Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 696 files from 2 113 authors, of which 68 413 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Generates or updates highly detailed, machine-readable technical specification documents in the /spec/ directory.
Workflow to generate a comprehensive Product Requirements Document (PRD) detailing user stories, acceptance criteria, technical considerations, and metrics.
Systematic codebase exploration, architectural critique, and generation of Project Discovery Drafts for SDLC Phase 0.
Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.
Workflow for auditing, designing, and writing structured documentation based on the Diátaxis Framework (Tutorials, How-to, Reference, Explanation).
Generates formal, structured, and executable implementation plan documents based on specifications.
Elite UI/UX Design Lead & Frontend Architect. Generates distinctive, non-templated interfaces with opinionated aesthetics, deliberate typography, and exact UX copy. Triggers on UI design, frontend styling, or layout creation.
Phase 6: Coding & Execution. God-Tier Autonomous Engineer implementing code strictly based on approved /spec/ and /plan/.
Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code. Requires the Joyride extension.
Custom Instructions: Clean Architecture & Clean Code Expert
Prompt for creating Product Requirements Documents (PRDs) for new features, based on an Epic.
Create a new implementation plan file for new features, refactoring existing code or upgrading packages, design, architecture or infrastructure.
Create a README.md file for the project
Create a new specification file for the solution, optimized for Generative AI consumption.
Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.
Custom Instructions based on "Eloquent JavaScript, 4th Edition" (2024)
Custom Instructions: Senior Flutter & Dart Engineer
Laravel & PHP Development Instructions for GitHub Copilot
Documentation and content creation standards
Prompt: Prompt Refinement and Optimization
Custom Instructions: HTML5 & CSS3 Responsive Design Expert
Memory - Preferensi Pengguna
Custom Instructions: PHP 8+ & Laravel Architecture Expert
Custom Instructions: Node.js Backend & Architecture Expert
Menganalisis sesi terakhir untuk mencatat progress, mengambil pelajaran, dan menyimpannya ke instruksi memory proyek.
Contemplates repeated mistakes and success patterns, and transforms lessons learned into domain-organized Copilot instructions. Automatically discovers existing memory domains, intelligently categorizes new learnings, and creates domain-specific instruction files in the project workspace .github/instructions/ folder. You can make the categorization/domain designation specific by using `>domain-name` as the first thing in your request. Like so: `/remember >domain-name lesson content here`
Review and refactor code in your project according to defined instructions
Custom Instructions: The strict "Clean Architecture" & "Clean Code" Enforcer
Your mission is to be a precise, surgical assistant that respects existing code, follows user commands absolutely, and avoids any unsolicited changes.
Update an existing implementation plan file with new or update requirements to provide new features, refactoring existing code or upgrading packages, design, architecture or infrastructure.
Update an existing specification file for the solution, optimized for Generative AI consumption based on new requirements or updates to any existing code.
Build a promotion case: evidence log, impact narrative, manager alignment plan, submission-ready promo doc.
Create an AI Evals Pack (eval PRD, test set, rubric, judge plan, results + iteration loop). See also: building-with-llms (build), ai-product-strategy (strategy).
Apply behavioral science to product design: target behavior, intervention map, experiment plan.
Build an early sales team: hiring plan, role scorecards, interview loop, onboarding/ramp.
Create an AI Product Strategy Pack (thesis, use cases, system plan, eval plan, roadmap).
Build or refresh a team culture code, norms, and reinforcement plan.
Analyze user/customer feedback into a Feedback Analysis Pack (taxonomy, themes, recommendations). See also: conducting-user-interviews (collect new), designing-surveys (quantitative).
Create a Brand Storytelling Pack: brand narrative, founder story, channel scripts, Q&A bank.
Coach PMs: evidence-based assessment, growth bets, development plan, coaching cadence.
Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). See also: ai-evals (eval only), ai-product-strategy (strategy only).
Plan a career transition: push/pull map, target archetypes, option scorecard, pipeline + outreach, skills plan.
Build a Community Pack: strategy, platform plan, ambassador program, governance, metrics.
Plan, conduct, and synthesize user/customer interviews. See also: conducting-interviews (hiring), designing-surveys (quantitative).
Build a content marketing program: SEO topic map, editorial calendar, content briefs, measurement plan.
Produce a Competitive Analysis Pack (alternatives map, landscape, battlecards, monitoring plan).
Run structured behavioral HIRING interviews: plan, questions, scorecard, debrief. See also: conducting-user-interviews (product research).
Create a Delegation Pack (brief, decision rights, context handoff, check-in cadence, debrief).
Produce a Cross-Functional Collaboration Pack (charter, stakeholder map, roles contract, decision log).
Define or refresh a product vision: vision statement, narrative, pillars, strategic choices, rollout.
Build or evolve a design system: charter, token model, component inventory, governance plan.
Design and launch a product survey: brief, questionnaire, analysis plan, launch checklist. See also: conducting-user-interviews (qualitative).
Design growth loops (viral/referral/acquisition): loop map, scorecard, experiment backlog.
Run an internal dogfooding program: scenario map, routines, triage spec, ship/no-ship gate.
Stand up a Design Engineering practice: charter, prototype-to-production workflow, component delivery plan.
Build an Energy Management System: drivers/drains map, energy-aligned schedule, recovery routines.
Make evidence-based hiring decisions: scorecards, work samples, reference checks. See also: conducting-interviews (run interviews).
Produce an Engineering Culture Operating System Pack (culture code, DevEx backlog, workflow contract).
Create an Enterprise Deal Execution Pack (buying committee map, mutual action plan, ROI model).
Produce a Trade-off Evaluation Pack (options matrix, cost table, impact ranges, recommendation). See also: evaluating-new-technology (tech-specific).
Claude Skills — questions
Answers built from the skills we actually parsed.