agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Joonganggroup corporate voice skill

    claudianus/joonganggroup-corporate-voice-skill Skill

    0★

    Use when writing or rewriting Korean corporate, media, entertainment, culture, CSR, recruitment, or brand copy in a JoongAng Group-inspired voice. Produces original copy with the analyzed cadence, vocabulary, and tone of joonganggroup.com while avoiding verbatim copying, trademark confusion, or false official affiliation.

  • Your ui ux designer

    zeeshani42/your-ui-ux-designer Skill

    0★

    Universal UI/UX skill for generating production-grade screens, components, and design systems. Triggers on any UI/UX design intent — dashboards, landing pages, mobile apps, admin panels, modals, forms, and more.

  • Churn reduction

    SkillMedev/saas-growth-stack/skills/churn-reduction Skill

    0★ repo

    Diagnoses SaaS churn root causes through cohort analysis and a seven-category taxonomy, then builds segmented intervention playbooks ranked by frequency, revenue at stake, and addressability - including save-offer economics. Use when someone asks "why is our churn so high", "build a churn reduction plan", "should we offer discounts to cancelling customers", or when NRR/GRR is slipping and the team needs a diagnosis before prescriptions. Do NOT use for gym or fitness-studio member retention - use retention-and-churn-killer instead. Do NOT use for re-acquiring customers who already left - use win-back-campaign instead. Do NOT use for growing existing accounts - use expansion-revenue instead.

    The same file is in 3 other repositories

  • Agent orchestration

    SkillMedev/ai-engineer-toolkit/skills/agent-orchestration Skill

    0★ repo

    Designs reliable multi-agent LLM systems - choosing a topology, writing handoff contracts between agents, deciding what runs in parallel vs series, and setting context, retry, and cost budgets that stop runaway loops. Use when someone asks "should I split this into multiple agents", "my agents keep looping", "how do I pass context between agents", "orchestrator vs pipeline vs router", or is architecting an agent workflow. Do NOT use for tuning a single prompt - use prompt-engineer instead; do NOT use for measuring agent output quality - use llm-evaluation instead; for making a product agent-operable end to end, use build-on-agent-native.

    The same file is in 1 other repository

  • Ab test analyzer

    SkillMedev/performance-marketing/skills/ab-test-analyzer Skill

    0★ repo

    Analyzes an A/B experiment to a defensible verdict - sample-size and minimum-detectable-effect math, two-proportion significance testing with confidence intervals, and checks for the traps that fake a win (peeking, sample ratio mismatch, multiple comparisons). Use when someone asks "is this test significant", "did variant B win", "how long should I run this experiment", "what sample size do I need", or shows experiment results and asks whether to ship. Do NOT use for logging and organizing ML training runs - use experiment-tracking instead; for causal questions without a randomized experiment use causal-inference; for general funnel or metric investigation use funnel-analysis or product-analytics.

    The same file is in 2 other repositories

  • Sai poster studio

    wyuee912-ops/sai-poster-studio Skill

    no license0★

    Turn a line of text or a post into a finished, on-brand Sai/Simular poster. 11 brand templates (event, talk, benchmark, launch, hackathon, editorial, mixer, enterprise…), every social size (Instagram, LinkedIn, X), a free-form editor (align, rotate, fonts, background patterns, keyword highlight), and print-resolution PNG/SVG export. No API keys — Claude writes the brief, the local Vite app renders it in the browser. Triggers: sai poster, simular poster, poster studio, make a poster, social graphic, instagram poster, linkedin poster, launch poster, event poster, benchmark poster, sai social, simular social.

  • Actions

    nord342/claude-meeting-notes/meeting-notes/skills/actions Skill

    0★ repo

    Review and maintain the cross-meeting action ledger (ACTIONS.md) — show what's open, overdue, or due soon, filter by owner, and mark items done. Use when the user asks "what are my open action items", "what's overdue", "what does Sarah owe me", or wants to check off completed tasks.

  • Product id handler

    AmyLFrederick/Claude-Skills/product-id-handler Skill

    0★ repo

    Claude Skills and design patterns for AI workflows in high-stakes environments.

  • Zoom out

    RobertGumeny/skills/zoom-out Skill

    0★ repo

    Use this skill when two conditions are met: (1) the user is already mid-session on a technical topic, and (2) they signal a desire to step back and reconnect with human impact, business outcomes, or plain-language tradeoffs. Trigger phrases: "zoom out", "step back", "big picture", "plain terms", "remind me why we're doing this", "what does this mean for users", "what's at stake", "plain english", "without the jargon", "losing the forest for the trees", "what are we actually deciding", "eli5 what we're trading off", "lost the thread". Do NOT trigger for: standalone learning questions with no prior session context, fresh architecture comparisons, document summarization, code review, or general "explain X to me" requests.

