The catalog
610,220 rows, by stacks then stars
dysfunc/ai-plugins-cc/dist/plugins/gemini/skills/gemini-cli-runtime Skill
4★ repoInternal helper contract for calling the gemini-companion runtime from Claude Code
akhilkannur/marketing-agent-blueprints/skills/10k-report-prospector Skill
no license4★ repoParses a public company's 10-K (Annual Report) to extract specific 'Risk Factors' and generates a cold email positioning your product as the solution.
echowang97/brandbook-skill Skill
4★Distill any brand into a complete brand system: paste a URL, name, or screenshots and get a design-model.yaml (single source of truth), a script-rendered brandbook.html (tokens, type, voice, imagery spec, components, applications) and one hand-crafted landing page that proves the system captures the brand. Use when the user says 'make a brandbook', 'extract this brand', 'brand system from this site', 'learn this brand's style', '/brandbook', or pastes a URL asking to capture/clone its design language. Also triggers for 'remix my brandbook' or 'make it warmer/darker/etc'.
avikbal-dm/anti-ai-writing-claude-skill Skill
no license4★Avik Bal's writing-style ruleset for clear, specific, original text that reads like a person wrote it. Use it two ways: write fresh copy in this voice, or run a humanizing edit pass that strips the tells from an existing draft. Triggers on humanize this, make it sound human, this reads like AI, remove AI tells, de-AI this, rewrite this robotic copy, edit for voice, make it less generic, polish this draft, or write in my voice. Covers banned AI vocabulary and phrase shapes, the negative-parallelism and reframe ban, analogy and metaphor control, specificity rules, and a final cleanup pass. It asks the user for the real inputs only they have and never fabricates facts, data, or examples. Apply with judgment. Clean writing wins.
aetox-skills/idea-to-architecture-agent Skill
4★Question-first architecture proposal discipline for AI agents. Use when a user provides a raw idea, product concept, feature request, business goal, or system goal without an existing implementation and needs a reviewable architecture proposal with assumptions, open questions, risks, decision options, workflows, module boundaries, and handoff notes.
emlog/emlog-app-dev-skill Skill
no license4★协助开发 Emlog 应用(包括插件和主题)。当用户想要创建新插件或主题、修改迭代现有插件或主题、询问 Emlog 应用开发规范、查找模板变量、使用系统通用函数或挂载点时调用。Make sure to use this skill whenever the user mentions emlog plugins, emlog themes, emlog templates, php emlog, Emlog插件, Emlog主题, Emlog模板, 插件开发, 主题开发, 或者 Emlog 相关开发需求。
fruafr/skills/skills/incus-doc Skill
4★ repoGround AI responses and scripts in offline authoritative Incus CLI help and documentation. Must be loaded before using incus, writing scripts that invoke incus CLI commands, invoking incus CLI commands directly, or answering questions about incus. Reduces hallucinations by routing all claims through verified reference files.
nouvath07/KhamLao/skills/khamlao Skill
4★ repoຄຳລາວ (KhamLao) — Lao language quality + compression skill for Claude. Always loaded when the user is writing or requesting Lao output. Covers: register (ຂ້ອຍ/ເຈົ້າ vs ຂ້າພະເຈົ້າ), tense (ສິ not ຈະ), script-only rules, tone marks, top false-friend Thai→Lao corrections, and a built-in vocabulary reference (everyday, cooking, school, nature). Triggers: - "/khamlao" / "/khamlao full" / "ຄຳລາວ" / "ໃຊ້ລາວ" / "ຕອບເປັນລາວ" → enable full - "/khamlao lite" → enable lite - "/khamlao stop" / "ຢຸດຄຳລາວ" / "ປ່ຽນເປັນປົກກະຕິ" → disable
chkfail/mindreader-skill Skill
4★构建数字影子,分析过去对话,预演未来对话
dreamid27/frontend-slides Skill
4★Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
mihkarp/trash-panda/skills/trash-panda Skill
4★ repoA raccoon that digs through your Claude/ChatGPT chat history, pulls out the valuable artifacts, and files them into a local markdown "den" organized by project. Triggers on "/dig", "/den", "/sniff", "/feed", "/wash", "/nap", or natural language like "go dig through my chats", "what piled up", "drag the good stuff into my projects", "show me my den". Reads recent chats, extracts four artifact types (To Do's, Shiny, The Plan, Loot), routes each to a project file, dedupes, appends, links back to the source chat, and rebuilds the den index. ALWAYS use this skill for these commands — do not do it by hand.
