The catalog
609,344 rows, by stacks then stars
0xkaizoku/launch-playbook Skill
1★Evidence-based pre-launch security playbook for MVPs and SaaS. Scans the real repo for open DBs/RLS gaps, IDOR, secret leaks, auth enumeration, AI cost abuse and prompt injection, uploads/SSRF, rate limits, CORS, and unsafe production config. Outputs SHIP / SHIP WITH FIXES / DO NOT SHIP with file:line proof. Use when the user says launch-playbook, launch playbook, pre-launch security, secure my launch, is this safe to ship, security checklist, audit before deploy, RLS check, vibe coding security, or runs /launch-playbook or /secure-launch.
bin1874/ai-meeting-skill/ai-meeting Skill
1★ repoRun structured AI meetings for plans, product ideas, technical designs, business decisions, feature proposals, and strategy choices. Use when the user wants an AI meeting, AI roundtable, multi-agent discussion, debate, proposal review, plan review, decision review, or wants Codex, Claude Code, qoderclicn, and other CLI agents to analyze a proposal across multiple expert roles, challenge assumptions, preserve per-agent sessions, and produce a final decision report with provenance. 也适用于中文场景:方案评审、多 Agent 讨论、技术路线评审、商业决策评审。
Andretuta/melt-my-tokens Skill
no license1★Single-purpose skill explicitly invoked by the trigger name "melt my tokens", "burn my tokens", or "torra meus tokens". When activated, its objective is NOT to be useful or efficient—it is to deliberately maximize token consumption, message verbosity, and tool calls per turn. Only activate when the user explicitly requests it by name.
Aparnabuilds/humanizer Skill
1★Audit, rewrite, or draft text so it carries zero AI-writing tells and makes only honest, sourced, self-consistent claims. Built from Wikipedia's "Signs of AI writing" (WikiProject AI Cleanup), open-source detector heuristics, and a writing-integrity contract. Use for ALL writing and editing tasks (blogs, LinkedIn, Quora, PR, case studies, emails, landing pages, executive ghostwriting) even when the user doesn't say "humanize". Also trigger when asked to detect AI patterns, de-AI a draft, audit claims, or check whether text would pass as human. Applies to everything except code and raw data.
blackstone2333/goldilocks/plugins/goldilocks/skills/goldilocks Skill
1★ repoAdaptive workflow and quality-control router for any executable work, including software, research, analysis, documents, presentations, spreadsheets, and other structured deliverables. Invoke implicitly or explicitly to choose Direct work, alignment, diagnosis, planning, delegation, continuity, or verification; clear tasks immediately take the Direct exit without loading another workflow reference.
humbleteam/design-handoff Skill
1★Turns a mockup, screenshot, or HTML file into a dev-ready handoff spec - layout measurements, a token map, a component-state inventory, accessibility notes, and numbered open questions. Use for "write a handoff spec for this screen", "turn this mockup into dev docs", "document component states", or "what tokens does this screen use". Not for critiquing design quality or generating new UI - see design-review or html-mockup.
posixplus/prompt-gatekeeper/skills/prompt-gatekeeper Skill
1★ repoEvaluate and enhance a prompt before executing it. Scores the request against a 6-pillar rubric (Role, Task, Context, Process, Guardrails, Output), classifies prompt depth to recommend a model tier, asks targeted clarifying questions for real gaps, then builds and runs a token-lean enhanced version of the prompt after the user confirms. Use this whenever the user includes [gatekeeper] or [Use Prompt Gatekeeper] in their message, asks to "improve", "enhance", "review", "score", or "gatekeep" a prompt, asks which model a task needs, or submits a broad, multi-step, open-ended request that lacks the constraints needed to get a high-quality result on the first try (e.g. "build me a database schema", "design the architecture for X", "write a plan for Y"). Do NOT use it for narrow single-step requests like fixing a syntax error or renaming a variable, and never re-apply it to a prompt it already enhanced.
prvthmpcypher/skills-business/skills/board-deck-builder Skill
1★ repoStructures and drafts board meeting decks/updates — standard section flow, metrics presentation, and how to frame asks/decisions needed from the board. Use this whenever the user is preparing a board meeting deck or update, asks how to structure a board presentation, needs help framing a difficult update (missed targets, a pivot, a fundraise ask) for a board audience, or wants feedback on an existing board deck draft. Distinct from investor-pitch-deck-writer, which is for raising a new round rather than updating an existing board.
