Moving this week

Ranked by stars gained over seven days, not by the total. An absolute count tells you what was popular in 2024; a delta tells you what people are picking up now, and it cannot be inherited from a parent repository.

Window This week Today
#ModTypeThis weekStarsScanTokensRating
701 compose-graphicsJwuthri/Tracely-aiAdvanced Compose visuals - Material 3 Expressive motion physics, AGSL shaders (Android 13+), Canvas/DrawScope generative, graphicsLayer effects. Skill ▲ +2 1.2k A 36
702 docxmateaix/mateclawUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). For CREATING new documents (report, memo, letter, résumé, contract from scratch), call the built-in tool renderDocx instead — it renders Markdown to .docx in milliseconds without forking Node.js. This skill… Skill ▲ +2 1.1k A 152
703 PostToolUseareal-project/AReaLRuns after a tool call finishes for Write and Edit tool calls, executing check-expert-update.sh. From areal-project/AReaL. Hook ▲ +2 5.7k A
704 Tracely-ai CLAUDE.mdJwuthri/Tracely-aiClaude Code instructions for Jwuthri/Tracely-ai, covering claude.md, commands, architecture, hard rules and gotchas. Instructions file ▲ +2 1.2k A 3,206
705 arcade-mcp CLAUDE.mdArcadeAI/arcade-mcpClaude Code instructions for ArcadeAI/arcade-mcp, covering claude.md, what this is, commands, library dependency graph and versioning rules. Instructions file ▲ +2 1.0k A 4,698
706 build-error-adapterArcadeAI/arcade-mcpBuild new Arcade error adapters from scratch using public Arcade TDK patterns. Use when adding provider integrations, mapping SDK exceptions, or extending HTTP/GraphQL/auth adapter behavior. Skill ▲ +2 1.0k A 39
707 bernstein AGENTS.mdsipyourdrink-ltd/bernsteinAGENTS.md instructions for sipyourdrink-ltd/bernstein, covering bernstein - agents.md, module map, directory context files, build & test and setup. Instructions file ▲ +2 1.0k A 1,131
708 debateagent-sh/agentsysStructured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 'stress test idea', 'devil advocate'. Skill ▲ +2 980 A 41
709 workergmickel/flow-nextTask implementation worker. Spawned by flow-next-work to implement a single task with fresh context. Do not invoke directly - use /flow-next:work instead. Agent ▲ +2 692 A 34
710 flow-next-interviewgmickel/flow-nextIn-depth Q&A to refine a spec, task, or spec file before building. Use when asked to flesh out, refine, or interrogate requirements. Skill ▲ +2 692 A 36
711 bernstein copilot-instructions.mdsipyourdrink-ltd/bernsteinCopilot instructions for sipyourdrink-ltd/bernstein, covering copilot instructions, architecture, key constraints, before committing and git rules. Instructions file ▲ +2 1.0k A 740
712 bernstein-runsipyourdrink-ltd/bernsteinRun a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a finished run against its… Skill ▲ +2 1.0k A 75
713 discover-tasksagent-sh/agentsysUse when user asks to "discover tasks", "find next task", "prioritize issues", "what should I work on", or "list open issues". Discovers and ranks tasks from GitHub, GitLab, local files, and custom sources. Skill ▲ +2 980 A 55
714 agentsys AGENTS.mdagent-sh/agentsysAGENTS.md instructions for agent-sh/agentsys, covering project memory: agentsys, critical rules (priority order), architecture, commands and core workflow. Instructions file ▲ +2 980 A 3,115
715 flow-next CLAUDE.mdgmickel/flow-nextClaude Code instructions for gmickel/flow-next, covering claude code project guide, stack and tooling, when to use a skill (the default), when to use deterministic flowctl python and the common pattern: skill + thin flowctl plumbing. Instructions file ▲ +2 692 A 7,936
716 bernstein-plansipyourdrink-ltd/bernsteinCreate and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working. Skill ▲ +2 1.0k A 51
