ 1,3 K↓ —
- api-page-generatorkostja94/marketing-skillsDeprecated compatibility entry for API Page construction. This page is now maintained in Pagina; install and use page-builder to build a new API Page.InginerieFără avertismente★ 1,1 K↓ —
- cscw-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when readying a CSCW manuscript for upload — confirming the current pathway (rolling via Manuscript Central as of mid-2026), the single-column ACM template, the word-length scrutiny band, anonymization of author and community identifiers, ethics statements, and desk-risk triage.AlteleFără avertismente★ 1,3 K↓ —
- bamaNoudaveebbelaar/bamaBuild any Mac app. Start here to pick the next skill for a native macOS app.AlteleFără avertismente★ 1 K↓ —
- code-reviewdzhng/skillsReview changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.InginerieFără avertismente★ 1,4 K↓ —
- faq-page-generatorkostja94/marketing-skillsDeprecated compatibility entry for FAQ Page construction. This page is now maintained in Pagina; install and use page-builder to build a new FAQ Page.AlteleFără avertismente★ 1,1 K↓ —
02-ref-hallucination-arena
agentscope-ai/OpenJudge
ȘtiințăActualizat alaltăieri
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