Lion-1209/Lion-Skills/skills/clarifying-questions Skill
4★ repo需求模糊、含隐藏假设或 X-Y problem,需先澄清再动手时。
tuoxie2046/claude-code-research-skills/plugins/academic-research-skills/academic-paper-reviewer Skill
no license4★ repoMulti-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy.
Epistates/sparX/.claude/skills/analyze Skill
4★ repoRead real engagement analytics from X via browser automation. Use when the user wants to check how their posts are performing, review analytics, or get real engagement data without manual entry. Requires claude-in-chrome.
Consulting client presentation
matellez/claude-skills/consulting/consulting-client-presentation Skill
4★ repoAUTO-TRIGGER: Apply this skill when the user is preparing to present findings, recommendations, or results to a consulting client. Trigger phrases include: "presenting to my client," "client readout," "how do I present what I found," "delivering findings," "presenting my recommendations," "the client meeting is this week," "I need to show what I discovered in their HubSpot," "presenting my audit results," or any situation where the user is preparing to communicate findings or recommendations to someone who is paying them for consulting work. Also trigger when the user is preparing for a status update with a consulting client, or when they need to deliver bad news about what they found during an engagement. Do NOT trigger for internal presentations to leadership at a full-time employer (use marketing-budget-defense or managing-up for those), or for general presentation design. This skill is specifically for the independent consultant presenting findings or recommendations to an external client.
The same file is in 1 other repository
akhilguptahub/fable-skill Skill
4★Apply Claude Fable 5's reasoning methodology on any model (Haiku, Sonnet, Opus). Use this skill whenever the user says /fable, "use fable", "fable mode", "think like fable", "fable-level thinking", or asks for maximum reasoning quality, deep analysis, rigorous thinking, or "think harder" on a problem. Also use when the user asks for a decision, strategy, architecture, analysis, or debugging task where getting it wrong is costly and they signal they want the strongest possible reasoning. It upgrades HOW the model reasons (structured decomposition, competing hypotheses, belief-killing, self-verification) without changing the model itself.
fabkury/twq Skill
4★Study a task, ask me clarifying questions, then proceed.
yegor256/critic/skills/analyze-argumentation-flow Skill
4★ repoUse this skill when the user wants to diagnose flaws in argumentation in English prose, without rewriting it.
vignzpie/resume-agent-skills/career-profile-builder Skill
4★ repoBuild a comprehensive career profile (career_profile.md) through a structured interview that adapts to the user's experience level and career track. Use this skill whenever the user wants to "build a resume from scratch", "start fresh", "create my professional profile", "I don't have a resume yet", or when the resume-tailor skill needs a profile and none exists. Also use when the user wants to refresh, expand, or update their existing career_profile.md after a job change, promotion, new project, or new skill. The output is a reusable source-of-truth that the resume-tailor skill consumes for every future job application — so it should be thorough and honest, not surface-level.
vladimirlucantis/meta-ads-framework-es/skill Skill
4★ repoAnaliza y optimiza campañas de Meta Ads (Facebook e Instagram) en español. Agnóstico de estrategia (Advantage+, segmentación manual, FRIA+CALIENTE, creative testing, WhatsApp/Mensajes). Activar con informes o métricas de campañas, capturas del Administrador de Anuncios, preguntas sobre pixel o audiencias, guiones de Reels, copy, o decisiones de pausar/escalar/mantener ad sets.
Imran-ml/claude-skills/.claude/skills/commit Skill
no license4★ repoUse this skill when the user wants to create a git commit, stage files, write a commit message, or finalize their work with a git commit. Also invoked by phrases like "commit my changes", "save to git", "git commit".
arslan555/claude-android-feature-skill Skill
no license4★Production-ready, step-by-step skill for implementing a new feature in any modern Android application (Kotlin, Jetpack Compose, Hilt, MVI, offline-first). Encodes module/package layout, file-by-file templates, naming conventions, and quality bars derived from the Now in Android (android/nowinandroid) reference architecture. Covers feature module scaffolding (single module AND api/impl split), Clean Architecture layers (Presentation → Domain → Data), MVI contract (Screen, View, ViewModel, UiState, Intent, Event, ViewMapper), Hilt DI, type-safe Compose Navigation, offline-first repository pattern with Room + Ktor, build flavours, Compose preview/test conventions. Includes embedded references for software design principles (SOLID/KISS/DRY/YAGNI) and quality gates verification (Detekt, Lint, coverage, scoring). Use standalone for complete feature building workflow from generation through quality verification.
