agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • Cicada

    Synthrun/Cicada Skill

    no license1★

    Cicada — Security Audit & Fix Skill for LLM coding agents (16 domains, cross-framework)

  • Code review brief

    gitgitWi/council-flow/skills/code-review-brief Skill

    no license1★ repo

    Write the base material for a code review — a "review brief" for a pull request that the USER feeds to their own external agent(s) to post review/comments on GitHub. This skill does NOT perform the review itself and does NOT post comments; it prepares the document a reviewer works from. The flow agent gathers the diff, the changed-file list, a summary of major changes, and the original intent/plan plus the user's key requests, then writes multi-angle review prompts (UX, code quality, redundant or over-engineered implementation, security, stability) tailored to the change. Use to prepare a review for any PR, whether just opened by flow:deploy or already on GitHub. Triggers on "코드리뷰 준비", "리뷰 brief 만들어줘", "PR 리뷰 자료 작성", "prep a review for PR #N".

  • Carousel scripter

    SkillMedev/social-media-studio/skills/carousel-scripter Skill

    1★ repo

    Scripts a multi-slide Instagram or LinkedIn carousel as a hook slide, one-idea-per-slide value frames, and a single-CTA closing slide, with per-slide copy and design direction. Use when the user asks to write, script, or outline a carousel, turn a post/idea/listicle into swipeable slides, or build an Instagram carousel or LinkedIn document (PDF) post.

    The same file is in 1 other repository

  • Skill payment processing

    zavora-ai/skill-payment-processing Skill

    no license1★

    Orchestrate governed payment operations — create payment intents, manage approval gates, execute approved payments, reconcile against invoices, and maintain audit evidence. Use when processing payments, issuing refunds, creating payouts, checking payment status, reconciling transactions, or generating payment reports. Agents propose — policy decides — humans approve — system executes.

  • Acceptance scope control

    Gesondian/ai-collab-governance-skills/skills/acceptance-scope-control Skill

    1★ repo

    Use when an AI is about to report accepted, passed, closed, ready, done, or equivalent handoff, receipt, or completion wording.

  • Lecture notes

    ChristinaAndrinopoyloy/claude-skills/plugins/christina-skills/skills/lecture-notes Skill

    1★ repo

    Transform raw lecture content (transcript, plain text, or slides) into clean, structured, study-ready notes in Markdown. Use this skill whenever the user pastes lecture material — a transcript (with or without timestamps), course/lecture text, or slide content — and asks for notes, a summary, or help studying. Also trigger when the user says things like "take notes", "κράτα σημειώσεις", "φτιάξε σημειώσεις", "notes από το μάθημα", "summarize this lecture", or pastes a transcript and asks to organize or study it.

  • Shorthand mem

    jai2010/shorthand-mem Skill

    no license1★

    A two-way semantic compiler that compresses PRDs, codebases, research papers, and meeting notes into dense symbolic notation, and reconstructs them back into professional prose. Use this skill whenever the user writes SQUEEZE, EXPAND, DIFF, MERGE, SUMMARISE, LIST SQUEEZES, RECALL, SEARCH, DELETE, or EXPORT ALL — or when they want to compress, store, retrieve, compare, or summarise any document. Works across four domains: PRD, CODE, PAPER, MEETING. No MCP server or API key required — runs entirely within Claude.

  • Semver cop

    tokyubevoxelverse/semver-cop Skill

    1★

    Determine whether the next release is legally a patch, minor, or major by diffing the public API surface against the last published version. Use before cutting a release, when reviewing "is this breaking?", or when writing honest release notes.

  • Generated skill

    spmisha134/skillOps-intellij/docs/templates/generated-skill Skill

    no license1★ repo

    Use this skill when an example Codex skill is needed for documentation or testing.

  • Ai workflow

    vindm/dotclaude/deferred/skills/ai-workflow Skill

    1★ repo

    Set up LLM workflow discipline for projects that use AI / LLM calls in production or eval suites. Authors an eval-cost-watcher agent that projects token cost BEFORE regression evals run, plus an AI-workflow-discipline rule covering mock-mode placement, fixture freshness, and multi-stage cost accumulation. Optionally a small eval-regression skill stub. Invoke /dotclaude:ai-workflow only when the project actually has AI workflows.