DXShelley/obsidian-cli-plugins-skill/skills/obsidian-cli-plugins Skill
no license1★ repohcussi/claude-code-toolkit/.claude/skills/new-agent Skill
no license1★ repoScaffold a new agent in this claude-code-toolkit repo (create agents/<name>.md, the mirrored docs/agents/<name>.md, and add the README table row) following repo conventions. Use when adding a new agent to the toolkit.
Swarno1996/Handoff-pill Skill
1★Generate a handoff pill, a single dense markdown file that carries a long chat's full context, decisions, solved problems, and the user's working directives into a fresh chat. Use whenever the user says pill, handoff pill, context pill, or ingestible pill; asks to package, transfer, or hand off this conversation to a new chat; says the chat is getting too long or slow and wants to continue elsewhere without losing context; or asks to distill the session's learnings into a portable file. Also use in reverse, whenever a file named like *_PILL.md or *HANDOFF*.md is uploaded or pasted at the start of a chat, by following this skill's ingestion protocol before doing anything else.
BhaveshKhaple/bhavesh-claude-skills/graph-engineering Skill
1★ repoDesign resilient multi-step LLM/agent workflows using the loops-and-graphs pattern. Covers all 5 layers: reflection, tool use, planning, multi-agent coordination, and critique loops — with anti-patterns and cost guidance.
Aakreit/design-counsel Skill
1★Design Counsel — evidence-grounded senior product design and UX review for screenshots, prototypes, specifications, implemented interfaces, and end-to-end workflows. Produces prioritized findings for UX audits, design critiques, workflow coverage, accessibility, content, visual craft, dashboards, onboarding, forms, settings, billing, checkout, and enterprise administration. When explicitly invoked for greenfield design exploration, it can also research precedents, frame directions, and critique its own concepts before implementation. It does not replace specialized implementation skills or force staged exploration onto a routine build. Never treats visual precedent or an isolated screenshot as proof.
huangjie127/pitch-video-auto-generation Skill
1★Turn a product website URL (or a product description) into a real, finished MP4 pitch video in Apple WWDC launch style: AI-generated cinematic shots (liquid glass / luxury-tech CGI) via Atlas Cloud video models, AI-generated soundtrack, premium typography overlaid in post, auto-stitched with ffmpeg. Use whenever the user wants an actual video file for a product: "pitch video", "产品宣传视频", "生成一条视频", "宣传片成片", "WWDC 风格视频", "AI 生成产品视频", "出一条 30 秒的片子", or gives a product URL and asks for a video/film/广告片. This produces a real .mp4 by calling paid generation APIs — distinct from the apple-launch-video skill, which renders a free HTML animatic; prefer THIS skill when the deliverable is a video file, and mention the HTML animatic as a free preview option for the script.
Professional Ai Governance Framework
Kamel707/Professional-Ai-Governance-Framework Skill
no license1★Governance framework for using AI within a regulated professional practice (engineering, law, medicine, finance, etc.). Use whenever a deliverable produced with AI assistance carries the professional responsibility of its author: a calculation, a diagnosis, an opinion, a client report, a documented decision. Structures work through validation gates (G0–G5) and adapts the level of rigor to criticality (N1–N4).
xr09/zeal-docs Skill
no license1★Consult offline documentation from locally installed Zeal (Linux) / Dash docsets. Use this WHENEVER a coding, debugging, or config task involves a technology that has a docset installed — to confirm exact signatures, flags, return values, defaults, or behavior instead of relying on memory, AND for conceptual "how do I / how does X work" questions, since docsets also contain tutorials and how-to guides. Installed docsets include Ansible, Bash, Bootstrap 5, C, Django, Docker, ElasticSearch, Emmet, Flask, Go, HTML, Jinja, Nginx, NodeJS, PostgreSQL, Python 3, Python Telegram Bot, Redis, Rust, SQLAlchemy, SQLite, Scrapy, and Wagtail. Trigger on questions like "what are the args to X", "does this function return Y", "which flag does Z", "how do I do X in Python/Go/...", or before writing non-trivial API calls in these languages/frameworks. Works fully offline; no network needed.