717 plan-syncgmickel/flow-nextSynchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly. Agent ▲ +2 692 A 27
718 flow-next-auditgmickel/flow-nextAudit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate. Skill ▲ +2 692 A 46
719 Ghost-Agent CLAUDE.mdCryptoDmitry/Ghost-AgentClaude Code instructions for CryptoDmitry/Ghost-Agent, covering claude.md, repository overview, core architecture, main scripts and library components (lib/). Instructions file ▲ +2 747 A 6,216
720 agentsys CLAUDE.mdagent-sh/agentsysClaude Code instructions for agent-sh/agentsys, covering agentsys, critical rules, model selection, core priorities and dev commands. Instructions file ▲ +2 980 A 360
721 toolset-designcontainers/kubernetes-mcp-serverDesign and validate new MCP toolsets, tools, and tool changes. Use when planning a new toolset, adding tools to an existing toolset, reviewing a toolset PR, or deciding whether a new tool is warranted. Covers the full lifecycle: eval-first validation, tool design methodology, consolidation patterns, and review… Skill ▲ +2 2.0k B 69
722 premiere-pro-mcphetpatel-11/Adobe_Premiere_Pro_MCPInstall, verify, troubleshoot, and operate the Adobe Premiere Pro MCP server. Use when a user wants an agent to set up Premiere MCP, connect Claude Code/Codex/Claude Desktop, control Premiere, import media, build sequences, edit timelines, apply effects, or diagnose bridge issues. Skill ▲ +2 511 A 64
723 atmoscloudposse/atmosAgent settings declaring 1 hook event (PostToolUse) and 31 allowed tools. Settings file ▲ +2 1.4k A
724 mongodb-mcp-server copilot-instructions.mdmongodb-js/mongodb-mcp-serverCopilot instructions for mongodb-js/mongodb-mcp-server, covering project overview, folder structure, libraries and frameworks, coding standards and architectural guidelines and best practices. Instructions file ▲ +2 1.1k A 1,576
725 atmoscloudposse/atmosAtmos skills for AI coding assistants: Terraform/OpenTofu/Helmfile/Packer/Ansible orchestration, stacks, remote imports, components, immutable vendoring and Component Updater PRs, containers, emulators, Native CI, SBOM provenance, Atmos Pro, Auth, GitOps, secrets, cache, hooks, shared steps, workflows, version tracks. Plugin ▲ +2 1.4k A
726 kubernetes-mcp-servercontainers/kubernetes-mcp-serverA Model Context Protocol (MCP) server for Kubernetes and OpenShift. Runs locally from the kubernetes-mcp-server npm package. MCP server ▲ +2 2.0k A
727 agentsysagent-sh/agentsys26 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, unified static analysis, durable memory, negative behavior memory, skill and system prompt curation, perf investigations, topic research, agent… Plugin ▲ +2 980 A
728 cloudpossecloudposse/atmosOfficial Atmos plugins and skills for Claude Code. Plugin ▲ +2 1.4k A
729 mongodb-mcp-servermongodb-js/mongodb-mcp-serverMongoDB Model Context Protocol Server. Runs locally from the mongodb-mcp-server npm package. Needs 42 environment variables to run. MCP server ▲ +2 1.1k A
730 bernstein-contextsipyourdrink-ltd/bernsteinBernstein orchestrator context - always active when working in a Bernstein-managed project. Cursor rule ▲ +2 1.0k A 399
731 directory-contextsipyourdrink-ltd/bernsteinPer-directory context files for agents working inside a subtree. Each covers: what the directory is for, key files, invariants, and how to test that subtree. Cursor rule ▲ +2 1.0k A 0
732 orchestratorsipyourdrink-ltd/bernsteinDecomposes goals into parallel tasks, assigns them to CLI coding agents, verifies output, and merges results. Use when a task is too large for a single agent. Agent ▲ +2 1.0k A 38