  • Analise juridica br

    falercia/deep-claude/skills/analise-juridica-br Skill

    no license1★ repo

    Skill para análise estruturada de contratos brasileiros como apoio a advogado. Acionar quando usuário pedir para "analisar contrato", "revisar cláusulas", "due diligence contratual" ou similar, em contexto de Direito brasileiro. NÃO emite parecer jurídico — produz insumo qualificado para advogado.

  • Competitive scan

    stanislavnianko/product-discovery-claude-skills/plugins/discovery-phase/skills/competitive-scan Skill

    1★ repo

    [discovery-phase pack · evidence] Maps direct competitors, indirect substitutes, and adjacent (non-software) workarounds for the problem in problem-canvas.md. Identifies the actual gap and any "free incumbent" the client can't outcompete. Produces competitive-scan.md. Reads discovery-context.md.

  • Community engagement playbook

    SkillMedev/course-creator-launch-system/skills/community-engagement-playbook Skill

    1★ repo

    Builds the student community system for a paid course - platform choice by where students already are, an introduce-yourself onboarding ritual, a weekly cadence of office hours, wins threads, and accountability checks, a hard creator-time budget, and scheduled testimonial-harvest moments. Use when a course creator says "my students aren't finishing the course", "should I use Circle or Slack or Discord", "how do I keep my community active without it eating my week", or "how do I get testimonials from students". Do NOT use for running the testimonial conversation itself - use testimonial-capture-interview instead.

    The same file is in 1 other repository

  • Claude context

    cs-shadowbq/claude-context/skills/claude-context Skill

    1★ repo

    Search across all ~/.claude data (conversations, project memories, global memories, plans, agents) to find prior work, past solutions, and relevant context before reading raw files or grepping manually. Use this whenever the user asks things like "have we dealt with this before," "did I solve this somewhere," "find that memory/note about X," "what project was that in," or when you (Claude) need to recall a prior decision, convention, or fix across projects without knowing which project or conversation it's in. Always prefer this tool over `grep`/`find`/reading whole .claude files directly — it is dramatically cheaper in tokens and returns structured, rankable results.

  • Business rule extractor

    SkillMedev/legacy-modernization/skills/business-rule-extractor Skill

    1★ repo

    Produces a documented inventory of the implicit business rules, edge cases, and bug-as-feature behaviors that tangled code encodes, with real input-to-output examples, so a rewrite preserves behavior. Use when you are about to rewrite, port, or replace legacy code whose only specification is the source, and you see policy buried in conditionals, magic numbers, hardcoded dates, or per-customer special cases. Do NOT use when you need an executable safety net before refactoring - use characterization-test-writer instead; do NOT use when you need to find service boundaries in a monolith - use monolith-decomposer instead.

    The same file is in 1 other repository

  • Video social editor

    joanseg/video-social-editor Skill

    1★

    Edits raw screen recordings into polished social media videos. Use this skill whenever the user has a screen recording (demo, walkthrough, tutorial, product showcase) and wants to produce a cropped, cut, focused video ready for social media — Instagram Stories, TikTok, LinkedIn, YouTube Shorts, or any platform. Handles all four phases: shot list → rough cut → reframe to target format → text overlays. Also generates voice-over scripts. Trigger on phrases like "edit this video", "make a social clip", "cut this recording", "crop for stories", "add text overlays", "make it 9:16", "reel from this demo", or any time the user shares a video file and wants it edited.

  • Connect tools

    Fusion-Data-Company/bristol-os/plugins/bristol-os/skills/connect-tools Skill

    1★ repo

    Ask the Bristol user what tools and data Bristol already pays for, then connect them — or set up an export/drop path for the ones with no connector — and capture Bristol's real numbers for calibration. Runs during onboarding and any time someone says "connect," "add data," "make it more accurate," "hook up CoStar/Yardi," or wants better comps. Claude does the asking and the walking-through; the user just answers and clicks.