  • Signoff

    LuckyCody/signoff Skill

    0★

    End-of-session ritual. When the user says "/signoff", "wrap up", "i'm stepping away", "end session", or "update progress", run this — captures what shipped, updates the progress log, cross-checks memory, and proposes the first action for the next session. Replaces every ad-hoc "update progress before we stop" request.

  • Claude skill sansheng

    DQT-bit/claude-skill-sansheng Skill

    0★

    三省(sansheng)——多 Agent 并行调研工坊。把 OpenRouter Fusion API 的"panel + judge + 综合"多模型协作思路映射到 Claude Code 原生 Agent tool。 名字典故:曾子"吾日三省吾身"(独立反思)+ 三省六部(多部独立议事综合决策),三 = 推荐的 sub-agent 数。 方法论:spawn N 个 sub-agent 从互补角度并行调研 → 主 agent 做 Judge 交叉评审(标共识/分歧/缺口/独特观点)→ 综合输出敢下判断的结论。 当用户需要做"开放性研究、对比、评审、选型、风险盘点、跨领域调研"时使用。最终产出一份带共识/分歧/缺口标记的综合判断,以及可立即落地的下一步。 触发词包括但不限于:研究下 X、对比 X 和 Y、评审这个方案、X 的选型建议、X 有哪些风险、分析下 X、调研一下 X、X 和 Y 哪个更适合 Z、帮我看看 X 怎么选、X 方案有什么坑、三省一下 X、让三省看看。 即使用户只是丢一个开放性问题"应该 A 还是 B"、或要"全面看一下 X",只要任务有多个合理答案、需要多视角综合,都应该触发。 不要用于答案唯一的任务(bug 已定位、格式转换、单函数实现、删除冗余代码);不要用于用户在线等结果的实时迭代场景(spawn + 综合至少要 1-2 分钟);不要用于单页 web 查询能搞定的轻量问题。

  • Skeptic

    jai2010/skeptic Skill

    no license0★

    Forensic validation engine that strips narrative optimism, sentiment bias, and unverified claims from any text payload. Separates verifiable data from assumptions, maps downstream structural risks via domino-effect analysis, and recalculates a realistic success state. Use this skill whenever the user invokes `/skeptic`, submits a status report, strategy doc, proposal, roadmap, or any text containing confidence claims, projections, or "on track" language that needs adversarial validation. Also trigger when an orchestrator agent detects unverified claims, forward-looking statements, or suspiciously optimistic "Green" status. If the user pastes a block of text and wants it stress-tested, reality-checked, or pressure-tested — use this skill.

  • Ground first

    88plug/trigger-my-training/skills/ground-first Skill

    no license0★ repo

    Use BEFORE acting whenever getting it wrong has real cost — in ANY domain, not just infra. Fire for complex or multi-step work; irreversible or hard-to-undo actions; anything touching production, shared state, real user data, money/payments, security/credentials, schema/migrations, external APIs/integrations, concurrency, or a change rippling across many call sites; and debugging where acting on the wrong root cause makes it worse. Judge the REAL work from your own understanding, not keywords — a request can say "payment" or "migrate" or "refactor" and be a one-line cosmetic edit, while a plain-sounding one is deeply consequential. It splits what you KNOW from what you're ASSUMING, surfaces the silent failure modes, and verifies your riskiest assumptions before the irreversible step. Do NOT use for trivial reversible edits — renames of a local symbol, typos, comments, formatting, cosmetic tweaks.

  • Instagram post builder

    SkillMedev/instagram-trend-post-builder/skills/instagram-post-builder Skill

    0★ repo

    Interactively builds a complete, copy-paste-ready Instagram post package - three hook variants using distinct patterns, a caption body, one clear CTA, a 15-20 hashtag set across reach tiers, alt text, and a visual direction with shot list or slide breakdown - through a one-question-at-a-time interview, optionally grounded in a trend-educator briefing. Use when someone says "write an Instagram post for my launch", "build the full post package for this reel", "put together a carousel with hooks and hashtags", or reaches the build stage after trend-educator. Do NOT use for finding what is trending - use instagram-trend-scout instead; for a single caption without the full package - use social-caption-writer; for planning a month of content - use social-content-calendar.