alo-exp/multai/skills/comparator Skill
no license4★ repoGeneric Comparison Matrix Builder: creates, populates, and maintains weighted XLSX comparison matrices for ANY domain and ANY pair (or set) of solutions. Evidence comes from whatever is available — CIRs produced by MultAI's solution-researcher, documents in the working folder, LLM knowledge, or user description. A CIR is not required. Supports two entry points: • "compare X vs Y" — full standalone comparison from scratch (Gap 5 flow) • matrix operations on an existing XLSX — add-platform, reorder, combo, verify USE THIS SKILL when the user wants to: compare solutions head-to-head, build a capability matrix, add a platform to a matrix, reorder or verify a matrix, create a combo column, or produce a scored comparison of any two products. Trigger keywords: "compare", "comparison matrix", "capabilities matrix", "add platform", "update the matrix", "reorder", "verify ticks", "combo column", "score", "head-to-head", "which is better".
NTCHz/off-by-none/skills/off-by-none Skill
4★ repoUse when implementing or fixing code against a written spec, requirements doc, or ticket — especially under time pressure, "quick fix" or "minimal change" requests, or when about to declare work ready to ship.
Dhwanil25/Agentis Skill
no license4★Most AI tools give you one model and one answer. Agentis gives you a team. Open-source multi-agent platform across 12 LLM providers — watch agents think, collaborate, and deliver in real time.
yaniv-golan/skill-creator-plus/skill-creator-plus/skills/skill-creator-plus Skill
4★ repoBased on Anthropic's skill-creator — with bug fixes, working Cowork support, and official best practices baked in. Claude skill for creating, testing, and improving other Claude skills.
EdytaKucharska/keel/skills/architecture-review Skill
4★ repoReviews a proposed or existing software architecture for a product, feature, or system. Use this skill PROACTIVELY whenever the user describes how their product is structured, proposes a new architecture, mentions splitting or merging services, brings up data model decisions, discusses scaling, or asks any structural "how should we build this" question — even if they don't explicitly ask for an architecture review. Common trigger phrases include "should we use microservices", "should we split this service", "we're going to architect it like this", "I'm thinking the data model should be", "we'll use a queue here", "we want to scale to X", "we're going to add a new service", "should I separate the frontend and backend", "our backend is doing too much", or any sketch of how a system or feature is structured. Also triggers when the user shares an architecture diagram, a system description, or a feature spec that implies structural choices. Especially important to trigger when the user is non-technical, is working with junior engineers, or has shipped through AI tools and doesn't fully know what they built. Produces a structured architecture review covering segment-aware context, stage/scale/team fit, Conway-law alignment, observability and operational readiness, one-way doors, an antipattern cross-reference, and at least two credible alternative shapes for the same system.
nmoinvaz/speedy-gonzales/skills/acli Skill
no license4★ repoCommon Atlassian CLI (acli) commands for Jira operations
toolbox-playground/super-claudio/skills/ai-and-agents Skill
4★ repoAI integration and agent building skill. Use when the user wants to use the Claude API, build AI-powered apps, create Claude Code skills or agents, connect MCP servers, or improve their prompts and AI workflows. Trigger on: "use the Claude API", "Anthropic API", "build an AI app", "create a Claude skill", "write a skill for Claude Code", "build an agent", "MCP server", "Model Context Protocol", "connect Claude to X", "prompt engineering", "improve my prompt", "system prompt", "AI workflow", "LLM integration", "build a chatbot", "fine-tuning", "Claude Code plugin", "create a plugin", "AI pipeline", "multi-agent", "tool use", "function calling". Also trigger when the user mentions: superpowers, skill-creator, claude-md-management, pr-review-toolkit, context7, or any Claude Code plugin by name. Do NOT trigger for: general code questions without AI integration (use software-development).
davccavalcante/supreme-coding-guidelines-skill.ah/skills/ah-parser Skill
no license4★ repoPermanently activates the .ah (Teleological Semantic Format) for any LLM. Bootstraps the grammar once per session, then asks the user once whether assistant responses should use normal language, .ah structured form, or .ah compact form. User input may be in any natural language. User code, diffs, commands, and identifiers are always preserved verbatim. Required dependency for every .ah skill.
rampstackco/claude-skills-pm/skills/after-action-report Skill
4★ repoRun a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event. Triggers on after-action report, AAR, postmortem, retrospective, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys. Also triggers when the user has just shipped something or just resolved an incident and wants to capture learnings.