  • Skill notification delivery

    zavora-ai/skill-notification-delivery Skill

    no license1★

    Deliver notifications via push, SMS, email, in-app, and webhooks — manage templates, schedule delivery, track status, and respect user preferences. Use when sending notifications, managing templates, checking delivery status, scheduling alerts, or configuring preferences.

  • Skill test execution

    zavora-ai/skill-test-execution Skill

    no license1★

    Orchestrate test execution — run unit, integration, and E2E tests, collect coverage reports, and analyze failures. Use when running tests, checking coverage, debugging test failures, or validating code changes before merge.

  • Publish audit

    solidstatecc/skills/skills/publish-audit Skill

    1★ repo

    Audit a skill folder before you publish to ClawHub. Catches the frontmatter-vs-code mismatches, missing metadata, leaked secrets, and file-limit problems that hide or reject a release — so it passes the scan on first upload. Not for vetting a skill you're about to install (see skill-vetter).

  • Virtual panel

    koji/waza/skills/productivity/virtual-panel Skill

    no license1★ repo

    Simulate a high-value virtual panel discussion between 4 distinct fictional characters (Genius, Eccentric, Beginner, and one of Optimist/Worrier selected for fit) on any topic the user provides. The discussion uses critical thinking, active debate, and deep/lateral exploration — never mere agreement — and ends with structured meeting minutes written from the perspective of a "genius blogger". Use this skill whenever the user asks for a panel discussion, brainstorm session with characters, multi-perspective debate, virtual meeting, fictional roundtable, creative ideation session, or says anything like "panel discussion", "debate this topic", "run a meeting on", "brainstorm with characters", or "explore this from multiple angles". Also trigger when a user pastes a topic and wants rich, multi-voice analysis that goes far deeper than a standard essay or bullet list. Minimum output length is 10,000 characters.

  • Codebase understanding

    HelloThisWorld/agent-skill-verification-template/skills/codebase-understanding Skill

    1★ repo

    Answers questions about a codebase using source-grounded evidence. Every factual claim must cite a specific file and line; ambiguous or unsupported questions return insufficient_evidence instead of a guess.

  • Postsmith

    alqzowskiy/Postsmith/postsmith Skill

    1★ repo

    Use when the user wants Instagram or social-media visuals of any kind — a post, carousel, story, reel cover, infographic, ad creative, or branded image set — or asks to "send a prompt to the image AI", "generate an image", "make a post", "make a carousel", "design a story", or in Russian "сделай пост", "сделай карусель", "сгенерируй картинку", "нарисуй сторис", "оформи инфографику", "отправь промпт нейросети". Triggers even when the word "postsmith" is never said. Use whenever someone needs brand-consistent image generation with gpt-image-2.

  • Provision environment

    franzos/claude-plugins/plugins/engineers/skills/provision-environment Skill

    1★ repo

    Use before running any build, test, lint, or format command to establish a working toolchain or runtime. Follows the user's declared environment presets, probes what is already available, provisions only in ways that do not modify the host machine (an ephemeral nix/guix shell or a throwaway container), and otherwise asks the user instead of guessing or installing.

  • Briefing room

    glichtenthal/briefing-room Skill

    1★

    Use when the user brings messy, layered, scattered, overloaded, or ambiguous context and asks to organize it into a brief. Trigger on notes, transcripts, research dumps, meeting context, strategy thoughts, emails, Slack threads, customer feedback, planning fragments, personal context, or requests like "make sense of this," "structure this," "what matters here," "clean this up," "prepare this for Ground Truth," or "prepare this for The Quorum."

  • Bootstrap

    Stepkar2004/init-configurator/.claude/skills/bootstrap Skill

    1★ repo

    Phase 0 of any project - fire whenever asked to start, scaffold, set up, or adopt a project ("new Python CLI", "set this repo up properly", "add a frontend stack"). Interview, scaffold via OFFICIAL creators, describe into project.yaml, prove with gates.

  • Api testing

    ykotik/cli-power-skills/skills/api-testing Skill

    1★ repo

    Use when testing HTTP endpoints, probing URLs for status and headers, or running declarative API test suites from plain text files

    The same file is in 2 other repositories

  • Audit

    aljazfrancic/audit-skill/audit Skill

    1★ repo

    Audit a codebase for bugs, report verified findings BEFORE changing anything, then on approval fix, verify with a build/tests, and commit + push. Use when the user asks to "audit the codebase", "find bugs", "audit and fix", "check for bugs", or run their standard audit-fix-verify-push loop.

