The catalog
609,856 rows, by stacks then stars
hunghy93-pixel/FableWorks/skills/fable-safe-prompt Skill
2★ repoUse when rewriting a user's prompt for Claude Fable 5 / Mythos 5 to reduce false-positive safety-classifier refusals (stop_reason "refusal" -> user notified, request routed to Opus 4.8) on normal work such as refactoring, architecture review, research, documentation, code maintenance, benign security or ML work, or planning, without bypassing safeguards or enabling cyber, biology/chemistry, frontier-LLM/distillation, or reasoning-extraction requests. It also emits the leanest prompt that still does the job — fewest tokens, only the classifier-scope lines the task actually needs.
cleatai/agent-skills/skills/capability-statement-refresh Skill
2★ repoRefresh a government contracting capability statement from live CLEATUS data (capture profile, recent wins, and differentiators), producing updated copy plus a summary of what changed. Run monthly.
Bulk rnaseq counts to de deseq2
hossainlab/omics-skills/skills/bulk-rnaseq-counts-to-de-deseq2 Skill
2★ repoRun differential expression analysis on bulk RNA-seq count data with DESeq2 (R). Covers DESeqDataSet construction from a count matrix, tximport (Salmon/Kallisto), featureCounts, or SummarizedExperiment; pre-filtering; design formulas (simple, batch, paired, interaction, multi-factor, LRT); result extraction by coefficient or contrast; log-fold-change shrinkage (apeglm/ashr); VST/rlog transformations; and exporting significant genes. Use when the user has RNA-seq counts and wants differential expression, DE genes, volcano/MA inputs, or a DESeq2 workflow.
mdorf/agent-skills/skills/before-and-after Skill
2★ repoUse when a code change is meant to produce an observable improvement and no captured evidence exists yet: performance work (fewer SPARQL/SQL queries, fewer backend or triple-store round trips, batching, caching, lower latency), visual or UI changes (layout, styling, CSS, UX behavior), or any change whose effect can be demonstrated. Also use when the user asks to instrument before/after evidence (metrics or screenshots) for a fix, branch, or PR, or when about to open a PR whose central claim is an improvement.
gezihua123/cc-planet Skill
no license2★omer-sher/cosmos-os/skills/add-scenario Skill
2★ repoAdd a scenario (animated flow) to the Cosmos map. Use when the user says "add a scenario", "add a flow", "show what happens when X", or names a user action whose path through the system should play on the map. Traces the real flow from source across repos, then writes Scenario + Step entries (and any missing services/topics) into src/scenarios/.
7ucg/baron-forge/plugins/baron-forge/skills/commit-work Skill
2★ repoCreate high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages. Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
doramirdor/ppt90s/skills/ppt90s-video Skill
2★ repoGenerate a 90s PowerPoint-style video (WordArt, clip art, cheesy animations, Solitaire finale) from a folder of images or a Google Photos shared-album link. Use when the user asks to make a retro slideshow / 90s PowerPoint video / bar-mitzvah-style video from photos, or invokes /ppt90s-video. Interviews the user (music from 7 styles or a song link, number of images, length, title, optional event), then runs the bundled ppt90s.py and sends the video.
ibadbasit/skill_doc2ppt Skill
2★将 .md 或 .docx 文件转换为可投屏的单文件 HTML 演示文稿。设计风格:暖奶油×赭红×深棕黑,Cormorant Garamond + Noto Serif SC,键盘翻页+导航点。用法:/ppt <文件路径>
The same file is in 1 other repository
kimtth/azure-ml-finetuning-eval-skills/skills/azure-ml-dataset-creator Skill
no license2★ repoGenerate synthetic and simulated datasets for evaluation and fine-tuning using Azure AI Foundry simulators. Create non-adversarial task data, adversarial safety data, and conversation datasets without manual data collection.
tkolleh/skills/analyzing-architecture Skill
2★ repoDetects repository context, maps dependencies (enterprise-specific or general), and generates/persists architectural documentation.