wysocki-lu/pisz-po-ludzku Skill
1★Poprawna, naturalna polszczyzna bez manier AI. Używaj przy pisaniu lub redagowaniu KAŻDEGO polskiego tekstu (artykuł, e-mail, post social, raport, oferta, UI copy, komunikat): usuwa AI-tells frazowe, strukturalne i typograficzne, pilnuje rejestru grzecznościowego, odmiany i konkretów zamiast waty.
makieali/claude-code-engineer/skills/architect Skill
1★ repoAnalyzes a problem and generates a phased execution plan with progress tracking, shared contracts, dependency graphs, per-phase isolation, and task-level detail. Use when tackling any large feature, refactor, migration, or complex fix. Trigger: "plan this", "break this down", "architect this", "create a plan".
AndriyKalashnykov/flight-path/.claude/skills/environment Skill
1★ repoDevelopment environment setup, tool locations, and dependency installation for the flight-path Go project. Use when setting up the project, installing tools, troubleshooting PATH issues, or asking about Go/Node versions. Do NOT use for runtime troubleshooting, workflow guidance, or CI pipeline questions.
FarzamMohammadi/dev-toolbox/.claude/skills/commit Skill
no license1★ repoAnalyze code changes, group them into logical packages where appropriate, to create sequential, clear, descriptive commits with effective titles and detailed descriptions
morganmuli/metaskill/examples/data-science/.claude/skills/evaluate-model Skill
1★ repoLoad the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.
The same file is in 1 other repository
komodgn/meta-android/.claude/skills/add-data-module Skill
1★ repoCreates a new data module in the MetaSearch Android project. Use this skill when requested to 'add data module', 'implement a repository', 'implement a usecase', or 'add a data layer implementation'.
stefan-stepzero/shipkit/install/skills/shipkit-adr Skill
1★ repoLand one architecture decision atomically: full entry to architecture-archive.json, hard-capped lean entry to architecture.json. Handles new decisions, supersession, amendment. Triggers: 'record this decision', 'log an ADR', 'we decided', 'supersede ADR', 'that replaces the earlier decision'.
waddie/lisp-validator-skill Skill
1★Validate Lisp code (Clojure, Racket, Scheme, Common Lisp) for syntax errors, parenthesis balance, and semantic issues. This skill should be used when validating Lisp code files, checking for syntax errors before execution, or validating LLM-generated Lisp code including incomplete or partial expressions. Provides structured JSON output optimized for automated workflows.
wrm3/ai_project_template/.claude/skills/artifacts-builder Skill
1★ repoSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
The same file is in 15 other repositories
JamesPrial/claude-plugins/.claude/skills/claude-code-plugins Skill
1★ repoContains all relevent documentation for Claude Code Plugins. ALWAY PROACTIVELY use when work on or with plugins.
kevinl95/ForecastSkill/forecast_skill Skill
1★ repoProvides real-time weather forecasts using OpenWeather API. Use when users ask about current or future weather conditions, temperature, precipitation, or weather-dependent planning for any location (e.g., 'What's the weather in Paris tomorrow?', 'Will it rain in Seattle this weekend?', 'Should I bring a jacket to Denver?').
TELLEBO/universal-framework-os Skill
1★Universal operating system for every Claude interaction. Apply on every message regardless of topic — coding, writing, research, math, physics, scraping, planning, debugging, creative work, analysis, conversation, or any other task. Defines how Claude thinks, plans, executes, and validates ALL work using frameworks from 19 repos and 3 reference books. Triggers on everything: any prompt, question, request, topic, domain. Includes spec-driven development (GSD), agentic skills (Superpowers), agent harness (ECC), multi-agent swarm orchestration (Ruflo), web scraping (Scrapling, Crawl4AI, Firecrawl, Scrapy, Crawlee), intelligence pipelines (Crucix), autonomous research (AutoResearch), swarm prediction (MiroFish), GraphRAG knowledge graphs, cybersecurity (HexStrike), session memory (claude-mem), and math/physics reference knowledge. NOT optional — foundational layer for all work.