  • Llm council

    refaelach/gmba-class-19-skills/skills/decision-making/llm-council Skill

    1★ repo

    Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.

  • Readme

    myl7/readme-skill/readme Skill

    1★ repo

    Use when creating or updating the readme (README.md).

  • Aspx analyzer

    sarveshtalele/aspx-analysis-skill/.claude/skills/aspx-analyzer Skill

    no license1★ repo

    Analyze ASP.NET Web Forms applications (.aspx pages, .ascx user controls, .master pages). Produces 5 views: (1) Project Overview — architecture, master pages, auth model, functional areas; (2) Page-by-Page — every .aspx with controls, handlers, redirects; (3) Functional View — pages grouped by business domain (Authentication, Orders, Admin, Reports, etc.); (4) Component View — user controls and master pages with usage maps; (5) Navigation Map — page-to-page transition graph. Supports GitHub repo URLs AND local/current repo paths. Builds a JSON index once; subsequent queries served from cache — handles 1000+ ASPX pages efficiently. For HUGE repos (10,000+ files) use the streaming single-file business analyzer (aspx_business_analyzer.py) — memory-safe, multiprocess, emits ONE consolidated business-logic markdown file instead of 5. Also emits an OpenSpec handoff: openspec/config.yaml (project context + modernization rules) and one openspec/changes/<area>/proposal.md stub per business capability, for repos that are using OpenSpec (openspec init) to plan a legacy-to-modern migration. Also emits a MODERNIZATION_ROADMAP.md: target tech-stack folder layout + scaffold commands, plus every functional area ranked simplest-first (direct-SQL weighted heaviest) with a concrete first-page-to-port suggestion per capability. Also emits a STAKEHOLDER_DOCUMENTATION.md: a business-facing summary (executive summary, capability inventory with risk flags, real OpenSpec progress if present, where to start, and how to build the complete project end-to-end) for non-technical readers. Trigger when user says: analyze aspx, aspx pages, web forms analysis, page inventory, aspx architecture, what pages does this app have, show me the screen flow, show user controls, master page analysis, aspx functional view, reverse engineer aspx, analyze this aspx project, how does this web forms app work, what is on the Login page, show me the Admin area pages, generate openspec config, prep this repo for modernization, convert this to openspec, generate a roadmap, create a modernization roadmap, what order should I build this in, what tech stack should I use, plan the migration order, stakeholder documentation, business documentation, explain this project to stakeholders, document this for business, or provides any GitHub URL for an ASP.NET Web Forms project.

  • LUDDITE KR

    devjun7/LUDDITE_KR Skill

    1★

    AI가 쓴 듯 경직되거나 번역투가 두드러지는 한국어 글을 원래 뜻과 장르를 보존하면서 읽기 쉽고 자연스럽게 다듬는다. 이메일, 보고서, 제안서, 안내문, 블로그, 설명문, 신문 오피니언, 발표문, 기술 문서, 일상 메시지 등 분야와 형식에 관계없이 문장 흐름·구조·어휘·리듬·어조·설명 방식을 개선할 때 사용한다. 사용자가 "사람이 쓴 것처럼", "AI 티를 줄여", "딱딱하지 않게", "번역투를 고쳐", "자연스럽게 윤문해", "독자가 이해하기 쉽게"라고 요청하거나 내용은 유지한 채 문체만 손봐야 할 때 사용한다.