733 brightdata-mcpbrightdata/brightdata-mcpBright Data's Web MCP server enabling AI agents to search, extract & navigate the web. Runs locally from the @brightdata/mcp npm package. Needs 9 environment variables to run. MCP server ▲ +2 2.6k A
734 versioningArcadeAI/arcade-mcpGuidelines for library versioning. Cursor rule ▲ +2 1.0k A 206
735 runsipyourdrink-ltd/bernsteinStart a Bernstein orchestration run with a goal. Command ▲ +2 1.0k A 9
736 Arkana CLAUDE.mdJameZUK/ArkanaClaude Code instructions for JameZUK/Arkana, covering arkana development guide, what is arkana?, project structure, running tests and unit tests (no server needed, 2 seconds). Instructions file ▲ +2 211 A 9,744
737 agentsysagent-sh/agentsysProfessional-grade slash commands for Claude Code with cross-platform support. Plugin ▲ +2 980 A
738 memoraagentic-box/memoraUse when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful. Skill ▲ +2 709 A 33
739 agentsysagent-sh/agentsysAgent settings declaring 1 hook event (PostToolUse). Settings file ▲ +2 980 A
740 flow-nextgmickel/flow-nextPlugin marketplace listing 1 plugin: flow-next. Plugin ▲ +2 692 A
741 PostToolUseagent-sh/agentsysRuns after a tool call finishes for Bash tool calls, executing enforce-script-failure-report.sh. From agent-sh/agentsys. Hook ▲ +2 980 A
742 bernsteinsipyourdrink-ltd/bernsteinMCP server "bernstein" as configured in sipyourdrink-ltd/bernstein. Launched with bernstein mcp. MCP server ▲ +2 1.0k A
743 flow-nextgmickel/flow-nextZero-dependency, spec-driven agentic SDLC: durable specs, context-fit plans, re-anchored workers, adversarial cross-model review, and receipts. Includes 20 subagents, 29 commands, 33 skills. Plugin ▲ +2 692 A
744 radare2-mcp AGENTS.mdradareorg/radare2-mcpAGENTS.md instructions for radareorg/radare2-mcp, covering agentic coding guidelines for r2mcp, build & test, code style, memory and json (pj api). Instructions file ▲ +2 302 A 1,097
745 arkana-code-reviewerJameZUK/ArkanaUse this agent for code reviews and legacy/architectural audits of the Arkana MCP server. This agent enforces strict quote-before-claim discipline — every finding must include a verbatim code snippet from a verified file:line, and the agent will reject any internal hypothesis it cannot back with quoted source. Use it… Agent ▲ +2 211 A 143
746 memoraagentic-box/memoraPersistent semantic memory for Claude Code with knowledge graph visualization. Plugin ▲ +2 709 A
747 kinocutKyaniteLabs/kinocutUse Kinocut for guarded video editing, source-backed planning, FFmpeg operations, media analysis, subtitles, audio workflows, Hyperframes rendering, repurposing packages, and release checkpoints through an MCP server, Python client, or CLI. Trigger when an agent needs to inspect, plan, edit, render, validate, or… Skill ▲ +2 132 A 74
748 humanizer-ruVladimir-Human/humanizer-ruA Russian-language editing tool that checks text for signs it was generated by a machine and can rewrite it in a more natural style when asked. Skill ▲ +2 120 A 164
749 memoraagentic-box/memoraPersistent semantic memory for Claude Code — auto-injects relevant context at session start, captures git commits, test results, and research via hooks, and provides 30+ MCP tools for memory management. Plugin ▲ +2 709 A
750 settingsgmickel/flow-nextAgent settings declaring 1 hook event (PostToolUse). Settings file ▲ +2 692 A
751 PostToolUsegmickel/flow-nextRuns after a tool call finishes for Edit and Write tool calls, running bun run lint. From gmickel/flow-next. Hook ▲ +2 692 A
752 skills AGENTS.mdvuejs-ai/skillsAGENTS.md instructions for vuejs-ai/skills, covering vue skills development guide, branch strategy, development workflow, skill scopes and common pitfalls & best practices. Instructions file ▲ +2 2.8k A 3,082