joncutrer/astrojs-expert-skill Skill
no license1★Expert guidance for building websites and applications with the Astro web framework (v5 and v6). Use this skill whenever the user mentions Astro, .astro files, Islands Architecture, Content Collections, Live Content Collections, SSR/SSG with Astro, Astro integrations (React, Vue, Svelte), View Transitions, Astro DB, Astro Actions, Server Islands, Astro Fonts API, or any Astro-specific concepts. Trigger for questions like "how do I do X in Astro", "build me an Astro component/page/layout", "set up a blog with Astro", "add React/Vue to my Astro site", "configure Astro for SSR", "migrate to Astro v6", or any task involving astro.config.mjs or the astro CLI. When in doubt, use this skill — Astro has many unique patterns that differ from other frameworks, and getting them right (especially v5→v6 migration changes) matters.
norahe0304-art/30x-seo-cn/seo Skill
1★ repoMaster SEO orchestrator with 23 specialized sub-skills across 8 categories. Comprehensive SEO analysis for any website or business type. Performs full site audits, single-page deep analysis, technical SEO checks (crawlability, indexability, Core Web Vitals with INP), schema markup, content quality (E-E-A-T framework), image optimization, sitemap analysis, site architecture planning, AI search optimization (GEO for ChatGPT, Perplexity, AI Overviews), backlink analysis, keyword research, SERP tracking, and AI visibility monitoring. Industry detection for SaaS, e-commerce, local business, publishers, agencies. Triggers on: "SEO", "audit", "schema", "Core Web Vitals", "sitemap", "E-E-A-T", "AI Overviews", "GEO", "technical SEO", "content quality", "page speed", "structured data", "site architecture", "metadata", "AI SEO", "backlinks", "link building", "keywords", "keyword research", "SERP", "AI visibility".
wemush/wemush-skills/wemush-mycology-assistant Skill
1★ repoGuide mycology research workflows using WeMush's MCP server for specimen tracking, research projects, cultivation analytics, and strain catalog exploration. Use when users ask about mushroom cultivation, research projects, specimen management, or mycology data analysis.
mattjaikaran/meridian Skill
1★Skill that gives AI coding agents persistent memory and quality enforcement
gigayaya/DAA-Master/plugins/DAA-Master/skills/daa-architect Skill
1★ repoUse when designing a new automation testing framework, scaffolding project structure, or planning test architecture following DAA principles
landim32/awesome-ai-skills/skills/readme-generator Skill
1★ repoGenerates a comprehensive, standardized README.md for any project. Use when the user wants to create or regenerate a README file following the project's documentation standard.
The same file is in 7 other repositories
Modellix/modellix-skill/.agents/skills/skill-creator Skill
1★ repoCreate 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.
The same file is in 66 other repositories
lc-rezende/AI-Custom-Skills/sample-skill-advanced Skill
1★ repoDemonstrate progressive disclosure with references, scripts, and assets for creating a new skill. Use when you need a structured example of how to split instructions and supporting files.
LaserPhaser/teamwork-plugin/skills/begin Skill
no license1★ repoUse when the user has a docs/PLAN.md from /teamwork:boss and wants to execute it with parallel chunk processing — dispatches multiple Developer, Code Reviewer, and QA agents simultaneously
robrohan/claude-skills/skills/KanbanBoard Skill
1★ repoManage an Obsidian Kanban board through a multi-agent workflow. Subcommands: init, plan, manage, work, verify, view.
smartbrainactivity/electron-desktop-builder Skill
1★Converts a web app (Express, React, Vite, Next.js) into an Electron desktop app. Use when starting a new Electron project from an existing web app, when setting up electron-builder for the first time, when creating main.ts/preload.ts boilerplate, when generating icon assets, or when configuring NSIS installers. Handles the full setup: project detection, main process, preload, icons, build config, installer, and first build. For troubleshooting existing builds, use electron-desktop-builds instead.
Firekid-is-him/Reasoning-Skill-Claude Skill
no license1★A reasoning framework that forces Claude to think beyond its training data, challenge its own answers, understand context before responding, and find paths around walls instead of stopping at them. Use this skill for every conversation — especially when a problem seems impossible, when the user is asking for something that "doesn't exist", when the obvious answer has already been tried, or when a creative or technical solution is needed. This skill should always be active.