  • Research code skill

    SaltGardenia/research-code-skill Skill

    1★

    Coding-standard enforcer for AI agents working inside a research (ML/DL) lab project. Its core job is twofold: (1) keep the project's fixed architecture intact across all coding work 鈥?never break or drift from the established structure; (2) enforce code-level conventions 鈥?naming, formatting, calling, and configuration 鈥?so every file is uniform. It codifies five authoritative systems as machine-executable Rule Cards (RC-*). It fuses thirteen authoritative references into four usage clusters so the agent never stacks them as separate checklists, plus a Karpathy-inspired behavioral discipline (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution) layered above the mechanical cards: (1) Project Scaffold & Python Grammar (Lightning-Hydra-Template structure + Hydra configs + Google Python Style); (2) Model & Component Design (PyTorch Lightning Style Guide + timm named architectures + OpenMMLab Registry pattern); (3) Experiment Reproducibility (Hydra Config-First + FAIR data + SemVer/Git Flow + Meta Research philosophy); (4) Engineering Process (Software Engineering at Google + Scientific-Python idiom). It operates in two scenarios: build from zero (A) or tidy an existing repo (B). It is NOT a post-hoc reviewer: it constrains code as it is written. Trigger on any code task: "add a model", "write a training script", "refactor this module", "create the project scaffold", "name this function", "add a config group", "manage dataset metadata", "tag this experiment release", or "what structure should this file use".

  • Journalism legal il

    bdnhost/claude-skills/skills/journalism-legal-il Skill

    1★ repo

    Israeli journalism legal advisor — specializes in defamation (חוק איסור לשון הרע), privacy (חוק הגנת הפרטיות), press freedom, and takedown demand handling. Activates for questions like "is this defamation?", "can I publish this?", "received a lawyer letter", source-protection, Freedom of Information Act queries, photo publication of residents/minors, and any pre-publication risk review for local Israeli news outlets. Produces a safe-to-publish edited version + explanation of changes. Hebrew primary, English secondary. Not a substitute for licensed legal counsel on high-stakes matters.

  • Api design

    simanam/theaiteam/team/skills/architecture/api-design Skill

    no license1★ repo

    REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.

    The same file is in 11 other repositories

  • Engineering standard skills

    Ewanjohndennis/engineering-standard-skills Skill

    1★

    Apply rigorous engineering standards when writing, refactoring, debugging, or reviewing Python, Java, or C code. Loads calibration and language-specific guidance automatically.

  • Stop slop zh

    LuoHaomin/stop-slop-zh Skill

    1★

    消除中文写作中的AI痕迹。在起草、编辑或审阅中文文本时使用,去除可预测的AI写作模式。当你在写中文文章、编辑中文草稿、检查文本是否有AI味、润色AI生成内容使其更像人写的,都应该使用这个skill。即使用户没有明确说"去AI味",只要是中文写作编辑任务,都可以参考。

  • Word counter

    Moosphan/word-counter-skill/skills/claude/.claude/skills/word-counter Skill

    1★ repo

    Deterministic counting for Chinese, English, and mixed-language text such as articles, essays, novels, chapters, outlines, transcripts, and pasted paragraphs. Use when the user asks for word count, character count, manuscript length, bilingual text count, chapter length, or wants a stable count instead of a model estimate.

  • Skill creator

    arcjet/skills/.agents/skills/skill-creator Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

  • Saop

    kaposty/saop/skills/saop Skill

    1★ repo

    Plan a non-trivial task with the SAOP method before starting the work: Sketch, Analyze, Optimize, Partition. It first locks the goal with you, grounds itself in the real context, then returns a decomposed plan pyramid whose endpoints are each checkable, ready for approval, and never implements a planned task until you approve. Domain-agnostic: a new project or subproject, a feature, a migration, a security hardening, a compliance review, a backend. Invoke it explicitly with /saop; it does not fire on its own. Skips routine or well-understood tasks where a full four-phase pass would be overkill.

  • Ai written check

    cabbagecachekid/neon-jetpack/skills/ai-written-check Skill

    1★ repo

    Detects the mechanical tells that make professional prose read as AI-generated — em dashes, triple-list anaphora, "not X but Y" antithetical pairs, spatial and economic metaphors for abstract ideas, "architect" as a verb, engineered sentence cadence, mid-paragraph register swerves, builder/startup slang, and unfalsifiable universal claims ("everyone", "across the board"). Use when reviewing or editing a resume, cover letter, portfolio page, case study, proposal, bio, or any human-facing copy, or when the user asks for an "AI-written check", "AI tells", says copy "sounds like AI", or asks to make writing sound less generated.