    The same file is in 1 other repository

  • Analyze

    Lemonaderrrrr/flow-kit/skills/analyze Skill

    0★ repo

    Turn data, a situation, or a set of options into a structured analysis with a confidence-rated conclusion. Default Engineer mode. Two branches — 🧮 Decision analysis (which path to choose) and 📈 Data analysis (find insight in data). Hands off to the research skill when external data is missing. Saves to outputs/analysis/. Use when the user says "analyze this", "run the numbers", "which of these should I pick", "what does this data say", or invokes the skill.

  • Hooksmith

    arhamhi/hooksmith/skills/hooksmith Skill

    0★ repo

    Use when the user asks for Instagram Reel hooks, TikTok or Shorts hooks, stronger openings, first-frame text, spoken intros, identity hooks, open loops, rehooks, retention paths, caption hooks, or an audit of the first 15-30 seconds of a short-form video. Builds, audits, rewrites, and stress-tests complete hook systems. Also handles `hooksmith init`, `hooksmith generate`, `hooksmith audit`, `hooksmith rewrite`, `hooksmith identity`, `hooksmith rehook`, and `hooksmith caption`.

  • Greenfish cpm skill

    DumbGreenFish/greenfish-cpm-skill Skill

    0★

    A Claude skill designed for working with Compose Multiplatform, based on my own experience using the Claude Code and CMP combination.

  • Agent team

    0jg/skills/agent-team Skill

    no license0★ repo

    Configures and invokes the Claude Code subagent team for implementation tasks. Use this skill whenever a task involves more than one file, any physics or ML logic, or any implementation that warrants specialist review. Triggers on: "implement", "write the code for", "build", any task moved to In Progress on the board, or whenever the implementer produces code touching physics equations, numerical methods, ML architectures, or training loops. Always invoke this skill for non-trivial work — do not let the main agent implement and review its own code.

  • Agreement drafter

    Uhudsavasindankacanokcu2/legal-skills-for-claude/agreement-drafter Skill

    no license0★ repo

    Draft common business agreements from a short description — NDAs, freelance/contractor agreements, service agreements, simple terms of service, and letters. Produces a clean, balanced first-draft contract with placeholders filled from the user's inputs. Use when the user asks to write/draft/create an NDA, contract, agreement, ToS, or engagement letter.

  • Ciloop

    BiswaViraj/agent-skills/plugins/agent-workflows/skills/ciloop Skill

    0★ repo

    Use when CI is failing on a branch/PR and the user wants it driven back to green — "fix the failing CI", "CI is red, sort it out", "make the checks pass", "loop until CI is green". Pulls the real error from the failing GitHub Actions logs, reproduces it locally, fixes the confident failures, pushes once, and re-watches until green. The red-CI twin of reviewloop.

  • Telegram rich messages

    ganiyevuz/telegram-richtext/skills/telegram-rich-messages Skill

    0★ repo

    Use when an aiogram Telegram bot should send a message that reads better with structure than as plain text — tables, inline images/video/audio, headings, lists, collapsible sections, block quotes, footnotes, math, or maps — or when tempted to fake a table with <pre> monospace, split an image into a separate photo+caption message, or reach for parse_mode HTML/MarkdownV2. Applies to Telegram Bot API 10.1 rich messages (send_rich_message, InputRichMessage, streaming drafts) with aiogram >= 3.29.

  • Last 90

    Avanderheyde/webapp-last-90/plugins/last-90/skills/last-90 Skill

    0★ repo

    The last 90% of shipping a web app — everything agents skip: authz, monitoring, legal, backups, rate limits, CI/CD, ops. Run it after deploying (the follow-on to vps-saas / levels.io) to make a freshly-launched web app actually safe and set up properly. Goal-driven: keeps working until the launch gate is 10/10, checking in only when it needs your accounts or a decision. Pass 'explain' for teaching mode that explains what the last 90 is and why each item matters.

  • Make presentation

    samulee003/agentic-ppt-skills/skills/make-presentation Skill

    0★ repo

    Turns a source folder, existing deck, or presentation idea into a complete presentation product by routing through source intake, product grilling, evidence, story, prototype, stage review, and final delivery. Use when starting a presentation from materials, rebuilding a deck, resuming a partial presentation project, or asking for an end-to-end PPT/PDF workflow.

  • App analyzer optimizer

    roedyrustam/claudevibeskills/src/app-analyzer-optimizer Skill

    no license0★ repo

    Deeply analyzes application architecture, dependencies, and performance configurations, and executes targeted optimizations aligned with active project skills. Use whenever the user wants a full project health check, dependency audit, performance review, or asks "analyze my codebase" or "optimize my app." Trigger on phrases like "audit my project", "analyze the architecture", "find performance issues", "optimize this app", or "review my dependencies".