Goodsmileduck/claude-registry/plugins/cicd-skills/skills/aws-codepipeline-codebuild Skill
1★ repoAuthors and debugs AWS CodePipeline + CodeBuild workflows — pipeline v1 vs v2 (triggers, variables), source providers via CodeStar Connections, artifact handoff, buildspec.yml authoring, IAM service roles, ECR pull permissions, VPC build environments, S3/local caching strategies, Lambda invoke action callback pattern, and manual approval setup. Use when working with AWS CodePipeline, AWS CodeBuild, buildspec.yml, CodeStar Connections, pipeline service roles, build VPC config, or "CodeBuild can't pull image" / "Lambda action hangs" debugging.
lijinnair/claude-code-skillforge Skill
1★Generates highly optimized Agent Skills for both native Claude Code and the Antigravity system, according to official best practices and the "Progressive Disclosure" strategy. Use when the user wants to build a new skill, turn a workflow into a skill, upgrade an existing skill to latest best practices, audit a skill for compliance, or structure agent instructions for either ecosystem.
b4tchkn/claude-review-metrics/plugin/skills/review-metrics Skill
1★ repoAnalyze team code review activity and performance metrics from GitHub PRs. Use when: (1) User asks about team review statistics or performance, (2) User wants to see who reviewed what PRs, (3) User asks about review response times or approval rates, (4) User mentions "review metrics", "review stats", "review activity", or "レビュー分析", (5) User asks about review bottlenecks, stuck PRs, or review load.
The same file is in 2 other repositories
violasgarbi/cae-tutor/cae-tutor Skill
no license1★ repoA comprehensive CAE (Cambridge C1 Advanced) exam preparation tutor for self-studying students. Activate this skill whenever a student mentions the CAE, C1 Advanced, Cambridge Advanced English, or any of its component papers (Reading & Use of English, Writing, Listening, Speaking). Also trigger for requests like "practise CAE", "CAE exercise", "Cambridge C1", "CAE writing task", "CAE word formation", "open cloze", "key word transformation", "CAE essay feedback", "CAE speaking part", or any request to prepare for or practise a C1-level English exam. This skill generates authentic practice exercises for Reading & Use of English (all four parts) and Writing (both tasks), gives strict examiner-standard feedback, and explains grammar and vocabulary in context. For Listening and Speaking, it provides expert strategy advice, language coaching, and format guidance, but does not generate exercises — these papers require authentic audio and real interaction to practise effectively.
thepushkarp/cc-codex-plugin/skills/codex Skill
no license1★ repoThis skill provides guidance on using OpenAI's Codex CLI for detail-oriented code analysis. Use when the user explicitly invokes "/codex", asks to "use codex", "run codex", "have codex review", or when Claude determines that Codex's sharp-eyed analysis would complement its work on code review, bug hunting, or planning tasks.
seburbina/skillhub/base-skill/skillhub-identity Skill
no license1★ repoSet up your Agent Skill Depot identity. Trigger on 'register me with agent skill depot', 'claim my agent', 'verify my email', 'rotate my API key', 'check my skillhub status'. One-off setup; later triggers handle key rotation and email-claim verification.
ukkuru/testmetry-skills/defect-analyzer Skill
no license1★ repoUse when someone asks to analyze a defect report, analyze bug data, perform defect metrics analysis, review a defect log, or upload a defect file for quality insights.
mcltyl/skill-ideation/skills/skill-ideation Skill
1★ repoGenerate agent skill ideas through problem-driven brainstorming. Situation-specific, narrow-but-universal. Triggers when user wants skill ideas or needs to expand their skill collection.
Adding azure communication services email
alexpizarro/azure-lean-stack-skills/skills/adding-azure-communication-services-email Skill
1★ repoAdds transactional email to an Azure web app via Azure Communication Services (ACS) Email — verification emails, password resets, notifications. Encodes the three ACS quirks that consistently break Bicep deploys (location:'global' literal, dataLocation in plain English not Azure region IDs, declare-order to avoid circular dependency), and the safeSend() wrapper that prevents email failures from crashing HTTP handlers. Use when adding email sending to a project, fixing ACS Bicep deployment errors, or migrating off SendGrid/Mailgun.