The same file is in 1 other repository
erhwenkuo/stock_skills/.claude/skills/graph-query Skill
no license4★ repoNatural language queries to the knowledge graph. Search past reports, screenings, trades, research, and market context.
nocodework/growth-os/core/skills/audit Skill
4★ repoRun the Growth OS growth audit — SEO, page speed / Core Web Vitals, GEO (AI visibility), competitors, and a live GA4/GSC baseline — and write the results as an "## Audit Findings" section in the context hub. Use when someone runs /growth-os:audit, says "audit my growth," "how's my SEO," "give me a growth report," "what should I fix," or after onboarding to get a first read on the business.
arifulislamat/bd-income-tax-skills/skills/bd-income-tax Skill
4★ repoCompute and explain Bangladesh individual (personal) income tax under the Income Tax Act 2023 and the current Finance Act — tax slabs, tax-free thresholds (including women, senior citizens, persons with disabilities, third-gender, freedom fighters), salary exemption, the Section 78 investment rebate, minimum tax, net-wealth surcharge, TDS credit, filing/PSR rules, Tax Day, and penalties. Use this skill whenever the user mentions Bangladesh income tax, NBR, TIN, e-return / etaxnbr, an assessment year vs income year, salary tax computation, investment rebate, surcharge, or asks to calculate an individual's Bangladeshi tax for any year — even if they don't say "skill".
Pitchdrive/investor-update-skill Skill
4★Draft a monthly or quarterly investor update for your startup — structured like the updates VCs actually enjoy reading. Use when the founder asks to write, prepare, or send an investor update. Pulls KPIs from connected tools when available, asks for numbers when not, tracks commitments between updates, and renders a polished markdown (and optional single-page HTML) update.
ananthanandanan/skills/skills/engineering/handoff Skill
4★ repoGenerate a Markdown handoff document summarizing the current conversation so another agent (Claude, Codex, opencode, pi, ampcode, Cursor, or a fresh session) can resume without re-deriving context. Produces docs/<slug>-handoff.md. Invoke explicitly when a session is near its context limit.
mchlpdmnt/genz-writer-skill Skill
4★Write social media posts, blog entries, essays, research pieces, and creative writing in an authentic Gen Z voice — human, raw, and completely free of AI slop. Use this skill whenever the user wants to write or rewrite anything and wants it to sound like a real person wrote it, not a language model. Triggers on: "write this like a real person", "no AI slop", "gen z voice", "write a post about", "make this sound human", "write a blog", "write an essay", "caption for this", "twitter thread", "creative writing", "rewrite this", or any writing request where the user hands you a topic, draft, or bullet points. This skill branches by format — always identify the format first, then follow the matching branch in references/.
bx33661/oh-my-vul/skills/omv-audit Skill
4★ repoDeep-audits a candidate finding from an Evidence.v1 file. Use when the user has an omv-find result they want to investigate further, wants to prove or disprove a vulnerability, needs to fill Evidence.v1 fields for omv-report, or invokes `/omv-audit`. Reads .omv/findings/<id>.yaml and produces a confirmed or blocked finding with all required evidence fields populated.
WahyuS002/skills/skills/unvibe Skill
no license4★ repoCode ownership session that turns AI-written code into understood code. The agent shortlists "vibe-y" pieces from recent changes, checks the user's confidence, then guides explain/reimplement/test exercises in a LeetCode-style format and captures distilled per-piece ownership notes — all without silently mutating the repo. Use after an AI coding session, or on-demand when the user does not understand a specific API, function, or behavior the agent wrote.
Dragoon0x/product-skills/skills/alignment-influence/cross-functional-alignment Skill
no license4★ repoBring engineering, design, research, marketing, and sales onto the same page and keep them there. Covers alignment levels, RACI clarity, and continuous maintenance. Use when teams have different understandings of what's being built, cross-team dependencies are causing problems, or alignment keeps breaking down.
ahmeddabak/claude-arabic-writing/skills/arabic-writing Skill
4★ repoWrite and translate natural, grammatically correct Arabic — Modern Standard Arabic plus Egyptian, Levantine, Gulf, and Maghrebi dialects — that avoids machine-translation tells. Use whenever producing Arabic prose: writing original Arabic, translating into Arabic (especially from English), or editing/proofreading Arabic for grammar, spelling (hamza, ة/ه, ى/ي), agreement, collocations, punctuation, register, or naturalness. Use even when the user only asks to "say this in Arabic" or pastes Arabic text to fix.