noahrasheta/director/skills/blueprint Skill
2★ repoCreate, view, or update your project gameplan. Breaks your vision into Goals, Steps, and Tasks.
richardcarls/solid-js-best-practices Skill
2★Solid.js best practices for AI-assisted code generation, code review, refactoring, and debugging reactivity issues. Use when working in any SolidJS project or codebase — writing components, auditing code, migrating from React, fixing signals and fine-grained reactivity bugs, or integrating web component libraries. 67 rules across 9 categories (reactivity, components, control flow, state management, refs/DOM, performance, accessibility, testing, web component integration) ranked by priority.
jneaimi/evaluate-before-you-build/skills/design Skill
2★ repoSolution design skill based on Bloom's AI Collaboration model. Use when the user says /design, wants to design a solution, compare architectural options, evaluate tradeoffs, or produce a solution design document before building. Also trigger on phrases like "design the solution", "how should we architect this", "system design", "architecture review", "choose between approaches", "evaluate tradeoffs", "NFRs", or "solution shape". Produces an ADR-style document — not code.
Celina-create/X-Studio/skills/ai-agent-sdd Skill
2★ repoWrite a professional Software Design Document (SDD) for an AI agent or AI-powered product before writing code. Forces the team / vibe-coding agent to clarify problem, users, success metrics, agent workflow, LLM strategy, evaluation framework, failure modes, and acceptance criteria — so implementation is bounded, testable, and shippable. Use when starting a new AI agent project, before vibe-coding a prototype, when an existing AI feature is over-running scope, or when handing off an AI product to a new owner / external developer. Two depth levels: MVP (12 sections, ~30-min fill) and Full (23 sections, ~2-hour fill).
anombyte93/claude-research-skill Skill
2★Use when writing ANY implementation code, fixing bugs, or modifying existing code. Delegates research to a fast subagent that distills WebSearch results into compact RAG-efficient summaries. Main context never sees raw output.
The same file is in 1 other repository
shandar/pwp-plugin/skills/pwp-api-design Skill
2★ repoAPI design standards — consistent, predictable, documented endpoints. Use this skill whenever the user is building, reviewing, or planning an API. Also use when they mention REST endpoints, API routes, request/response shapes, status codes, pagination, versioning, or say things like 'design the API', 'what should this endpoint look like', 'review my API', or 'add an endpoint for X'. Covers REST conventions, status codes, response envelopes, pagination, filtering, versioning, and validation.
coastlight-ai/ai-writing-guardrails/skills/ai-writing-guardrails Skill
2★ repoAI-assisted academic writing process enforcer. Use this skill whenever the user wants to work on an academic paper, thesis, dissertation, or research document collaboratively with AI. Enforces phase-gated workflows, literature bias guardrails, citation verification, session transcript archival, and editorial decision logging. Triggers on: 'work on my paper', 'let's write', 'next section', 'paper session', 'resume writing', academic writing tasks, or any reference to a configured academic writing project. Also use when the user wants to set up a new academic writing project with process guardrails.
aroyburman-codes/para-second-brain/skills/para-system Skill
2★ repoA PARA (Projects/Areas/Resources/Archive) second brain plugin for Claude Code. Organize your work and knowledge with structured templates, quick capture, and review workflows.
gokhanarkan/claude-github-summary Skill
2★Generate an AI-synthesised summary of your GitHub activity (issues, PRs, commits) for a specified organisation and time period. Creates a natural language narrative with inline URL references. Use when user wants to summarise their work, review their contributions, or generate a work log.
cuishiqing/remotion-video-starter Skill
2★A complete Remotion video production automation skill for creating product promotional videos
nextauralabs/shelter-skill Skill
2★Connect to your Shelter financial data. Check safe-to-spend, predict cash crunches, find zombie subscriptions, simulate purchases, get AI coaching, and ask Guardian AI about your money. Read-only access to real bank data via Plaid.