knitli/toolshed/plugins/codeweaver/agents/onboarding Skill
1★ repoCurated Claude Code plugins by Knitli
hedging8563/tokenlab-skills/skills/tokenlab-api-integration Skill
1★ repoIntegrates TokenLab chat, image, audio, video, and other API families into code with runnable examples, model discovery, public contract checks, and agent-first recovery paths. Use when the user wants to add TokenLab APIs to an app or script.
xedyx123/LUME Skill
1★Build award-winning frontend interfaces. Use for landing pages, portfolios, hero sections, or any UI needing premium animations, scroll storytelling, and Awwwards-level visual craft.
andersongrowth/searchlens Skill
1★Analyze Google Search data — GSC exports, keyword research files, ranking reports, CTR data, impressions/clicks CSVs — and extract actionable SEO insights. Use this skill whenever the user shares Google Search Console data, keyword lists, ranking spreadsheets, or any search performance data and wants analysis, diagnosis, optimization recommendations, content gap audits, or SEO strategy based on real data. Trigger even for partial data like "I have this GSC export, what do I do with it?" or "here are my top keywords, help me understand them." Also trigger when the user wants to compare periods (MoM, YoY, before/after update), estimate traffic impact, audit CTR performance, detect keyword cannibalization, or prioritize content investments based on real search data. Activate for any file upload that could contain search data.
frankxai/visual-intelligence/.claude/skills/vis Skill
1★ repoAgentic visual asset management — scan, audit, and manage images across your site with AI-powered quality enforcement
XueweiW-21/interview-prep-ai-assistant Skill
1★Generates personalized interview prep documents with real questions from the web, answers written in the user's voice, and post-round debrief support.
ParticleG/llm-fingerprint-skill Skill
1★Use when the user asks to identify, fingerprint, or verify an AI model's true identity, knowledge cutoff, or capabilities. Triggers on phrases like "model identification", "who are you really", "verify model identity", "knowledge cutoff test".
nainishshafi/developer-productivity-skills/.github/skills/architectural-planning Skill
1★ repoUse when the user asks to "plan my architecture", "design system architecture", "create an architecture document", "help me choose a tech stack", "what technologies should I use", "generate an architecture diagram", "plan my project structure", "recommend a database for my project", "design my API layer", "create a system design", "architecture planning", "tech stack recommendation", or wants interactive guidance to design and document a software system's architecture with technology recommendations.
bbaassssiiee/ansible-rabbit-hole/.claude/skills/ansible-coach Skill
no license1★ repoDeep Ansible expertise for DevOps practitioners. Use this skill automatically whenever the user is writing, reviewing, debugging, or asking questions about Ansible roles, playbooks, collections, inventory, Molecule tests, variable management, or project structure. Activate proactively when you see YAML that looks like Ansible, or when the user mentions tasks, handlers, defaults, group_vars, molecule, ansible-lint, galaxy, or vault. This skill encodes production-grade Ansible opinions and knows where the rabbit holes are.
PersephoneKarnstein/brewing-skill Skill
no license1★Use when brewing beer, making wine or cider (including country/fruit wines), fermenting mead, distilling spirits (bourbon, whiskey, Scotch, rum, brandy, tequila, vodka, gin, soju, shochu, arrack, arak, ouzo, raki, pastis, sambuca, absinthe), barrel aging, calculating alcohol content (ABV/OG/FG), troubleshooting fermentation issues, understanding yeast health, designing recipes, scaling batches, making sake, makgeolli, or other Asian fermented beverages, or when users mention brewing, fermentation, hops, malt, grapes, fruit wine, elderberry, dandelion, parsnip wine, barrel aging, oak, distillation, proof, specific gravity, yeast, ABV, mash, wort, must, spirits, bourbon, whiskey, mash bill, rum, cognac, tequila, mezcal, soju, shochu, makgeolli, sake, koji, nuruk, awamori, cheongju, arrack, arak, ouzo, raki, pastis, sambuca, anise spirits, punch, Swedish punsch, or louche, barleywine, barley wine, old ale, strong ale, parti-gyle, high-gravity brewing, wee heavy.
iruhdam1/prefix-first-design/skill Skill
1★ repoA session framework for AI-assisted product design based on Prefix-First Design. Helps designer-builders cast a stable brief once, explore against it freely, ship decisions with the work, and check that the brief still holds as products live on. Built from 15+ shipped prototypes by Madhuri Maram (madhurimaram.com).