  • Spike first

    AllenShi100/spike-first Skill

    no license0★

    在写任何代码或计划之前,对抓取/爬虫/API集成/第三方服务/自动化对接类任务强制做一道"可行性闸门"—— 先用一次性探针对真实目标验证最大未知点(先打靶再造枪),探针通过才放行到设计和实现,不通过当场喊停换方案。 Use this skill whenever the user asks to scrape a website, crawl data, integrate with an external or third-party API/service, build an automated data pipeline against a system you don't control, or any task where "can we even reliably get the data or access we need?" is still an open question — even if they don't explicitly ask for validation. 触发词:抓取、爬虫、采集、集成、对接、API、第三方服务、自动化对接、 反爬、scrape、crawl、integrate、webhook。务必在这类任务一出现就触发,不要等撞墙了才想起。 但以下情况**不要触发**(即使句子里带了上面的关键词):维护或调试**已经在跑**的抓取/集成代码、 处理已经拿到的数据、纯本地的重构或性能优化、跑测试(含"集成测试")、写文档、 纯概念问答(如"解释 REST 和 GraphQL 的区别")。判据只有一条——有没有一个开工前还不确定 "能不能稳定拿到"的外部数据或访问;没有,就不是这个 skill 的活。

  • Prompt lint

    fxw-labs/prompt-lint Skill

    0★

    评估和审计 AI prompt 的质量。检测常见错误模式,输出 8 维度雷达图评分和改进建议。仅在用户明确要求评估/检查/lint prompt 时激活。不激活于正常对话、编码、文档编写。

  • Screen recording to pdf

    Denlie-code/screen-recording-to-pdf Skill

    no license0★

    Convert a screen recording / screencast / demo video (.mp4, .mov, .mkv, .webm, .gif, etc.) into a single multi-page PDF by extracting key frames and assembling them. Use when the user has a recording and wants it as a PDF document. TWO modes: (1) `--capture-all` -- scroll-aware capture for CONTINUOUS content like a scrolling CHAT-RECORDING, captures EVERY message (一条不差, no skips) by measuring scroll and keeping a frame each half-screen; (2) `--auto` / manual scene-detection / max-frames -- key-frame extraction for demos/tutorials. Triggers (CN/EN): 录屏转pdf, 录屏做成PDF, 把这段录屏转成PDF, 录屏导出PDF, 聊天记录转pdf, 聊天记录导出, chat history to pdf, screen recording to pdf, video to pdf, 视频转PDF. Requires Python 3 + ffmpeg (system PATH, or `pip install imageio-ffmpeg`) + numpy (for --capture-all) + Pillow; `pip install img2pdf` for lossless JPEG-to-PDF assembly.

  • Tdd

    kongyo2/TDD/tdd Skill

    0★ repo

    Strict t-wada style Red-Green-Refactor TDD for TypeScript + Vitest projects. Use when implementing features, fixing bugs, changing runtime behavior, or refactoring logic — any task that adds or modifies production code. Enforces test-first development with a verified Red, minimal Green, and disciplined Refactor, plus agent-safe Vitest execution rules.

  • Acars decode

    WPTK/acars-decoder-claude-skill/acars-decode Skill

    0★ repo

    Use this skill whenever the user wants to decode, interpret, analyze, or understand an ACARS message, VDL Mode 2 (VDLM2) message, CPDLC message, or any aviation datalink message. Triggers include: any mention of 'decode this ACARS', 'what does this message mean', 'interpret this VDL2', 'ACARS message', or when the user pastes raw ACARS/VDL2 text, or any structured aviation datalink output and wants to understand what it says. Also trigger when the user shares output from any ACARS/VDL2 decoder tool. This skill covers ALL ACARS message types. It handles OOOI (out/off/on/in), position reports, weather requests, free text, ATS/CPDLC, departure/arrival, ETA, meteorological, engine data, media advisory, and any other ARINC 620/618 label. It also handles VDL Mode 2 framing metadata from decoder tools. Do NOT use for aircraft ownership research (use aircraft-research skill) or ADS-B position data without an ACARS/datalink message attached.

  • Freeticket cli

    AppFreeticket/agent-skills/skills/freeticket-cli Skill

    0★ repo

    Drive the official FreeTicket CLI (binary `ft`, npm `@freeticket/cli`) to operate a workspace from the terminal — log in through the browser (device flow), list/inspect AND create/update/delete events, dates, ticket types, sales, membership plans, venues, staff, discount codes and webhooks; publish events; create/cancel/refund sales; check tickets in at the door and resend QRs; list a sale's tickets, a plan's subscribers, cancel subscriptions; run reports (summary, by-event, timeseries, inventory, CFO reconciliation); and export buyers/attendees/subscribers to CSV. Superadmin (`ft admin …`) manages tenants, users, platform plans, feature flags and impersonation. Use it when the user wants to read OR mutate their FreeTicket account from the terminal, run `ft <command>`, automate with `--json`/`jq` or `--csv`, manage the session/workspace, send feedback/suggestions (filed as GitHub issues on the right repo), or when another skill needs live data or actions on the B2B v1 backend.