    The same file is in 1 other repository

  • Gutenberg layout

    iwritec0de/wp-dev/skills/gutenberg-layout Skill

    1★ repo

    This skill should be used when the user asks to "build a Gutenberg layout", "create a page layout", "design a WordPress page", "generate block markup", "build a landing page in Gutenberg", "create a block pattern layout", "design a section layout", "generate Gutenberg HTML", or mentions "gutenberg layout", "block layout", "page builder", "block pattern", "WordPress page design", "section layout", "full site editing layout". Provides Gutenberg layout generation by discovering available blocks on a WordPress site (via WordPress MCP), then producing valid block markup.

  • Textual

    vinsonconsulting/califa-cards/examples/textual Skill

    1★ repo

    Build, style, and debug terminal user interfaces in Python with Textual. Use when the user mentions Textual, a TUI, App/Widget/Screen subclasses, reactive attributes, TCSS or Textual CSS, `textual run`, `textual console`, or compose(). Do NOT use for plain CLI argument parsing (use click-cli), Rich-only static output (use rich-render), or curses (use curses).

  • Ios app agentic engineering

    markus-smile/ios-app-agentic-engineering/skills/ios-app-agentic-engineering Skill

    1★ repo

    End-to-end agentic engineering for iPhone apps, from idea to a secure App Store release through 8 gated phases. Use when someone wants to build, plan, or ship an iPhone/iOS app — especially a non-programmer ("vibe coder") asking to create an app, pick a tech stack (SwiftUI, React Native, Flutter), choose a backend (CloudKit, Supabase, Firebase), publish to the App Store, or make their app secure. Also use when an iOS project shows symptoms of skipped planning - hardcoded API keys, no threat model, Firebase test mode, missing privacy manifest, or App Store rejection.

  • Brand guidelines

    SkillMedev/content-marketing-engine/skills/brand-guidelines Skill

    1★ repo

    Writes a brand guidelines document - personality traits with is/is-not definitions, voice principles, a tone-by-context matrix, writing mechanics, a say-this-not-that word list, and visual usage rules - all made concrete with do/don't examples. Use when someone asks "write our brand guidelines", "document our voice and tone", "make a style guide the whole team can follow", or teams keep producing off-brand copy and design. Do NOT use for inventing the brand name itself - use brand-naming instead; for organizing messaging by audience and claim, use messaging-hierarchy.

    The same file is in 2 other repositories

  • Bloodwork explainer

    SkillMedev/health-and-longevity/skills/bloodwork-explainer Skill

    1★ repo

    Translates common lab panels - CBC, CMP, lipid panel, thyroid, hormones, HbA1c - into plain language, flags values against the lab's own reference ranges, and produces a prioritized question list to bring to a physician. Use when someone asks "what does my bloodwork mean", "is my ALT high", "explain my lipid panel", or "what should I ask my doctor about these results". General wellness education, not medical advice - it flags and explains, never diagnoses or prescribes. Do NOT use to summarize a medical chart or clinical document - use clinical-summary instead; for diet changes motivated by results, hand off to nutrition-planner.

    The same file is in 1 other repository

  • Data table design

    SkillMedev/document-studio/skills/data-table-design Skill

    1★ repo

    Designs presentation tables that read correctly at a glance - numeric alignment, consistent precision, deliberate sort order, unit-labeled headers, and well-placed totals - and delivers a before/after redesign of the reader's table. Use when someone asks "make this table more readable", "how many decimals should I show", "should totals go at the top or bottom", "this report table is a mess", or is preparing tabular data for an exec deck or published report. Do NOT use for designing database tables, keys, and normalization - use database-schema instead; for narrative structure around the numbers - use data-story instead; for assembling the full multi-section document - use formatted-report-writer instead.

    The same file is in 1 other repository

  • Pragmatic laravel layered architecture

    yuriymarad/laravel-skills/skills/pragmatic-laravel-layered-architecture Skill

    no license1★ repo

    Use this skill for Laravel backend tasks where implementing, changing, or reviewing functionality requires architecture decisions. This skill defines the project's custom architectural approach and should be treated as the source of truth for architecture, layer placement, and responsibility boundaries. Use it when deciding where code belongs, how to split responsibilities, how to wire a use case end-to-end, or whether something should be a Controller, Form Request, MCP Tool, Action, Core class, Value Object, Data object, Enum, Model, Event, Listener, Job, Contract, Integration, or Provider.