bekservice/Famulor-Skill/skills/famulor-skill Skill
2★ repoComplete customer onboarding for the Famulor AI phone platform. Creates AI phone assistants from A to Z: detect the niche, gather configuration, write the system prompt, set up the knowledge base, deploy the assistant. ALWAYS use this skill when someone wants to create a new assistant, onboard a customer, mentions 'onboarding' or 'new client', or wants to set up an AI phone solution for a business. Also trigger on: 'create a bot', 'set up an assistant', 'configure a phone bot', 'answering machine', 'inbound bot', 'outbound bot' (German: 'Bot erstellen', 'Assistent anlegen', 'Telefonbot einrichten', 'Anrufbeantworter').
varunk130/claude-code-skills/plugin-skills/document-skills/algorithmic-art Skill
2★ repoCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
nevenincs/vaultspec-core/.vaultspec/skills/vaultspec-adr Skill
2★ repoCapture an architectural decision as an ADR in .vault/adr/. Use after research, before planning, when a significant design choice and its trade-offs must be recorded.
benman1/wiggum/.claude/skills/test-first-verifier Skill
2★ repoImplement a code change with trustworthy verification — plan and list the files that change, verify assumptions (APIs exist, imports resolve, config values), write tests first when none cover the change, then gate completion on tests + lint + type-check + happy/edge/failure spot checks. Use when implementing or fixing code and you want it actually verified, not assumed.
lemur47/si-protocols/skills/si-quick-check Skill
2★ repoDetect manipulation and disinformation patterns in spiritual, metaphysical, New Age, guru, channelled, prosperity-gospel, conspirituality, or self-help text, scoring seven dimensions plus a CVP consciousness-topology layer. Use whenever the user asks to quick-check, screen, vet, or analyse a passage for manipulation markers, coercion, red flags, or undue influence — e.g. "quick-check this", "analyse this text for manipulation", "is this spiritual content manipulative?", "run a threat check on this channelled message", "スピリチュアルのテキストを分析して", "この文章を診断", "操作のパターンをチェック". Auto-detects English or Japanese (日本語) input. Produces an approximate 0–100 threat score, a per-dimension table, quoted signals, matched tradition categories, and a CVP structural assessment. Heuristic pattern analysis for human judgement, not a verdict on truth or harm.
ShellyDeng08/codebase-slideshow Skill
2★Generate beautiful HTML slideshow courses for any codebase — glassmorphism reveal.js presentations with dialogue narrative, quizzes, and adaptive teaching.
ChewbaccaRoars/pathfinder-skills/skills/agent-architect Skill
2★ repoGuides users from simple automations to building their own agents. Introduces concepts gradually — from scripts that check-and-act, to multi-step workflows, to decision logic, to full agents. Use when someone is ready to level up beyond simple automations.
jackhendon/ecom-feedback-intelligence/.claude/skills/analyze-reviews Skill
no license2★ repoOpen-source Claude Code skills for turning eCommerce customer reviews into structured PM insights. Configurable for any brand via a single YAML file.
aavanian/convo-to-org Skill
2★Export the current conversation to org-mode format. Two modes: (1) notes — generates an org snippet for pasting into a notes file, (2) blog — generates a Hugo-compatible org file with TOML frontmatter. Trigger with phrases like 'save this to my notes', 'summarize for notes', 'save this for my blog', 'summarize for blog', or 'export this conversation'.
garroshub/backtesting-skill Skill
2★Use when a user wants reproducible ziplime backtests from a constrained JSON schema, with optional Yahoo ingestion and optional grid search, in any CLI agent environment.
Hambaobao/hambaobao-skills/skills/aliyun-cli Skill
2★ repoManage Alibaba Cloud resources using the Aliyun CLI tool. Use this skill whenever the user wants to manage any Alibaba Cloud resource via the aliyun CLI, including: ECS instances, VPC networking, OSS object storage, RDS databases, SLB/CLB load balancers, RAM users/roles/policies, DNS records, or aliyun CLI setup and authentication. If the user mentions "阿里云", "Alibaba Cloud", "aliyun", "ECS", "VPC", "OSS", "RDS", "SLB", "RAM", "ACR", "Container Registry", or any Alibaba Cloud service, use this skill.