  • Picture cube solve

    Erlemar/cayley-puzzles/.agents/skills/picture-cube-solve Skill

    no license0★ repo

    Use this skill for any task in the cayley IHES Picture Cube project — training, solving, evaluation, ensembling, submission. Covers the full ML+search pipeline.

  • C4 views

    TheAkshitS/skills/skills/c4-views Skill

    0★ repo

    Generate and review C4 model software-architecture diagrams (System Context, Container, Component) in Mermaid, Structurizr DSL, or C4-PlantUML. Use when the user wants to create, draw, author, diagram, or visualize software architecture or system structure, or to review, critique, or sanity-check an existing architecture or C4 diagram — including requests mentioning 'C4', a 'context/container/component diagram', an 'architecture diagram', or 'mermaid C4', even when they don't say 'C4' explicitly.

  • Image license rights

    SkillMedev/stock-asset-sourcing/skills/image-license-rights Skill

    0★ repo

    Decides whether a specific image use is legally permitted, what the license obligates, and whether a model or property release is required - covering CC0 and Creative Commons variants, Unsplash/Pexels/Pixabay terms, royalty-free vs rights-managed, standard vs extended tiers, editorial-use-only, and AI-image caveats - and delivers a per-image license record. Use when someone asks "is this free for commercial use", "do I need to credit the photographer", "can I put this on merchandise", "what is royalty-free vs rights-managed", "is editorial-use-only a problem", or "do I need a model release", or is about to publish, advertise, or sell anything containing a stock image. Do NOT use to find or search for a photo - use stock-photo-finder instead; do NOT use to fetch images via an API with attribution rules - use stock-photo-api instead.

    The same file is in 1 other repository

  • Project prospector

    88plug/project-prospector/skills/project-prospector Skill

    no license0★ repo

    Discover, catalog, and rank everything a person has built or sketched on a machine by fanning out parallel read-only investigation agents over the filesystem, then synthesizing a tiered ranking by idea-novelty and leverage. The defining signal is a whole-machine survey of the user's OWN work — every project, repo, half-built thing, abandoned experiment, or loose idea (notes, downloads, transcripts included), usually wanting a ranking or verdict: most original, strongest, worth finishing. Trigger on asks like "what have I built on this laptop", "take stock of my half-finished repos", "rank my projects by which ideas are most original", or "fan out agents and catalog my side projects" — even without the words "agents" or "skill". Supports a time window and scope exclusions (e.g. "except my job's repo"). Strictly read-only. Do NOT use it for work inside a single repo (its files, PRs, TODOs), bare repo listing, choosing the next feature, or surveying projects that aren't the user's.

  • Manuscript canon ledger

    dinaf2026-web/manuscript-editorial-suite-plugin/skills/manuscript-canon-ledger Skill

    0★ repo

    Living, versioned canon ledger for any book or series — the persistent source of truth the continuity pass reads before it audits. Holds canon as STATE (per character/place/timeline fact, marked STABLE, DISPUTED, or EVOLVING) plus a DELTAS changelog of intentional changes tagged to book + chapter + reason, and OPEN QUESTIONS for unresolved canon disputes. Stored per project under .manuscript/canon-ledger.json. Use when the author says "canon ledger", "update the ledger", "record a canon change", "is this canon", "what's the canon for X", "add a delta", "resolve open question", or "seed the ledger from book N". It maintains the ledger and renders a human .xlsx view; it does NOT audit a manuscript (continuity-audit does that, consuming this ledger), rewrite prose, or judge mystery logic.

    The same file is in 1 other repository

  • Meta ads cli

    gfsaaser24/meta-ads-cli/skills/meta-ads-cli Skill

    0★ repo

    Run the Meta (Facebook/Instagram) Ads CLI — the `meta` command from the `meta-ads` Python package — inside Cowork's sandbox to manage Meta advertising from the terminal. Use this skill whenever the user wants to install or run the Meta Ads CLI / Facebook Ads CLI / the `meta` command, or asks to list, create, update, or delete Meta/Facebook ad campaigns, ad sets, ads, or ad creatives; pull ad performance insights or reporting (spend, ROAS, CTR, CPC, conversions) from the command line; or manage Meta pixels/datasets, product catalogs, product feeds, product sets, ad accounts, or Facebook Pages via CLI. Trigger this even when the user does not name the package — phrases like "set up the Meta ads CLI", "create a Facebook campaign from the terminal", "pull my Meta ad insights", or "spin up an Advantage+ sales campaign with the meta command" all apply. For pulling existing ad metrics where a Meta Ads MCP/connector is already attached, that connector may be simpler; this skill is for the standalone CLI.