753 edit-premiere-projecthetpatel-11/Adobe_Premiere_Pro_MCPInspect, edit, verify, and export an open Adobe Premiere Pro project through the local Premiere MCP Bridge. Skill ▲ +2 511 A 26
754 MacOS-MCP CLAUDE.mdCursorTouch/MacOS-MCPClaude Code instructions for CursorTouch/MacOS-MCP, covering macos-mcp: project documentation for claude, project overview, tech stack, architecture and entry point (src/macosmcp/main.py). Instructions file ▲ +2 165 A 1,096
755 memora CLAUDE.mdagentic-box/memoraClaude Code instructions for agentic-box/memora, covering memora and memory. Instructions file ▲ +2 709 A 63
756 memoraagentic-box/memoraMCP server "memora" as configured in agentic-box/memora. Launched with memora-server. Needs 3 environment variables to run. MCP server ▲ +2 709 A
757 adobe-premiere-pro-mcphetpatel-11/Adobe_Premiere_Pro_MCPPlugin marketplace listing 1 plugin: premiere-pro-mcp. Plugin ▲ +2 511 A
758 premiere-pro-mcphetpatel-11/Adobe_Premiere_Pro_MCPInspect, edit, verify, and export local Adobe Premiere Pro projects through the MCP Bridge. Plugin ▲ +2 511 A
759 kinocut AGENTS.mdKyaniteLabs/kinocutAGENTS.md instructions for KyaniteLabs/kinocut, covering kinocut - project rules, public agent skill, before writing any code, ffmpeg security and error handling. Instructions file ▲ +2 132 A 1,121
760 kinocut-repurposeKyaniteLabs/kinocutUse the current Kinocut tools to turn one local video path into a short platform-ready clip package with manifests, review artifacts, and human approval gates. Skill ▲ +2 132 A 37
761 humanizer-ru AGENTS.mdVladimir-Human/humanizer-ruRepository instructions for humanizer-ru, a tool that removes signs of machine-generated writing from Russian text. They document mirrored files, rules that keep continuous integration checks passing, and validation steps. Instructions file ▲ +2 120 A 1,795
762 sigmasanyuan0704/sanyuan-skillsPersonalized 1-on-1 AI tutor using Bloom's 2-Sigma mastery learning. Guides users through any topic with Socratic questioning, adaptive pacing, and rich visual output (HTML dashboards, Excalidraw concept maps, generated images). Use when user wants to learn something, study a topic, understand a concept, requests… Skill ▲ +2 3.9k A 124
763 active-memory-reminderArchive228/loopkitBefore compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop. Skill ▲ +2 753 A 44
764 feature-list-jsonArchive228/loopkitEnumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order. The ledger fresh-context sessions read to know what's done, what's next, and what they're forbidden to touch. Skill ▲ +2 753 A 50
765 polishArchive228/loopkitRun the batch quality pass over the current diff — simplify → reduce-nesting → kill-dead-code → a11y-pass → loading-empty-error-states → readme-audit. Command ▲ +2 753 A 37
766 book-studysanyuan0704/sanyuan-skillsReading coach: guides users through books systematically with knowledge compilation, mastery testing, spaced repetition, and knowledge querying. Use when user says 'read this book with me', 'book study', 'start studying X', 'reading plan', 'ingest this chapter', 'review what I read', 'quiz me on the book', 'what did… Skill ▲ +2 3.9k A 121
767 create-adaptable-composablevuejs-ai/skillsCreate a library-grade Vue composable that accepts maybe-reactive inputs (MaybeRef / MaybeRefOrGetter) so callers can pass a plain value, ref, or getter. Normalize inputs with toValue()/toRef() inside reactive effects (watch/watchEffect) to keep behavior predictable and reactive. Use this skill when user asks for… Skill ▲ +2 2.8k A 80
768 verifyArchive228/loopkitRun adversarial verification on the current diff before claiming done. Loads the loopkit adversarial-verify skill and dispatches the verifier subagent. Command ▲ +2 753 A 29
