#SkillRepo stars
- 2305Cmd PR Sculpt CodeOlshansk/agent-skillsReshape code for readability, naming, structure, TODOs, and reduced surface area across any language9
- 2306Cmd Review Chain HaltOlshansk/agent-skillsReview protocol code for chain halt risks, non-determinism, and onchain behavior bugs9
- 2307Completeborkweb/skillsDrive a coding goal with two or more slices to merge-ready through delegated builders, frozen gates and independent review. Use for '/complete', 'run the whole loop', 'take this to merge-ready' or a plan that needs a fleet of builders. One slice goes to offload instead.9
- 2308Offloadborkweb/skillsMake this session the ARCHITECT and hand implementation to a builder harness you can watch (codex, claude, opencode, pi, grok or a custom command), judged slice by slice on frozen gates and an independent review. Use when the user says "offload", "hand this to codex", "hand this to a builder", "architect mode", "have codex build this", or invokes /offload.9
- 2309Plan Devex Reviewborkweb/skillsReview a plan for a developer-facing surface (API, CLI, SDK, config or install) for setup friction, ergonomics, error messages and compatibility. Use for 'devex review', 'review the API design', 'is this CLI ergonomic' or 'review the onboarding for developers'.9
- 2310Plan Eng Reviewborkweb/skillsReview an implementation plan's architecture, contracts, failure paths, concurrency and test strategy before code is written. Use for 'eng review this plan', 'review the architecture', 'is this plan sound' or when do runs plan reviews.9
- 2311Angular Best Practiceshuytran1120/vietnam-agentic-skillsAngular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and rendering efficiency.9
- 2312API Design Principleshuytran1120/vietnam-agentic-skillsMaster REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers and stand the test of time.9
- 2313API Documentationhuytran1120/vietnam-agentic-skillsAPI documentation workflow for generating OpenAPI specs, creating developer guides, and maintaining comprehensive API documentation.9
- 2314API Patternshuytran1120/vietnam-agentic-skillsAPI design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.9
- 2315Apify Generate Output Schemahuytran1120/vietnam-agentic-skillsGenerate output schemas (dataset_schema.json, output_schema.json, key_value_store_schema.json) for an Apify Actor by analyzing its source code. Use when creating or updating Actor output schemas.9
- 2316Architect Reviewhuytran1120/vietnam-agentic-skillsMaster software architect specializing in modern architecture9
- 2317Architecturehuytran1120/vietnam-agentic-skillsArchitectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.9
- 2318Architecture Decision Recordshuytran1120/vietnam-agentic-skillsComprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.9
- 2319Architecture Patternshuytran1120/vietnam-agentic-skillsMaster proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design to build maintainable, testable, and scalable systems.9
- 2320Astrohuytran1120/vietnam-agentic-skillsBuild content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.9
- 2321Async Python Patternshuytran1120/vietnam-agentic-skillsComprehensive guidance for implementing asynchronous Python applications using asyncio, concurrent programming patterns, and async/await for building high-performance, non-blocking systems.9
- 2322Clueless BlindspotsADanMan/cluelessUse when the user asks what they are not seeing, what they forgot, what could go wrong, or what an expert would say about a plan, decision, document, code change, or setup they already have. Triggers: "what am I missing", "what don't I know", "poke holes in this", "what would an expert ask", "что я упускаю", "что я не вижу", or /clueless-blindspots. One-shot review; does not change the always-on level.3
- 2323Codex ReviewTabithaFanny/claude-skills-collection当用户说"codex审查"、"codex review"、"让codex审一下"、"用codex审查代码"时使用。 这个skill调用OpenAI Codex来进行代码审查。5
- 2324PunchcardMaksim-Burtsev/punchcardArchitecture-level design review of a code change: module boundaries, dependency direction, data model, error paths, cost of the next change — never naming, formatting, or anything a linter catches. Use when the user invokes /punchcard, says 'punchcard review', or asks for any design, architecture, or structural review of a diff, branch, merge request, or PR. Do not use for general correctness/bug review, style feedback, or whole-repo audits.2
- 2325Vibe CodingTabithaFanny/claude-skills-collectionVibe Coding 全流程技能:规划驱动的 AI 结对编程方法论。触发词:vibe、规划、plan、需求分析、架构设计、代码审查。5
- 2326What Could Breakstas4000/what-could-breakFind what a change could break outside its own diff, then prove the one fact that makes it safe by running real code instead of writing an essay. Use before any multi-file edit or an edit to a shared path (API payload, config, stored data, a client other apps read, a prompt or policy file), when asked 'what could this break' or 'blast radius of X', for a small diff you do not trust, or when a task asserts something about existing code ('X already handles Y', 'just make X public') before you design against that assertion.2
- 2327Codebase Explorercellrishi-code/claude-skills-atlasUse when entering an unfamiliar codebase and you need to understand architecture, entry points, dependencies, conventions, and data flow before editing.5
- 2328Codebase Understandingcellrishi-code/claude-skills-atlasBuild a reliable mental model of an unfamiliar repository before making changes. Use when entering a new codebase, investigating architecture, or when the user asks where a feature belongs.5
- 2329Debug Systematicallycellrishi-code/claude-skills-atlasDiagnose software failures systematically instead of guessing. Use for bugs, failing tests, unexpected output, crashes, regressions, and inconsistent behavior.5