  • House builder

    argent-gnome/sdlc-skills/skills/house-builder Skill

    0★ repo

    The house SDLC build executor — run in a build session that house-orchestrator spun up to implement ONE plan unit. Use when you've been handed a kickoff prompt (project, repoPath, plan unit, stack, scope guards) and your job is to build, self-review, reconcile that unit's docs, and report back. Do NOT use to drive a whole slice (that's house-orchestrator), or for non-build chat.

  • Abm account brief skill

    saurabhshuklagrowisto/saurabh-ai-systems/claude-skills/abm-account-brief-skill Skill

    0★ repo

    Generates a hyper-personalized ABM account brief and outbound hook for a target B2B account. Takes a company domain plus optional context (recent signals, persona, ICP fit notes) and returns a structured brief with company snapshot, three personalization hooks ranked by strength, a recommended channel (email / LinkedIn DM / LinkedIn InMail), a 60-word cold email draft, and a confidence score. Use when researching a target account before outbound, when refreshing a stale prospect, or when generating hooks at scale across a target account list.

  • 1on1 agenda

    SkillMedev/remote-team-toolkit/skills/1on1-agenda Skill

    0★ repo

    Structures recurring manager-report 1:1s with a rolling shared agenda that balances check-in, blockers, two-way feedback, and career growth instead of status updates. Use when someone asks "what should I cover in my 1:1s", "build me a 1:1 agenda template", "my 1:1s have turned into status meetings", or is setting up 1:1s with new reports. Do NOT use for general meeting agendas - use meeting-agenda instead; for writing a formal review document, use performance-review-writer; for drafting a specific piece of feedback, use feedback-writer.

    The same file is in 2 other repositories

  • Dependency risk audit

    SkillMedev/security-compliance-hardening/skills/dependency-risk-audit Skill

    0★ repo

    Audits third-party dependencies for exploitable CVEs, abandonment, license exposure, and supply-chain hygiene, and delivers a ranked findings report with a remediation order. Use when someone asks "is this package safe to add", "audit our dependencies", "npm audit is screaming, what actually matters", "can we use this GPL library", or is preparing a security review or vendor questionnaire. Do NOT use for triaging vulnerabilities in first-party code or a full CVE queue - use vulnerability-triage instead; for reviewing the code you wrote for security flaws - use secure-code-review instead; for how secrets are stored and rotated - use secrets-hygiene instead; for assembling compliance evidence - use soc2-evidence-helper instead.

    The same file is in 2 other repositories

  • Data drift monitor

    SkillMedev/data-science-ml/skills/data-drift-monitor Skill

    0★ repo

    Designs a production drift-monitoring plan for ML systems - statistical tests per feature type, PSI and KS alert thresholds, monitoring cadence, and evidence-based retraining triggers - including a runnable PSI calculator. Use when someone asks "how do I know if my model is drifting", "set up drift monitoring for this model", "should we retrain", or is investigating unexplained model performance degradation. Do NOT use for judging whether a model is good enough to ship in the first place - use model-evaluation-report instead; for tracking training runs use experiment-tracking; for documenting the model for consumers use model-card-writer.

    The same file is in 1 other repository

  • Budget vs actual

    SkillMedev/finance-accounting-ops/skills/budget-vs-actual Skill

    0★ repo

    Structures a budget-vs-actual variance analysis that isolates root causes - price/volume/mix decomposition, timing vs structural expense buckets, a materiality screen, and reforecast flags - instead of restating numbers. Use when someone asks "why did we miss budget", "write the variance commentary for the board deck", "explain this expense overrun", or is closing the month and owes narrative on the P&L. Do NOT use to build the budget or plan itself - use budget-builder instead; do NOT use for a full driver-based forecast model - use fpa-model instead; do NOT use for cash timing and runway questions - use cash-flow-forecast instead.

    The same file is in 1 other repository

  • Html share

    lxhsoluto-star/html-share-skill/html-share Skill

    0★ repo

    Share a single HTML file as a short URL + QR code. Reads a local .html, uploads it (with its local images) to the html-share backend, inlines/uploads assets, auto-adds mobile viewport, generates a social-preview (OG) image, and prints a short link + scannable QR. Supports custom short links. Use when the user says "share this html", "分享这个html", "上传html", "生成分享链接", "生成二维码", "share this page", "make a link for this HTML", "publish this HTML", or asks to host/share a single HTML artifact you just produced.