  • Vibecoder skill

    RemDee13/vibecoder-skill Skill

    1★

    Kickoff protocol for any new project in Claude Code. Trigger this skill whenever the user starts something new, such as a new project, product, service, app, bot, script, MVP, or prototype ("let's build", "starting a new project", "I want to make", "scaffold this", "spin up an app", "new repo"). It runs discovery on the idea, proposes a stack and external API services, scaffolds living documentation under ./docs, generates a product-specific CLAUDE.md, and optionally sets up an Obsidian wiki of the codebase. Use this at the start of any new build to run discovery, propose a stack, scaffold living docs, and write a tailored CLAUDE.md before coding begins.

  • Forensic read

    3243dwon/clear-eye/forensic-read Skill

    1★ repo

    Read any document the way a detective reads a witness statement — surface what it is NOT saying. Unlike a summarizer (which tells you what a text says), this skill exposes the subtext: hedging and weasel words, conspicuous omissions, buried leads, frequency tells, tone shifts, and non-answers. Use it on earnings calls, shareholder letters, job postings, press releases, politician statements, news articles, performance reviews, legal language, and the email that's clearly avoiding something. Trigger on phrases like "what are they really saying?", "read between the lines", "decode this earnings call", "is this a red flag?", "what's this not telling me?", "what are they hiding?", or any request to analyze the subtext, spin, or evasion in a document rather than just summarize it.

    The same file is in 1 other repository

  • Resume optimerzer claude skill

    DhruvkrSharma/Resume-optimerzer-claude-skill Skill

    no license1★

    AI/ML Career Copilot. ATS analysis, resume optimization, keyword research, GitHub review, LinkedIn review, project evaluation, interview preparation, market fit analysis, and career readiness scoring.

  • Website standards auditor

    Abhishek-Chougule/website-standards-auditor/skills/website-standards-auditor Skill

    1★ repo

    Audit and fix any website (new, in development, or already live) against the organization's mandatory engineering and web standards, then scaffold or repair the gaps after the user approves. Use this whenever the user wants an SEO, GEO, AEO, accessibility, performance, structured data, schema, sitemap, robots.txt, llms.txt, Core Web Vitals, Lighthouse, mobile, metadata, canonical, hreflang, redirects, or internal linking review, or asks to check a repository against the .gitignore and README policy, or mentions auditing, gap analysis, compliance, standards review, or "make my site follow our rules". Always use this for any website quality, discoverability, or standards conformance task even if the user does not name the standard, and follow its two phase flow that produces gap_identification.md first, then fixes only after explicit approval.

  • Cycle coded

    AlbionaHoti/cycle-coded/skills/cycle-coded Skill

    1★ repo

    Shape output using girl-internet operating language — menstrual cycle phases, astrology events, and eras (building, villain, soft life). Use when the user mentions cycle/phase/luteal/follicular/ovulatory/period/PMS, astrology (mercury retrograde, full moon, new moon), eras, girl math, walkthrough, be so fr, or asks for cycle-coded / mode headers. Also use when they want answers matched to energy, not generic productivity tone. Read glossary entries under glossary/ for the active term. Not medical advice — output policy only.

  • Architecture analyzer

    dayvisonassis/sdd-skills/skills/architecture-analyzer Skill

    1★ repo

    Performs a comprehensive surface-area analysis of any codebase scope (a component, module, service, layer, or the full project). Inventories every entry point, dependency, pattern, and integration, scores complexity, and produces a structured Architecture Analysis Report consumed by the deep-analyzer skill. Analysis/reporting only — never modifies the codebase. In the SDD flow this is the first setup step for an existing (brownfield) project; it feeds deep-analyzer and then gate-builder.