w4xqz/code-review-skill/code-review Skill
no license2★ repo对指定代码目录进行全量代码审核,按模块并行subagent方式分批审查,生成问题报告并追溯问题作者。适用于通用代码工程的定期代码质量审查。
codepros100-dev/claude-windows-health-check/windows-health-check Skill
2★ repoComprehensive Windows system health check, diagnostics, and remediation
Chosen9115/design-board/skills/amir-salihefendic Skill
2★ repoAmir Salihefendic (Todoist/Doist) design critique — calm technology, daily-use sustainability, anti-bloat. Brutally honest UX/UI feedback focused on productivity and the day-500 experience. Scores on 5 principles and implements fixes.
ciaransaunders/Skills-Public/bailii-case-download Skill
2★ repoSearch BAILII (www.bailii.org) for a UK or Irish case and download the full judgment as a clean PDF. Use whenever the user wants a case from BAILII, gives a neutral citation (e.g. "[2024] EAT 114", "[2021] UKSC 5") or a BAILII URL and asks to fetch/download/save it, asks for "the full case as a PDF", wants to verify a case PDF against the authoritative source, or asks to find a case on BAILII by name. Also trigger when the user mentions BAILII, case law downloads, or building a bundle of authorities and needs the underlying judgments.
XZTP/meta-ads-optimiser Skill
2★Meta Ads analysis and optimisation for small business owners. Use when user mentions "Meta ads", "Facebook ads", "Instagram ads", CSV export, campaign performance, CPA, ROAS, ad rejection, creative review, targeting, placements, A/B testing, creative fatigue, ad copy, ad audit, or budget.
yacb2/aidex/skills/aidex-audit Skill
2★ repoUse when the user wants to assess the state of a feature, flow, or module — a UX, security, performance, or accessibility audit; cataloging bugs, gaps, and opportunities; retesting open findings; escalating a finding to the backlog; or updating audit methodology. Fires on "I want to do a UX / security / performance / accessibility audit", "before we ship I want to audit X", "audit the X flow or module", "catalog the state of X", "list bugs and gaps in X", "retest open findings", "register a finding under audit X", "escalate finding <id> to backlog", and /aidex-audit commands. Not for: auditing the Claude Code setup itself like skills or MEMORY.md (aidex); creating plans or decisions (aidex-conventions); generic backlog items not from a finding (aidex-backlog).
Timmy6942025/opencode-builder-skill Skill
2★Use this skill when the user is building extensions, plugins, integrations, or custom developer tools on top of OpenCode (opencode.ai). This includes: creating plugins with custom AI tools and lifecycle hooks, using the SDK for programmatic session control and multi-agent workflows, building model providers or MCP integrations, configuring opencode.json, and implementing advanced orchestration like checkpoint/resume, parallel execution, or adversarial review. Trigger for any development work that extends or automates OpenCode. Do NOT trigger for general usage questions, troubleshooting, UI theming, or tool comparisons.
davidtheproduct/claude-ship-skills/skills/critic Skill
2★ repoUse when someone asks to critique, challenge, tear apart, stress-test, review, or find flaws in positioning, messaging, outreach, landing pages, USP, competitive positioning, GTM strategy, or any customer-facing work.
aksheyw/career-command-center-template/skills/apply Skill
2★ repoPaste a JD to get full analysis + tailored resume + cover letter. Argument: [paste JD text here]
WhiteMuush/Your-Claude-DevOps-Teacher/skills/ansible-playbook-builder Skill
no license2★ repoAutomatisation d'infrastructure avec Ansible, playbooks, roles, inventaires, vault et modules. Se déclenche avec "Ansible", "playbook", "ansible-playbook", "Ansible role", "Ansible vault", "automatisation serveur".
