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.
48.622 de skill-uri din 2.355 de depozite · actualizat acum 9 ore
47.548 de skill-uri
- 02-bib-verifyagentscope-ai/OpenJudgeVerify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for accuracy.ȘtiințăFără avertismente★ 1 K↓ —
- functionshashgraph-online/awesome-codex-pluginsBuild and prove durable studio functions for record, order, schedule and tool events, with concurrent database updates and event feeds.DateFără avertismente★ 1,5 K↓ —
- eval-reportagentscope-ai/OpenJudgeUse when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment, cross-skill signals, trends, prioritized actions, and an executive summary. Also use when the user mentions eval health check, evaluation audit, ship readiness, evaluation maturity, or "how good is my evaluation system itself." This is a read-only analysis skill.ProductivitateFără avertismente★ 1 K↓ —
- 00-arena-routeragentscope-ai/OpenJudgeUse when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.PlanificareFără avertismente★ 1 K↓ —
- bootstrapagentscope-ai/OpenJudgeUse when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and needs to turn them into principles. Outputs a v0 grader in 30 minutes using OpenJudge SimpleRubricsGenerator, plus a roadmap to reach calibrated evaluation.PlanificareFără avertismente★ 1 K↓ —
- oma-tf-infraNoufirst-fluke/oh-my-agentCreate or review Terraform infrastructure and plans. Use for cloud resources, IAM, networking, state management, and infrastructure changes.DevOpsFără avertismente★ 1,4 K↓ —
- agentlas-operationsagentlas-ai/Agentlas-OSAgentlas 시스템 운용 절차 — hep-network 편성, hep-graph 자동화, cargo/Agent Cloud·marketplace 활용, workforce 로스터 재사용, 메모리 계약. One(개인 에이전트)이 Agentlas를 조작할 때 이 절차를 따른다.AlteleFără avertismente★ 1,6 K↓ —Apare și în 2 alte depozite
- researchtaishi-i/awesome-japanese-nlp-resourcesAnalyze current trends and challenges in Japanese NLP for a topic. Surveys the existing awesome-japanese-nlp-resources dataset and augments it with up-to-the-minute web research to produce a combined trend + issue report. Use only when the user explicitly wants a trend/landscape report, a challenges/limitations report, or a general research overview of a Japanese NLP topic (this combines the bundled dataset with live web research). Trigger phrases include '日本語LLMの最新トレンド', '〜の動向をまとめて', '最近の日本語NLPの流れ', '日本語LLMの課題', '〜の問題点・限界', '未解決の論点', 'trend report on Japanese embeddings', 'latest Japanese speech models', 'challenges in Japanese NER', 'limitations of Japanese embeddings'. For a simple lookup use the search skill; this one runs web research.ȘtiințăFără avertismente★ 1 K↓ —
- verify-ui-changereticlehq/reticleCheck that a change to a web app actually works in the running app before calling it done. Drives the real page and returns a pass/fail verdict with the request that fired, the state that moved, and the file:line to fix. Use after editing a component, a form, a route, or an API call; when you have said "fixed" but have not opened the app; when the user asks "does it actually work?"; or when a change looks right on screen and you cannot prove it.DesignFără avertismente★ 1,3 K↓ —
- design-system-compliancereticlehq/reticleCheck that the UI you actually rendered uses the design system, by reading computed styles in the running app against the project's design tokens. Catches hardcoded hex colors, off-palette backgrounds, invisible or unusable controls, and animations that never ran. Use after building or restyling a component, when a design review is wanted, when a UI looks slightly off but nobody can say why, or when a design system exists and nothing checks whether the code follows it.DesignFără avertismente★ 1,3 K↓ —
- credit-memomohitagw15856/pm-claude-skillsWrite a credit memo for a lending decision: borrower story, facility structure, repayment sources, financial-ratio spread with covenant headroom, risk factors with mitigants, risk-rating rationale, and a recommendation. Use when asked to write a credit memo, credit application, credit paper, loan write-up, or prepare a deal for credit committee. Produces a complete credit memo ready for committee review.ȘtiințăFără avertismente★ 1,5 K↓ —
- weekly-unstuckmohitagw15856/pm-claude-skillsA short weekly ritual that clears the mental backlog, picks the one thing that matters, and keeps you honest about your dependence on autopilot. Use when asked run my weekly reset, help me plan my week, my weekly check-in, or get me unstuck for the week. Produces a quick brain-dump and triage of what's on you, the single most important focus for the week, the stuck things and their tiny first steps, and a self-check on where you're coasting or over-relying — a recurring executive-function reset rather than a one-off fix.PlanificareFără avertismente★ 1,5 K↓ —