- 2330Implementation Plannercellrishi-code/claude-skills-atlasUse when a coding task is large enough to require repository inspection, a plan, affected files, risks, and verification before implementation.5
- 2331Implementation Reviewcellrishi-code/claude-skills-atlasReview an implementation against its requirements, repository conventions, correctness risks, tests, and maintainability. Use before opening a pull request or when reviewing completed work.5
- 2332Adrtarunccet/pm-skillsDocument architecture and product decisions using the Nygard ADR format — captures context, alternatives considered, and consequences so the team never asks 'why did we do it this way?' again. Use when making architecture decisions, choosing between technical approaches, selecting vendors, or any decision that will be hard to reverse.9
- 2333Cf Buildecorkran/context-forgeBuild and load a Context Forge context prompt. Use when the user asks to build, load, or refresh Context Forge context, optionally for a particular phase or slice.5
- 2334Cf Checkecorkran/context-forgeRun Context Forge consistency checks on project artifacts. Use when the user asks to check, fix, or audit cf project document consistency.5
- 2335Cf Getecorkran/context-forgeShow all fields for the active Context Forge project. Use when the user asks to see the cf project's fields or configuration.5
- 2336Cf Nextecorkran/context-forgeShow the recommended next action for the current Context Forge project. Use when the user asks what to do next in the cf workflow.5
- 2337Cf Onboardecorkran/context-forgeGuide a user through Context Forge project setup and into their first phase of work. Use when the user wants to set up or onboard a project with Context Forge.5
- 2338Cf Projectecorkran/context-forgeManage Context Forge projects (list, get, set, rm, schema). Use when the user asks to list cf projects or manage project registration.5
- 2339Cf Setecorkran/context-forgeSet a field on the active Context Forge project (e.g. phase, slice). Use when the user asks to set or change a cf project field.5
- 2340Cf Statusecorkran/context-forgeShow Context Forge project status (phase, slice, task progress). Use when the user asks for cf status or where the project stands.5
- 2341Code Review for Pmstarunccet/pm-skillsReview AI-generated code from a PM perspective: spec compliance, security red flags, data model soundness, UX issues in frontend code, and error handling against product requirements.9
- 2342Debug with AItarunccet/pm-skillsGuide PMs through debugging AI-generated code: how to read error messages, form effective debugging prompts, isolate issues, and decide when to fix forward vs start over.9
- 2343Fema Real Estateanalyticsariel/tech-in-real-estateReference disaster declarations, NFIP flood insurance claims, Individual Assistance grants to households, and Public Assistance federal obligations from FEMA (Federal Emergency Management Agency, OpenFEMA v2) for real estate investment decisions. Use this skill whenever a user asks about FEMA data, OpenFEMA, disaster declarations, federally declared disasters, hurricane declarations, NFIP, National Flood Insurance Program, flood claims, flood insurance, NFIP payouts, NFIP claim severity, building damage assessed, IHP, Individuals and Households Program, disaster assistance, IHP grants, owner I5
- 2344Learn Vibe Codingtarunccet/pm-skillsInteractive guide for PMs getting started with vibe coding: choosing and installing the right AI coding tools, writing your first spec, planning a build, and shipping a prototype.9
- 2345Prioritizationtarunccet/pm-skillsUnified prioritization skill that adapts to what you're prioritizing: features (ICE/RICE/Opportunity Score), assumptions (Impact × Risk matrix + experiment design), backlog items (strategic alignment + effort), or general trade-offs. Includes reference to all 9 prioritization frameworks. Use when prioritizing a backlog, triaging assumptions, ranking ideas, or choosing between competing initiatives.9
- 2346Pywayne Adb Logcat Readerwangyendt/wayne-skillsAndroid device logcat reader for real-time log monitoring. Use when working with pywayne.adb.logcat_reader module to read Android device logs via adb logcat command, supporting both C++ backend (faster) and Python backend (subprocess) with generator-style output for streaming logs.9
- 2347Pywayne Aliyun Osswangyendt/wayne-skillsAliyun OSS (Object Storage Service) file management toolkit for Python. Use when working with Aliyun OSS to upload files, download files, list objects, delete files, manage directories, read file contents, check file existence, get file metadata, copy and move objects. Supports both authenticated (with API key/secret for write operations) and anonymous access (read-only).9
- 2348Technical Analysttarunccet/pm-skillsTechnical translator for PMs — helps understand systems, codebases, APIs, and technical concepts in PM-friendly terms without oversimplifying. Use when trying to understand a technical system, investigating code for product decisions, preparing for architecture discussions, or translating engineering proposals into product implications.9
- 2349Technical Decision Guidetarunccet/pm-skillsHelp PMs make technical architecture decisions without deep engineering background — database selection, hosting, auth patterns, monolith vs microservice, API design. Written in PM-friendly language with decision trees.9
- 2350Vibe Coding Spectarunccet/pm-skillsWrite a natural-language specification optimized for feeding to AI coding assistants. Covers problem statement, user flows, data model, API contracts, UI descriptions, tech stack, and constraints.9
- 2351Agy Delegatehuytran1120/vietnam-agentic-skillsDelegate coding tasks to the Google Antigravity CLI (`agy`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.9
- 2352Andrej Karpathyhuytran1120/vietnam-agentic-skillsBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.9