  • Agentmaster execute

    rhawk117/agentmaster/copilot/skills/agentmaster-execute Skill

    1★ repo

    Execute an agentmaster plan. Use when the user asks to execute, implement, or run a plan produced by agentmaster-plan, or invokes /agentmaster-execute. Honors the plan's execution mode (sequential default, justified parallel with optional pilot), gates every task on verification, re-verifies independently, runs the coherence pass, then chains into the review.

  • Dianpo

    jyuwaaw/dianpo-skill/skills/dianpo Skill

    1★ repo

    点破一段技术机制背后不明显的心智模型——角色是谁、token/凭证/密钥/证书归谁所有、谁在向谁证明什么、为什么设计成这个形状。资深工程师一句话能点明的东西("这个 token 是 OpenAI 的"),这个 skill 负责替用户点明。Use this whenever the user pastes a config, endpoint, protocol description, PR/work note, or auth flow and wants to understand it — trigger on "帮我理解", "点破", "这是谁的 token/key", "谁验证谁", "为什么要这么设计", "为什么非要这样/绕一圈", "没看懂这个流程", "who owns this token", "whose cert/key is this", "who signs what", "who is verifying whom", "who trusts whom", "give me the mental model", "explain this mechanism/design", "why is it designed this way" — and also proactively whenever explaining any challenge/verification/handshake/webhook/signature/receipt/attestation/OAuth-like mechanism, or certificate/CA/mTLS/SSO/SAML trust chains, where credential ownership is easy to misread.

  • Skill creator

    valorisa/Claude-Skill-Creator/skill-creator Skill

    1★ repo

    A meta-skill for Claude Code (Anthropic CLI) that guides you through creating, testing, and iterating custom skills via structured conversation. Designed with LLM Council methodology: interview intent, generate draft, smoke-test immediately, refine until satisfied. A skill is just a markdown file — this tool embraces that simplicity.

  • Interactive spec

    roeibh/interactive-spec Skill

    1★

    Generate a self-contained interactive HTML artifact from a spec, plan, or PRD so the developer can click through it, comment inline on any component or section, and submit those comments back to Claude — turning the HTML into a closed review loop, not a one-shot mockup. Use this skill whenever the user has just finished brainstorming a feature, has a spec or plan committed to `docs/superpowers/specs/` or `docs/superpowers/plans/`, mentions specs, plans, PRDs, design docs, requirements, mockups, or wireframes, says things like "make this concrete", "let me see it", "visualize the spec", "build a prototype of this", "turn this into a mockup", wants to review or iterate on a spec, or returns with a `feedback.json` or pasted feedback payload from a previously generated interactive spec. Especially use this right after `brainstorming` produces a design doc — offer it proactively then. Also triggers when the user says just "submitted", "feedback ready", "feedback sent", "applied", or similar short messages indicating they pushed feedback from the browser — in that case, check `~/.claude/interactive-spec-feedback/` for the most recent JSON file and consume it. Triggers for UI features (renders a clickable UI mockup) and non-UI features like backend, data pipelines, or algorithms (renders an interactive concept diagram or API explorer). Also triggers when the user pastes back a feedback bundle or drops a feedback.json. Don't undertrigger — if the user has a written spec and is about to implement, or is bringing feedback back from a review, this skill almost always belongs.

  • Exam study coach

    leoian611/exam-study-coach Skill

    1★

    一套基于课件、循循善诱的大学课程期末复习方法论,把抽象概念讲透、用真实工程/生活类比建立直觉、并精准锁定考点与计算题。当用户说要"复习某门课/准备期末/期末复习/帮我复习/出复习计划/讲讲这个知识点/我没看懂这页/考试会怎么考/出道题考我/帮我讲透XX原理",或上传课件 PDF/PPT、截图某一页课件、提到某门具体课程(如网络对抗原理、信息内容安全等)想搞懂内容时,都要使用这个 skill。即使用户只是随口问"这个是什么意思""为什么是这样",只要上下文是在复习某门课,也应使用本 skill 的方法来回答,而不是直接给百科式答案。

  • Antiflow

    ilyasstrougouty/antiflow/.agent/skills/antiflow Skill

    1★ repo

    Prevents the agent from writing core business logic. Use this when the user says "Activate Antiflow" or asks to set up a project while preserving human tasks.