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.
49.492 de skill-uri din 2.391 de depozite · actualizat acum 7 ore
49.492 de skill-uri
- minutes-ideassilverstein/minutesSurface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.AlteleFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- regex-buildermohitagw15856/pm-claude-skillsBuild a regular expression from a plain-English description, or explain an existing one. Use when asked to write a regex, match/validate/extract a pattern, or understand what a regex does. Produces the regex, a token-by-token breakdown, passing and failing test cases, and notes on flavor/edge cases.TestareFără avertismente★ 1,5 K↓ —
- sensory-auditmohitagw15856/pm-claude-skillsWalk a space — home, office, commute, classroom — and find the sensory landmines quietly draining or overloading you, with fixes ranked by cost and impact. Use when someone says 'my office wrecks me and I don't know why', 'I'm overstimulated all the time', 'make my home autism/ADHD-friendly', or lives with SPD, autism, migraine, or misophonia. Produces a room-by-room sensory map, a ranked fix list (free → cheap → invest), and a portable kit for spaces you can't change. A self-help audit, not a clinical assessment.ȘtiințăFără avertismente★ 1,5 K↓ —
- repairhashgraph-online/awesome-codex-pluginsSafe maintenance for an existing docflow setup. Regenerates INDEX.md, installs or refreshes recognized DocFlow-managed helper scripts, runs link checks, and reports placeholder/validation issues. Use when docflow exists, after adding or renaming docs, or when doctor recommends repair.AlteleFără avertismente★ 1,5 K↓ —
- render-glassy-matte-grwmgooseworks-ai/goose-skillsAssemble a multi-scene GRWM beauty-demo ad from a config — a locked-identity creator applies ~5 products step by step while a SEPARATE ElevenLabs voiceover narrates and every scene cut is snapped to the VO's product-name word-starts (Whisper word-level timestamps), then ~5 Playwright product overlay cards (real PDP-verified taglines) are composited onto the master each on its product-NAME word-start, the SEPARATE VO is mixed on top of a ducked music bed at loudnorm I=-14, clean-white 3-words/cue captions are burned, and the video closes on a flat-lay end card. This is the FREE deterministic assembly stage (re-cut to the VO word-starts, hard-concat, Playwright card render + card composite, VO plus music mix, caption burn, flat-lay end card); the VO, scene clips, product cutouts, and music come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the glassy-matte-grwm format.MediaFără avertismente★ 1,3 K↓ —
- account-planmohitagw15856/pm-claude-skillsBuild a structured account plan for any key customer or target account. Use when asked to create an account plan, key account strategy, strategic account review, or territory plan. Produces a complete account plan with relationship map, growth opportunities, risks, and 90-day action plan.PlanificareFără avertismente★ 1,5 K↓ —
- world-clockmohitagw15856/pm-claude-skillsGet the current time anywhere and convert between time zones with zero API keys — timeapi.io via curl (worldtimeapi fallback), plus the DST-safe meeting-window math. Use when asked what time is it in a city, convert 3pm my time to Tokyo, find a meeting slot across time zones, or what's the UTC offset somewhere. Produces the local time(s), the conversion with DST handled by the API not by memory, and the overlap window for scheduling questions.MarketingFără avertismente★ 1,5 K↓ —
- which-skillmohitagw15856/pm-claude-skillsRoute a fuzzy request to the right skill in this library. Use when the user is unsure which skill fits, asks 'which skill should I use for X', describes a task without naming a skill, or when a request could plausibly match several skills. Produces a best-fit recommendation with the inputs to gather, a runner-up with the tie-breaker, and a workflow recipe when the job spans multiple skills.ProductivitateFără avertismente★ 1,5 K↓ —
- meta-evalagentscope-ai/OpenJudgeUse when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.TestareFără avertismente★ 1 K↓ —
- rag-architectalirezarezvani/claude-skillsDesign a RAG pipeline: chunk size, embedding model, vector database and retrieval quality metrics. Use whenever the user builds search over their docs, picks a vector store or finds answers miss the right context.PlanificareFără avertismente★ 29,3 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↓ —
- 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↓ —
- os-whats-nextkharmanskyi/open-stepsALWAYS invoke this skill when the user asks what to do next, what is left, or what is blocked - "what's next", "what now", "what should we work on", "anything I can do" - in any language. This skill picks the next piece of work; when the user asks HOW to do a thing or says they do not understand what to do, that is os-step-by-step. Reads the last report, local changes, open pull requests and always the backlog. First finishes what is finished: verified-ready pull requests merge in the same pass. Then sorts the rest into doable-alone and needs-you, ending with one recommended next task in plain words - what it closes or unblocks. Never invents tasks.ProductivitateFără avertismente★ 1,3 K↓ —
- ai-model-webActualizatTencentCloudBase/CloudBase-AI-ToolkitUse 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).DesignFără avertismente★ 1,2 K↓ —
- flight-trackermohitagw15856/pm-claude-skillsTrack live aircraft positions with zero API keys — adsb.lol's open ADS-B network primary, OpenSky fallback, via curl: by callsign, registration, or area. Use when asked where is this flight right now, what planes are overhead, track a tail number, or is that flight in the air. Produces the live position with altitude, speed, and heading interpreted, the overhead list for a location, and the rerunnable command — with the positions-not-schedules boundary stated honestly.MarketingFără avertismente★ 1,5 K↓ —