Hectelion-SA/claude-dataroom-prep/skill Skill
2★ repoTrie et structure des documents en vrac en dataroom M&A-ready (11 dossiers + sous-dossiers multilingues), avec classification IA, détection des doublons exacts (SHA-256), détection des versions obsolètes, et checklist contextuelle enrichie via scraping site web + sources juridiques/fiscales/comptables (Légifrance, data.gouv, Fedlex). Multilingue FR/EN/DE/IT/ES. Utiliser quand l'utilisateur dit "structure cette dataroom", "trie ces documents", "prépare cette dataroom DD", "/dataroom-prep", ou demande de transformer un dossier en vrac en dataroom M&A.
isatimur/presentation-md/packages/core Skill
2★ repoGenerate a complete, polished slide deck as a single self-contained HTML file. Covers pitch decks, sales demos, investor updates, keynotes, and product launches — across 5 radically different visual identities. Use whenever the user wants to build any kind of presentation.
webmilmind1/claude-plugins/frontend-kit/skills/animejs Skill
no license2★ repoThis skill should be used when the user asks to "animate with anime.js", "use animejs", "add an animation" with timelines/staggers/springs, "animate on scroll", "make this draggable", "animate SVG" (draw lines, morph paths, motion paths), "split text and animate it", or when working in a project that imports from "animejs". Covers the v4 API (animate, createTimeline, stagger, onScroll, createScope) and v3→v4 migration.
ErickRamirezAU/claude-skills/claude-skills/skills/markitdown Skill
2★ repoConverts files (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV/JSON/XML, ZIP, YouTube URLs) to clean Markdown using Microsoft's markitdown CLI, and optionally reviews the result for extraction artifacts (fragmented sentences, missing headings, ligature glitches, spelling errors). Use this skill whenever the user attaches a file and asks to convert it, extract text/content from it, "turn this into markdown," get a readable or editable version of a PDF or Office doc, or mentions markitdown by name — even if they just say something like "can you get the text out of this" or "make this PDF editable."
hunthung-code/siti-grants Skill
2★協助台北市企業申請 SITI 產業發展獎勵補助計畫,涵蓋創新研發補助(最高500萬)、創業補助、品牌建立補助、新創拔尖補助等。提供資格快速判斷、申請策略、計畫書撰寫指引、常見地雷清單。全計畫隨到隨審,無截止日。
kumarrahul85/tax-sarathi/skills/indian-tax-calc Skill
2★ repoCalculate Indian income tax, capital gains tax (STCG/LTCG), advance tax, and TDS for FY 2025-26 under old and new regimes; includes live ITR e-filing portal verification via Playwright-over-CDP
kbelasheuski/ios-architecture-skills/plugin/skills/ios-architect Skill
2★ repoSenior iOS architecture skill for choosing, auditing, refactoring, and migrating app architectures across UIKit and SwiftUI. Use when the user mentions architecture choice, refactor planning, codebase audit, migration between patterns, or asks which architecture to use.
inkatze/planwright/skills/builder Skill
2★ repoDetect a project's stack and recommend or apply the universal mechanical quality guards from planwright's core catalog (formatter, linters, type-checker, test runner, secret scan, commit hooks, CI gate), plus the growable breadth dimensions. Escalates stake-bearing decisions (auth, data modeling, security posture, integration surface) into the deferral mechanism instead of auto-defaulting them. Plugs into /spec-draft's design phase and /execute-task's guard-application step.
jamesxjz/html-to-pdf-agent-skill Skill
2★将远程HTML网页转换为本地PDF文件,支持身份验证、自定义请求头、JavaScript渲染和CSS样式。支持单页转换和完整文档转换(自动爬取侧边栏所有子页面)。当用户需要下载网页为PDF、转换HTML到PDF、保存网页内容为文档、或提到完整文档/所有章节时使用。
0x0funky/claude-cache-guard Skill
2★Prevents prompt-cache thrash and runaway token burn in long or image-heavy agent sessions. Load BEFORE reading images/screenshots (visual QA, render checks, UI verification, diagram review) in a conversation that already has substantial history, when running long agentic loops with periodic wake-ups, or when the user asks why token usage / rate limits burn unusually fast. Teaches batched image reads, delegating vision work to isolated-context subagents, write-once notes instead of re-reading, and keeping large tool outputs out of context. Includes an audit script to measure a session's cache write/read ratio.