769 premiere-prohetpatel-11/Adobe_Premiere_Pro_MCPMCP Bridge for Adobe Premiere Pro with 283 tools for AI-driven video editing. Runs locally from the adobe-premiere-pro-mcp npm package. MCP server ▲ +2 511 A
770 toolporttsouth89/toolportUse when the user asks for any external action or data: email, payments, deployments, databases, repos, issues, files, web search, messaging, or any connected service. Toolport is the front door to every MCP server on this machine; search it before concluding a capability is unavailable. Skill ▲ +2 200 A 62
771 arkana-analyzeJameZUK/ArkanaBinary analysis skill for Arkana. Handles malware triage, reverse engineering, PE/ELF/Mach-O analysis, shellcode emulation, firmware inspection, vulnerability auditing, C2 config extraction, unpacking, deobfuscation, and threat intelligence. Triggers on: binary, malware, PE, ELF, Mach-O, shellcode, firmware, analyze… Skill ▲ +2 211 A 158
772 Context-Engineering CLAUDE.mdjasontang-ai/Context-EngineeringClaude Code instructions for jasontang-ai/Context-Engineering, covering claude.md - cognitive operating system, 1. core meta-cognitive framework, context schemas, code understanding schema and troubleshooting schema. Instructions file ▲ +2 9.2k A 5,062
773 Context-Engineering GEMINI.mdjasontang-ai/Context-EngineeringGemini CLI instructions for jasontang-ai/Context-Engineering, covering gemini.md - cognitive operating system, core reasoning frameworks, systematic problem solving, code analysis & generation and technical research. Instructions file ▲ +2 9.2k A 4,417
774 mcp-ui copilot-instructions.mdMCP-UI-Org/mcp-uiCopilot instructions for MCP-UI-Org/mcp-ui, covering mcp-ui development instructions, working effectively, bootstrap and build (critical - set 60+ minute timeouts), testing (critical - set 30+ minute timeouts) and code quality (always run before committing). Instructions file ▲ +2 5.1k B 1,709
775 arkana-learnJameZUK/ArkanaInteractive reverse engineering tutor using Arkana. Teaches binary analysis concepts from beginner to expert, adapting to the learner's level. Guides users through hands-on analysis or structured lessons using Arkana's 308 tools as the teaching platform. Triggers on: teach, learn, tutorial, lesson, explain, guide, how… Skill ▲ +2 211 A 118
776 vue-debug-guidesvuejs-ai/skillsVue 3 debugging and error handling for runtime errors, warnings, async failures, and SSR/hydration issues. Use when diagnosing or fixing Vue issues. Skill ▲ +2 2.8k A 36
777 READMEjasontang-ai/Context-EngineeringThis directory contains a growing library of modular, customizable, and extendable agents and harnesses embedded as slash commands, forming an Agentic Operating System (AgenticOS) designed for enhancing the capabilities of Claude Code and other frontier systems, such as OpenCode, Amp, Kiro, Codex, Gemini CLI, and… Command ▲ +2 9.2k A 0
778 alignmentjasontang-ai/Context-EngineeringCommand "alignment" from jasontang-ai/Context-Engineering, covering /alignment.agent system prompt, slash command invocation, context clarification, risk mapping and failure/adversarial simulation. Command ▲ +2 9.2k A 0
779 opencode-primer AGENTS.mdwesammustafa/opencode-primerAGENTS.md instructions for wesammustafa/opencode-primer, covering agents.md, what this repo is, repo layout, editing rules and always. Instructions file ▲ +2 384 A 1,646
780 toolporttsouth89/toolportEvery tool. One port. Connects this agent to your local Toolport gateway: every MCP server you set up in Toolport, exposed through a handful of compact meta-tools instead of hundreds of tool definitions (90% fewer tokens, measured). Plugin ▲ +2 200 A
781 reviewJameZUK/ArkanaRun the rigorous arkana-code-reviewer agent on uncommitted changes (or a specified scope). Command ▲ +2 211 A 22
