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.
11.424 de skill-uri din 333 de depozite · actualizat acum 21 de minute
9.601 skill-uri
- wiki-qasickn33/agentic-awesome-skillsAnswer repository questions grounded entirely in source code evidence. Use when user asks a question about the codebase, user wants to understand a specific file, function, or component, or user asks "how does X work" or "where is Y defined".TestareFără avertismente★ 48,2 K↓ —
- java-junitgithub/awesome-copilotGet best practices for JUnit 5 unit testing, including data-driven testsTestareFără avertismente★ 40,3 K↓ —
- build-uisickn33/agentic-awesome-skillsStep-by-step workflow for UI work: read the project, follow the plan for the job (new screen, dashboard, polish, simplify, review), then render, fix and check again.DesignFără avertismente★ 48,2 K↓ —
- blockrunsickn33/agentic-awesome-skillsBlockRun works with Claude Code and Google Antigravity.InginerieFără avertismente★ 48,2 K↓ —
- team-communication-protocolswshobson/agentsStructured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing communication norms for a newly spawned team, when deciding whether to send a direct message or a broadcast, when a team-lead needs to review and approve an implementer's plan before work begins, when orchestrating a graceful team shutdown after all tasks are complete, or when debugging why teammates are not coordinating correctly at integration points.PlanificareFără avertismente★ 41,4 K↓ —
- dataset-curationwshobson/agentsPrepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring sequence packing, generating synthetic training data, or writing a dataset card before a run.RedactareFără avertismente★ 41,4 K↓ —
- ux-copysickn33/agentic-awesome-skillsGenerate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and toneDesignFără avertismente★ 48,2 K↓ —
- ux-flowsickn33/agentic-awesome-skillsDesign user flows and navigation structure following proven UX patternsDesignFără avertismente★ 48,2 K↓ —
- varlocksickn33/agentic-awesome-skillsSecure-by-default environment variable management for Claude Code sessions.InginerieFără avertismente★ 48,2 K↓ —
- avoid-ai-writingwshobson/agentsAudit and rewrite prose so it stops reading as machine-generated. Use this skill when asked to remove AI-isms, clean up AI writing, edit a draft for AI tells, audit a README, changelog, release note, PR description, or blog post for machine-sounding prose, or make text sound less like AI. Supports a detect-only mode, a rewrite mode, and an edit-in-place mode, with optional voice and context profiles.RedactareFără avertismente★ 41,4 K↓ —
- seo-pagesickn33/agentic-awesome-skillsDeep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance. Use when user says "analyze this page", "check page SEO", or provides a single URL for review.MarketingFără avertismente★ 48,2 K↓ —
- dataladK-Dense-AI/scientific-agent-skillsRetrieves, versions, and publishes scientific datasets with DataLad and git-annex, and captures computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink or a small pointer instead of real data; when an analysis needs a machine-readable record of how each output was produced so it can be re-executed; or when publishing a dataset to siblings such as a GitHub repository plus a storage remote. Also use to decide between DataLad and plain Git for a data-carrying repository.ȘtiințăFără avertismente★ 53,4 K↓ —
- kaizensickn33/agentic-awesome-skillsGuide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements.InginerieFără avertismente★ 48,2 K↓ —
- eval-harness-firstwshobson/agentsBuild the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.AlteleFără avertismente★ 41,4 K↓ —
- use-domsickn33/agentic-awesome-skillsUse Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.InginerieFără avertismente★ 48,2 K↓ —
- understand-diffEgonex-AI/Understand-AnythingUse when you need to analyze git diffs or pull requests to understand what changed, affected components, and risksInginerieFără avertismente★ 87,4 K↓ —
- curlshotsickn33/agentic-awesome-skillsCapture web page screenshots, PDFs and scrolling videos, or render HTML/Markdown to images, with the hosted CurlShot API.MediaFără avertismente★ 48,2 K↓ —
- secrets-managementwshobson/agentsImplement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI/CD environments.DevOpsFără avertismente★ 41,4 K↓ —
- faf-gosickn33/agentic-awesome-skillsGuided interview to Gold Code (100% AI-Readiness). Use when helping users improve their .faf file through questions. Leverages Claude Code's AskUserQuestion for seamless integration. Just type /faf-go and answer questions till done.PlanificareFără avertismente★ 48,2 K↓ —
- accessibility-compliancewshobson/agentsImplement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support. Use when auditing accessibility, implementing ARIA patterns, building for screen readers, or ensuring inclusive user experiences.JuridicFără avertismente★ 41,4 K↓ —
- understand-chatEgonex-AI/Understand-AnythingUse when you need to ask questions about a codebase or understand code using a knowledge graphInginerieFără avertismente★ 87,4 K↓ —
- multi-reviewer-patternswshobson/agentsCoordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.InginerieFără avertismente★ 41,4 K↓ —
- resume-content-guidereactive-resume/reactive-resumeDecides what information belongs on a resume or CV, what to leave off and in what order, and audits an existing resume against those norms. Covers every section (contact details, photo, summary, experience, education and GPA, skills, languages, references), candidate situations (new grad, career change, gaps, layoffs, veterans, academic, visa and more) and country and industry norms. Use when the user asks "what should I put on my resume", "what should I leave off", "should I include my photo / GPA / date of birth", "how do I show a gap", "summary or objective?", "how long should my CV be", "CV for a job in Dubai / Germany", "I'm moving to another country, what should I change", "what to put on my resume as a veteran" or "audit / review my resume". Works with pasted text or the Reactive Resume MCP server. For rewriting bullets use resume-bullet-writer; for fitting a resume to one job posting use resume-tailor; for building a new resume as JSON use resume-builder.MediaFără avertismente★ 44,6 K↓ —
- postmortem-writingwshobson/agentsWrite effective blameless postmortems with root cause analysis, timelines, and action items. Use when conducting incident reviews, writing postmortem documents, or improving incident response processes.RedactareFără avertismente★ 41,4 K↓ —
eval-harness-first
wshobson/agents
AlteleActualizat acum 3 zile
De la autor
Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.
Instalare
npx skills add wshobson/agents --skill eval-harness-first -a claude-code
Se instalează în .claude/skills/eval-harness-first/ · 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 95
Securitate100
Proveniență95
Întreținere100
Licență100
Adopție71
Fișiere (3)
- SKILL.md
- references/grader-templates.md
- references/judge-calibration.md