YuYY2004/excel-skills/claude/skills/excel-date-to-text Skill
2★ repoScan all date columns in Excel and convert datetime values to user-specified text format (yyyymmdd, yyyy-mm-dd, yyyy/mm/dd, yyyy年mm月dd日, or any custom combination). Supports three output positions: insert new column on left, insert new column on right, or replace original column. New column headers can be customized, defaulting to "{original name}(text)". 扫描 Excel 中所有日期列,将 datetime 转为用户指定的文本格式(yyyymmdd、yyyy-mm-dd、yyyy/mm/dd、yyyy年mm月dd日 等任意组合)。支持三种输出位置:左侧插入新列、右侧插入新列、替换原列。新列表头可自定义,未指定时默认"{原列名}(文本)"。 Trigger keywords: "date to text" "yyyymmdd" "date format" "left of date column" "right of date column" "replace date column" "format date" 触发词包括"日期转文本""yyyymmdd""日期格式""日期列左边/右边""替换日期列""格式化日期"。
kalyvask/entrepreneurship-lessons/.claude/skills/ent-career-coach Skill
2★ repoCoach a career decision for someone who wants to end up building or joining startups — which job to take, how to evaluate offers, whether to take a chief-of-staff role, when to leave. This is the OFF-SPINE career layer, separate from the 00→07 venture journey. Use when the question is "where should I work / which offer / should I take this role," NOT "how do I build my company." Full reference in career/career_strategy.md.
kdykes/synthetic-customer-discovery Skill
no license2★Customer discovery with grounded synthetic personas. Plan interview studies, build evidence-grounded persona files, run synthetic discovery interviews against them, and synthesize transcripts (real or synthetic) into evidence-backed reports. Use when planning customer or user interviews, writing screeners or interview guides, building or refining personas or an ICP profile, pressure-testing positioning or pricing hypotheses before talking to real people, or synthesizing interview transcripts. Synthetic output is always framed as hypothesis, never as validation.
Creative coding concept coach skill
rasagy/creative-coding-concept-coach-skill Skill
no license2★A creative-partnership coach for developing art/tech project ideas — especially computational, generative, algorithmic, data-driven, or web-based work. Use whenever the user shares a rough one-liner, sketch, or short project idea and wants help brainstorming, fleshing it out, exploring directions, finding references, or "coaching" the concept — including phrases like "help me flesh out," "what would you do with this," "I have an idea for a piece," "brainstorm with me on this," or when they paste a prior session summary to resume. Also trigger for ideas that seem non-computational at first — this skill engages regardless of medium and clarifies direction with the user. Do NOT trigger for requests to build/code the piece end-to-end without exploration, or to write final artist statements or concept docs.
tony95253/llm-council Skill
2★6-Agent Council 重大決策審查。用 5 個獨立子 agent(反對者/第一性原理/擴張者/局外人/執行者)+主席綜合,反制 AI 順從與確認偏誤。當使用者說「開 council」「開議會」「council 分析」「/llm-council」,或在重大決策(商業方向、定價、架構取捨、要不要全職/投入)上明顯在尋求認同時使用。不適用於日常小問題、事實查詢、文案修改。
yyy805/my-skills Skill
no license2★通用 AI 提示词与技能资产管理器。扫描本地任意目录下的 prompt/skill 文件, 生成交互式 HTML 技能地图,支持 Claude Code、ChatGPT、Cursor、Gemini 等任意平台。 当用户说 "/my-skills"、"列出我的 skill"、"我装了哪些技能"、"帮我整理 prompt 清单"、 "查看我的提示词库"、"show my skills"、"what prompts do I have"、"技能总览"、 "我有哪些 prompt"、"整理我的 AI 工具箱" 时触发。 **不要 undertrigger**——只要用户想盘点自己的 AI 提示词/skill 资产就必须调用本 skill。
jneaimi/blooms-ai-collaboration/skills/think Skill
2★ repoBloom's AI Collaboration Framework — a cognitive protocol for human-AI collaboration. Ships as the /think Claude Code skill with the 9-pillar life taxonomy and the auditability boundary. v2.0.