JWCodeWrote/Agent_Skills_Plugin/AI-search-browser-use-main Skill
no license4★ repoUse this skill when a task needs AI-assisted web research via a real browser. Uses Chrome CDP (Chrome DevTools Protocol) as the primary automation method, with browser-use as fallback. Supports Gemini + Qwen queries with consolidated answers and citations.
ishosting/ishosting-manager/.claude/skills/ishosting-manager Skill
4★ repoComplete is*hosting infrastructure management via API. Order and configure VPS, Dedicated, Storage, VPN servers with custom hardware. Install OS, control panels, deploy apps and websites. Manage SSH keys, billing, invoices, DNS, and service lifecycle.
sanjay3290/notebooklm-skill Skill
4★Query and manage Google NotebookLM notebooks with persistent profile auth, source sync, batch/multi queries, and structured exports. Use when user asks to query NotebookLM, 'ask my notebook', shares NotebookLM notebook URLs, wants to list/create notebooks, manage sources, do bulk folder sync, dedupe, or audit exports.
The same file is in 1 other repository
zanwei/harness-design/skills/harness-design Skill
4★ repoQuality harness for design-dna Phase 3 output with browser-based visual verification. After an agent generates a design from a Design DNA JSON + user content, this skill acts as a verification and scoring layer — collecting all page resources via console/network inspection, performing section-by-section screenshot comparison against the reference website, frame-by-frame animation sampling, and driving a correction loop until the output is ship-ready. Use this skill when: (1) a design has been generated from a Design DNA JSON and needs quality verification against a reference URL, (2) you want to score how faithfully output matches its DNA spec AND the original website visually, (3) you need to review and correct design drift using real browser rendering evidence, or (4) you are iterating on a design and want structured pass/fail gates with screenshot proof before delivery. Triggers on "harness", "verify design", "score design", "design QA", "check design fidelity", "design review against DNA", "design quality gate", "audit design output", "does this match the DNA", "compare with reference", "visual comparison", "screenshot comparison".
closestfriend/slop-score-skill Skill
no license4★Run Sam Paech's eqbench Slop Score heuristic against a piece of writing — scores AI "slop" (overused words, slop trigrams, and "not X, but Y" contrast patterns) on a 0–100 scale and flags the specific offending phrases. Use when the user wants to slop-score writing, check a draft for AI-slop / GPT-isms, or get a Paech-style slop readout. Independent of any literary-critic agent or persona.
kcem/code-index/plugins/code-index/skills/code-indexing Skill
4★ repoUse when navigating source code by symbol with Universal Ctags: finding definitions, reading exact class/function ranges, building file/project outlines, checking duplicate symbols, or searching indexed symbols across projects. Prefer normal read/search for docs, config files, tiny files, or non-symbol text search.
indykite/skills/indykite-agent-gateway Skill
4★ repoDeploy and configure IndyKite Agent Gateway (IAG) in front of agent-to-agent (A2A) workflows or MCP servers. Use when wiring up A2A or MCP policy enforcement, modeling workflows in the IKG, or debugging IAG 401/403 responses.
ntholm86/principles-of-earned-autonomy-skills-suite/archive/v2/hansei Skill
4★ repoReflect on the improvement loop itself. Examine the trail, surface recurring findings, blind spots, methodology effectiveness, and what the loop has been ignoring. Meta-improvement - improving the improvement process. USE WHEN: reflect, retrospective, what are we missing, blind spots in the loop, why does this keep recurring, hansei, examine the trail, meta-improvement, loop critique, what hasnt worked, why is the score plateauing.
ahmedraza28/image-generation-skill/skills/image-generation Skill
4★ repoBest practices for prompting any text-to-image model (e.g. Imagen, Gemini Image, GPT Image, DALL·E, Stable Diffusion, Flux, Ideogram, Leonardo, Midjourney) to produce predictable, production-quality images. Use this skill whenever the task involves calling an image generation API, generating images programmatically, writing or revising prompts for image models, producing illustrations / photos / logos / posters / mockups / infographics / UI shots with AI, or debugging poor image output. Apply this even when the user just says "generate an image of X" — well-structured prompts dramatically outperform terse ones across every current model, and the cost of a bad prompt is almost always paid in retries.
shihabshahrier/Godot-Skill/.cursor/skills/godot Skill
4★ repoGenerate production-ready GDScript 2.0 for Godot 4.3+ with strict static typing. Auto-triggers on Godot, GDScript, or game development tasks. Enforces official style guide, modern architecture patterns, and version-safe syntax. Covers: player controllers, state machines, signals, tilemaps, save/load, UI, and more.