- token-dietmohitagw15856/pm-claude-skillsCut LLM output tokens 40–70% by stripping grammatical scaffolding while preserving every fact — telegraphic output modes, when they pay (pipelines, long sessions) and when they don't (single shots, human-facing prose), with the mode lines to switch on demand. Use when asked make the model respond tersely, cut output token costs, caveman mode, or compress agent-to-agent messages. Produces the diet-mode instruction block ready to paste, the three compression levels with examples, the economics of when each pays, and the never-diet list.RedactareFără avertismente★ 1,5 K↓ —
- read-the-roommohitagw15856/pm-claude-skillsFigure out the real social dynamics of a situation — the unspoken mood, who holds influence, what's actually going on beneath the surface — so you respond to what's real, not just what's said. Use when asked help me read this situation, what's really going on here, how should I play this socially, or I can't tell the vibe. Produces an interpretation of the likely dynamics from your description (the mood, the power/influence, the unspoken tensions, what people actually want), how to check your read, and how to adjust your approach — with a caution against over-reading and a nudge to verify rather than assume.AlteleFără avertismente★ 1,5 K↓ —
- minutes-briefsilverstein/minutesFast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", or right before walking into a meeting. Different from /minutes-prep — brief is the fast hook-fireable version that doesn't ask questions and doesn't set goals. Use brief when speed matters; use prep when the user wants to think hard about goals first.ProductivitateFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- ecommerce-video-adsNouhashgraph-online/awesome-codex-pluginsEcommerce video ad skills for Claude Code and AI agents: plans and makes short product videos that sell on TikTok, TikTok Shop, Instagram Reels and Meta ads, with AI or real footage. Asks the four questions that change the rules (where it runs, product facts, assets, budget), picks angle, hook, format and on-camera character, writes a second-by-second script, keeps the real product identical in AI shots, applies platform rules (AI labels, TikTok Shop bans on AI voices, slideshows and price mentions, the FTC fake-testimonial rule, music licensing), quotes cost before generating and plans different-concept variants. Use when someone wants a viral TikTok, Reels or TikTok Shop video for a product, ecommerce ad creatives or "10 ads for my product". Hands off to product-video-hooks, tiktok-shop-video, ai-ugc-ad-video, product-photo-to-video, ad-creative-testing and ecommerce-video-edit. NOT for app launch videos, music videos or brand films with nothing to sell.MediaFără avertismente★ 1,5 K↓ —
- verify-form-validationreticlehq/reticleCheck that a form actually rejects bad input: the error message renders, the submit button stays disabled, and no request goes out. Use when validation logic was written but never driven, when a "required" or pattern check looks right on screen but was never proven, or when a bug report says the form submitted invalid data anyway.MediaFără avertismente★ 1,3 K↓ —
- baoyu-compress-imageJimLiu/baoyu-skillsCompresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.MediaFără avertismente★ 27,3 K↓ —
- agent-specmohitagw15856/pm-claude-skillsSpecify an autonomous or tool-using AI agent before building it. Use when asked to design an AI agent, define an agent's tools and guardrails, scope what an agent is allowed to do, or write an agent spec/PRD. Produces an agent spec — goal & scope, tools with permissions, the control loop, guardrails & approval gates, memory, escalation/handoff, evaluation, and failure handling.PlanificareFără avertismente★ 1,5 K↓ —
- dns-lookupmohitagw15856/pm-claude-skillsQuery DNS records and domain registration data with zero API keys — DNS-over-HTTPS via dns.google and domain registration via RDAP, through plain curl. Use when asked what does this domain resolve to, check the MX or TXT records, who registered this domain, when does it expire, or has DNS propagated. Produces the records decoded (SPF/DKIM/DMARC read, not just dumped), the registration facts from RDAP, and the rerunnable commands.InginerieFără avertismente★ 1,5 K↓ —
- decision-memomohitagw15856/pm-claude-skillsWrite a crisp decision memo that drives a clear decision, not a discussion. Use when asked to write a decision memo, a recommendation memo, a one/six-pager for a decision, or to get leadership to decide something. Produces a decision memo — the decision & recommendation up front, the context, options with trade-offs, what you'd need to believe, risks, and the explicit ask with a deadline.RedactareFără avertismente★ 1,5 K↓ —
skill-eval
hashgraph-online/awesome-codex-plugins
AlteleActualizat acum 21 de ore
De la autor
Measure whether a skill helps by comparing runs with and without it. Use when: reading skill A/B results or deciding to keep, revise or remove one.
Instalare
npx skills add hashgraph-online/awesome-codex-plugins --skill skill-eval -a claude-code
Se instalează în .claude/skills/skill-eval/ · 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: APACHE-2.0
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență78
Întreținere100
Licență100
Adopție51
Fișiere (5)
- SKILL.md
- references/behavioral-probes.md
- references/coding-memory-readout.md
- references/dialogue-skills.md
- references/seeding.md