- docs-lifecycle-scanamplifthq/openmeldUse when closing out a feature, tidying developing/ documentation, or asked to check docs health — runs the lifecycle linter and applies the README deletion rules.AlteleFără avertismente★ 1,4 K↓ —
- skill-sync-publisherhashgraph-online/awesome-codex-pluginsSafely validate, publish, and track a local SKILL.md directory across GitHub, Awesome Codex Plugins, HOL Registry, skills.sh, SkillsMP, LobeHub, ClawHub, and Cursor Directory. Use when the user asks to publish, update, register, or synchronize an agent skill across marketplaces.AlteleFără avertismente★ 1,5 K↓ —
- codex-exechashgraph-online/awesome-codex-pluginsRun one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.AlteleFără avertismente★ 1,5 K↓ —Apare și în 2 alte depozite
- scenario-blenderscenario-labs/skillsUse when an agent works in an open Blender scene through the Scenario for Blender extension's local MCP server (scenario-blender on 127.0.0.1:9876): connecting Claude Code, Cursor, Claude Desktop or Codex to Blender, the headless scenario_blender command, quoting and generating Scenario images, PBR materials, 3D meshes, video, audio or 360 environments from the scene, capturing the viewport or selected meshes as references, placing saved results, Render Video camera paths, or execute_python.MediaFără avertismente★ 1,4 K↓ —
- render-cartoon-music-videogooseworks-ai/goose-skillsAssemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the bar, VEED-whisper white bold-sans captions in the BOTTOM third (Alignment 2, above the logo bug, no pill) burned from the song's word timings re-spelled against the locked lyrics, a persistent brand logo bug held over the body (suppressed on the end card), and closed on a solid-brand-color PIL end card with the song still playing under it — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-bar + hard concat + logo bug + captions + end card + song mux); the song, character, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cartoon-music-video format.MediaFără avertismente★ 1,3 K↓ —
- navigatehashgraph-online/awesome-codex-pluginsPick the next work in an epic or bead graph; closed is not proven. Use when: asked what is next or whether an epic is done.AlteleFără avertismente★ 1,5 K↓ —Apare și în 2 alte depozite
- 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↓ —
- verify-keyboard-accessreticlehq/reticleVerify that every interactive control on a page can take keyboard focus and that its primary action fires from the keyboard rather than only the mouse, and say plainly that Tab order cannot be verified today. Use when a component was hand-tested with a mouse, a custom dropdown/modal/combobox was added, or an accessibility report flags an unreachable control.AlteleFără avertismente★ 1,3 K↓ —
- make-static-ads-graphic-requestgooseworks-ai/goose-skillsMakes one simple non-ad brand graphic, such as an email header, social feed or story image, or a blog or link-preview image, in the brand's style with at most a short line of text, after claim and rights checks and a yes to the quote; returns the link and alt text. Not for carousels, decks or print. Use alone when you already have the purpose, placement and exact wording; otherwise run make-static-ads.MarketingFără avertismente★ 1,3 K↓ —
- code-completeciembor/agent-rules-booksApply Steve McConnell-inspired construction rules when implementing routines, variables, classes, control flow, defensive code, or tests.InginerieFără avertismente★ 3,2 K↓ —
- launch-nemo-rlNVIDIA/skillsPlaybook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.DevOpsFără avertismente★ 3,8 K↓ —
- make-static-ads-find-referencesgooseworks-ai/goose-skillsStep of make-static-ads: picks a template for every ad in its chosen style, after its visual idea and style are set, from the brand's own ads, the GooseWorks library or category leaders, and records what the chosen creativity level keeps from it. Run make-static-ads instead; not for direct use.MarketingFără avertismente★ 1,3 K↓ —
ai-model-web
TencentCloudBase/CloudBase-AI-Toolkit
DesignActualizat acum 10 ore
De la autor
Use this skill when a browser/Web app (React, Vue, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI, 页面, 前端, 网页) needs AI models via @cloudbase/js-sdk. Default routing for Web/frontend AI — call directly from the browser, do NOT propose a Node.js proxy. Covers generateText and streamText; models via ai.createModel with groups cloudbase, the legacy hunyuan-v3 / hunyuan-exp, or custom-*, model id in the `model` field. MUST run two-step preflight before code — see body. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).
Instalare
npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill ai-model-web -a claude-code
Se instalează în .claude/skills/ai-model-web/ · 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: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență77
Întreținere100
Licență100
Adopție50
Fișiere (1)
- SKILL.md