cfregly/gpu-perf-tune/plugins/profile-and-optimize/skills/_template Skill
4★ repoCopy this directory to plugins/profile-and-optimize/skills/<your-skill-name>/ and rewrite this description to be third-person + include WHAT the skill does and WHEN (specific trigger phrases). Max 1024 chars. Do NOT leave the word "template" in the real skill's description.
nataliacorrea03/claude-code-skills/skills/ai-writing-qa Skill
4★ repoScrubs scripts and copy for AI tells before they ship, then hands back a clean rewrite in your voice. Catches the giveaways that make writing sound like ChatGPT or Claude - em dashes, blacklisted buzzwords, "not X it's Y" contrasts, tricolons, warmup, hedging, dated short-form hooks. Auto-detects register (client-facing / internal / creative) and applies that voice. Trigger on "/ai-writing-qa", "scrub this", "de-slop this", "does this sound like AI", "QA this script", "QA this copy", "check this for AI tells", "make this sound human", or when you paste a script, caption, email, or piece of copy and want it cleaned before it ships. On-demand only, never auto-fires, never sends, never saves.
Standed/Seedance2.5 Skill
4★Seedance2.5 skill for AI video production. Use whenever a user mentions Seedance2.5, Seedance 2.5, AI video, short videos, marketing videos, product demos, talking-head videos, video prompts, storyboards, scene cards, B-roll, video repair, or continuity QA. Turn supplied scripts, briefs, assets, footage notes, or approved storyboards into grounded Seedance-ready plans, prompts, and checks; do not invent product claims, fabricate people, or claim platform controls without checking the active Seedance interface.
ltppp/douyin-ingest/skills/douyin-content-ingest Skill
4★ repoUse when a user provides an 抖音/Douyin (Chinese TikTok) creator profile, account, video link, or share text and asks for Top N popular or viral videos, video metadata, media download, speech audio, speech-to-text, captions, transcripts, or content research material. Do not use for generic local audio transcription, TikTok.com, or non-Douyin platforms.
eligapris/software-architect/.agents/skills/software-architect Skill
no license4★ repoSoftware architecture engineering consultancy skill. Analyzes overall application structure, recommends sustainable approaches, enforces architectural consistency, and documents decisions for future sessions. Use this skill whenever the user asks about system design, architecture decisions, feature integration strategy, technology choices, data management consistency, codebase structure review, migration planning, technical debt assessment, or any question about "how should I build/structure/organize" their application. Also trigger when the user mentions architecture, ADR, bounded contexts, clean architecture, hexagonal architecture, microservices, modular monolith, dependency management, coupling/cohesion, fitness functions, or technical debt. This skill ensures the app does NOT develop mixed approaches for data management, core logic, or integration patterns — and that every architectural decision is documented so future sessions can build on prior decisions rather than contradict them.
haixin-ye/skills/skills/idear Skill
4★ repoTurn a user's rough software, tool, automation, or AI-product idea into a clarified product definition, evidence-backed feasibility report, and implementation-ready technical handoff. Use when a user asks whether an idea can be built, whether suitable technologies/permissions/APIs exist, whether others have built it, what competing products or open-source projects exist, or how to begin if it is viable.
yuri-semenenko/ai-engineering-workspace/claude-code/.claude/skills/adr Skill
4★ repoScaffold an Architecture Decision Record (ADR) for a concrete decision that's already been made or is being made now. Use when the user says "ADR for X", "write up that decision", "ADR по <решение>", or wants to record a choice for future readers. Different from /rfc — RFC explores options; ADR commits to one.
circleghost/cloudflare-deploy-skill Skill
4★將網頁或 HTML 部署到 Cloudflare Pages 的標準方式。支援兩種模式:(1) 把文件放進一個文件中心站的對應子目錄再整包部署;(2) 把任意 HTML 或資料夾丟成一個獨立的 CF Pages 站並拿到網址。適用情境包含部署網頁、佈署 HTML、deploy 到 cloudflare、CF Pages、更新文件中心站、把網頁變成可公開訪問的網址。只要目標是把 HTML/網頁/資料夾變成線上網址,皆適用此 skill。
keli-wen/skills/skills-zh/ctx-research Skill
no license4★ repo基于项目持久 context 体系的深度调研。触发语:「ctx research」「基于 context 调研 X」「结合我们的 contexts 做深度研究」。先读已有 contexts,把问题磨到真正的知识缺口上,再多智能体展开调研,关键论断做对抗验证,结论写回去。