  • Ask me questions

    nsollazzo/skills/ask-me-questions Skill

    0★ repo

    Systematic requirements discovery through multi-round questioning before taking action. Use when the user explicitly asks — "ask me questions", "ask me first", "interview me", "gather requirements", "understand what I need" — or when a request is genuinely ambiguous: multiple plausible interpretations leading to materially different implementations, and the right one isn't discoverable from the code or context. Do NOT use for clear requests, however large.

  • Html ppt

    Frog1205/OPC-Skills/skills/html-ppt Skill

    0★ repo

    HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a reveal-style HTML deck, a 小红书 图文, or any kind of multi-slide pitch/report/sharing document that should look tasteful and be usable with keyboard navigation. Triggers include keywords like "presentation", "ppt", "slides", "deck", "keynote", "reveal", "slideshow", "幻灯片", "演讲稿", "分享稿", "小红书图文", "talk slides", "pitch deck", "tech sharing", "technical presentation".

  • Hypawave

    hypawave/skills/skills/hypawave Skill

    0★ repo

    Buy and sell over Bitcoin Lightning between autonomous agents — pay to unlock files, APIs, data, compute, or gated actions, or monetize your own behind a paywall. Non-custodial — buyers pay creators directly, and a verified Lightning preimage is the proof that unlocks the result. Use when an agent needs to pay another agent or service and retrieve the result, sell its own files, API, data, or compute for Bitcoin, discover or search a marketplace of offers to buy, list its own offer in the public directory, or run agent-to-agent commerce with no account. Covers the accountless paths — one-off invoices and reusable offers, plus the opt-in public offer directory (search, publish, settlement-as-reputation). Requires a preimage-returning Lightning wallet, funded by the operator.

  • Core

    isatimur/remotion-md/packages/core Skill

    0★ repo

    Make your AI agent produce structured Remotion video compositions — scene-by-scene JSON specs that render to production-ready animated video.

  • Pre merge conflict predictor

    ritesh31/claude-pre-merge-conflict-predictor/skills/pre-merge-conflict-predictor Skill

    0★ repo

    Before opening a PR, predict potential merge conflicts by checking if your changed files overlap with other open PRs or branches

  • Diagnostics

    WindcleaverDev/regkit/.agents/skills/diagnostics Skill

    0★ repo

    Run the full diagnostic battery on a fitted regression model — assumption tests (linearity, homoscedasticity, normality of residuals, independence, multicollinearity), influence analysis (leverage, Cook's distance, DFFITS), and bias/variance assessment via cross-validation. Produces a structured DiagnosticsReport with status flags and ranked remediation recommendations, plus a standalone HTML report. Use this skill whenever a regression has been fitted and the user wants to know if they can trust it, asks "are the assumptions met?", "is this model overfit?", "is this overfitting or underfitting?", or wants to identify influential outliers. Pair with the linear-regression or regularized-regression skills.

  • Daily update desktop

    pandoempe/mpw_claude/.claude/skills/daily-update-desktop Skill

    no license0★ repo

    Generates a daily intelligence briefing for a company using Claude's built-in web search only — the web/Desktop counterpart of the daily-update skill, for environments with no local filesystem and no API keys. It takes the user's search context (an attached file, the project's instructions, or text pasted into the chat), researches recent competitor/regulatory/industry/macro developments with WebSearch, and writes a briefing covering a news summary, impact to company risk, and concrete mitigation steps — shown in the chat first, then optionally exported to a downloadable Word document. Use this skill whenever a Claude.ai web or Claude Desktop user asks for their "daily update", "daily briefing", "morning briefing", "today's report/digest", wants to "catch up on news relevant to the company", or asks to check on competitors, industry shifts, or regulatory developments that could affect the business — even if they don't say "daily update" by name.

  • Assumption audit

    opelpleple/meta-skills/assumption-audit Skill

    0★ repo

    Excavates the hidden assumptions baked into a plan, belief, or estimate, lists them explicitly, then ranks them by how much damage results if each turns out to be wrong — so the riskiest get tested first. Use this skill when the user asks "what am I assuming", "audit my assumptions", "what am I taking for granted", has a shaky estimate or forecast, is building a plan that depends on unknowns, wants to de-risk before committing resources, or when a plan feels confident but rests on untested beliefs. Best when a plan looks solid on the surface but its foundations have never been checked.

  • Symlink skills

    usrrname/agent-skills/.agents/skills/symlink-skills Skill

    no license0★ repo

    Symlink every skill in this repo into one or more agent skills directories (defaults to ~/.claude/skills/ and ~/.agents/skills/) so the skills become globally discoverable. Use when the user says "install these skills", "make these skills global", "symlink skills to ~/.claude", "symlink skills to ~/.agents", "register the skills", or wants to update the global skill set after editing skills here.

  • Watchmark

    alexander-rehm/watchmark Skill

    0★

    Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls the transcript from native captions (captions-only by default, so no audio leaves the machine without consent). Produces a structured `report.md` and, after answering the user, saves a finished note (report.md plus hero frames) into your Obsidian vault under `Video notes/` (vault configurable via `$WATCH_VAULT_DIR`) - tied to *why* the user watched it.

  • Gpt tasteskill

    Fldicoahkiin/agent-skills-card/.claude/skills/gpt-tasteskill Skill

    no license0★ repo

    Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

    The same file is in 13 other repositories

  • Kiss blast radius

    Pr1m4lc0d3/KiSYSTEM/skills/kiss-blast-radius Skill

    no license0★ repo

    Use before editing, refactoring, moving, or deleting existing code — to keep the change contained to its bounded unit and prevent collateral damage to surrounding services and functions. Use whenever a change touches a file other code depends on, or whenever a refactor could ripple beyond the thing you were asked to change.

  • Relex citations

    relexyou/relex-claude/plugin/skills/relex-citations Skill

    0★ repo

    Use whenever legal authority is cited, quoted, or relied on in Relex work — drafts, memos, ontology issues, research notes, any jurisdiction. Teaches the three-tier epistemic labeling (secured / verify / never-use), the hard citation locks, and the minimum-data citation schema that keep hallucinated law out of legal work.

  • Cold email craft

    SkillMedev/outbound-sales-engine/skills/cold-email-craft Skill

    0★ repo

    Write short, personalized B2B cold emails and follow-up copy - under 90 words, one ask, personalization in the first line - with good/bad contrast pairs to calibrate. Use when someone asks "write a cold email", "why is nobody replying to my outreach", "draft a follow-up sequence", "make this email shorter", or is starting founder-led outbound. Do NOT use for sending infrastructure, domains, SPF/DKIM/DMARC, warmup, or spam placement - use cold-email-deliverability instead; for multi-channel cadence architecture use outreach-sequence-designer; for building and verifying the list use prospect-list-builder.

    The same file is in 5 other repositories

  • Neilization

    Coflazo/neilization Skill

    0★

    Rewrites, restructures, and expands explanatory prose into a vivid cosmic-perspective popular-science register inspired by broad public-science techniques, without exact imitation of any living author. Use when the user says "neilize", "make this more cosmic", "popular science voice", "science communicator style", "rewrite this for the public", or asks to make science, technology, policy, civic, or educational prose clearer, sharper, more concrete, and more memorable.

  • Claude

    giljr/claude Skill

    no license0★

    Complete guide to installing, configuring, and running bundler-audit in Ruby/Rails projects. Use this skill whenever the user mentions bundler-audit, gem auditing, vulnerabilities in Ruby gems, dependency CVEs, secure gem updates, or wants to ensure security in a Rails project's dependencies. Also trigger for bundler-audit result analysis, CVE/GHSA interpretation, and safe production update strategies.

  • Document format conformance

    QrCommunication/skills/skills/document-format-conformance Skill

    no license0★ repo

    Expert des spécifications de formats documentaires — PDF (ISO 32000), PDF/A (ISO 19005), OOXML/Office (ECMA-376 / ISO 29500 : .docx .xlsx .pptx), ODF/ OpenOffice (ISO 26300 : .odt .ods .odp) et Factur-X/PDF-A3 (conteneur). Permet d'INSPECTER la structure réelle d'un fichier, de VALIDER sa conformité structurelle ET sémantique (qpdf, veraPDF, lxml/xmllint, factur-x), de MODIFIER un fichier « à la volée » en garantissant qu'il reste conforme (incremental update PDF signature-safe, patch de part OPC/ODF avec repackage valide), et d'AUDITER une codebase/un moteur qui produit ces formats contre la spec. À utiliser dès qu'apparaissent : conformité PDF, PDF/A, PDF/UA, ISO 32000, veraPDF, xref/trailer, incremental update, OOXML, ECMA-376, ISO 29500, OPC, [Content_Types].xml, docx/xlsx/pptx, ODF, ISO 26300, manifest.xml, mimetype, Factur-X, ZUGFeRD, PDF/A-3, AFRelationship, valider/réparer/modifier un PDF ou un document Office/OpenOffice, auditer un générateur de PDF/Office.