782 loopkit AGENTS.mdArchive228/loopkitAGENTS.md instructions for Archive228/loopkit, covering agents.md — loopkit loop contract, the three-step loop, single-feature rule, clean-state contract (end of every session) and skills vs rules. Instructions file ▲ +2 753 A 1,078
783 kubernetes-mcp-server AGENTS.mdcontainers/kubernetes-mcp-serverAGENTS.md instructions for containers/kubernetes-mcp-server, covering project agents.md for kubernetes mcp server, project structure, feature development, logging and adding new mcp tools. Instructions file ▲ +2 2.0k C 2,111
784 security-auditorwesammustafa/opencode-primerSecurity-focused reviewer — audits code for vulnerabilities (OWASP Top 10, secret leaks, auth/authz issues) and reports findings without modifying files. Agent ▲ +2 384 A 30
785 code-reviewerwesammustafa/opencode-primerSenior code reviewer — reads diffs and surfaces bugs, security issues, and maintainability problems without modifying files. Agent ▲ +2 384 A 22
786 git-releasewesammustafa/opencode-primerDraft release notes from merged PRs, propose a semver bump, and emit a copy-pasteable gh release create command. Use when preparing a tagged GitHub release. Skill ▲ +2 384 A 40
787 SunoMCP CLAUDE.mdAceDataCloud/SunoMCPClaude Code instructions for AceDataCloud/SunoMCP, covering sunomcp, project structure, sync from docs and development. Instructions file ▲ +2 47 A 458
788 vue-skillsvuejs-ai/skillsA collection of skills for Vue.js development. Plugin ▲ +2 2.8k A
789 optimizewesammustafa/opencode-primerSuggest concrete performance improvements for the given file or directory. Command ▲ +2 384 A 10
790 toolporttsouth89/toolportMCP server "toolport" as configured in tsouth89/toolport. Runs ${CLAUDE_PLUGIN_ROOT}/bin/launch-gateway.mjs with node. MCP server ▲ +2 200 A
791 SunoMCP copilot-instructions.mdAceDataCloud/SunoMCPCopilot instructions for AceDataCloud/SunoMCP, covering copilot instructions for sunomcp, sync from docs, project structure and development. Instructions file ▲ +2 47 A 425
792 prwesammustafa/opencode-primerOpen a pull request from the current branch with a generated title and summary. Command ▲ +2 384 A 14
793 loopkit-marketplaceArchive228/loopkitStandalone marketplace for loopkit — 41 skills + minimal harness. Plugin ▲ +2 753 A
794 loopkitArchive228/loopkit33 battle-tested skills + a minimal harness (CLAUDE.md, verifier subagent, format-on-write hook, MEMORY index, loop runner) for Claude Code, Cursor, Codex, and Gemini CLI. Plugin ▲ +2 753 A
795 arkanaJameZUK/ArkanaMCP server "arkana" as configured in JameZUK/Arkana. Launched with ./run.sh --stdio. Needs 1 environment variable to run. MCP server ▲ +2 211 A
796 humanizer-ruVladimir-Human/humanizer-ruA Russian-language writing tool that detects signs of machine-generated text and, when asked, rewrites Russian text in a more natural style. Plugin ▲ +2 120 A
797 auditVladimir-Human/humanizer-ruA command that checks Russian text for signs of machine generation without rewriting it. Command ▲ +2 120 A 12
798 humanizeVladimir-Human/humanizer-ruA command that rewrites Russian text to sound more natural and less machine-generated while keeping its meaning. It can work from text supplied directly or from a file path. Command ▲ +2 120 A 25
799 verifierArchive228/loopkitReviews a diff against the goal spec assuming the code is broken. Invoke after every code change. Agent ▲ +2 753 A 22
800 kinocut CLAUDE.mdKyaniteLabs/kinocutClaude Code instructions for KyaniteLabs/kinocut, covering claude.md instructions for kyanitelabs/kinocut and empower orchestrator law. Instructions file ▲ +2 132 A 79

Two mods per repository at most, so one viral repository cannot occupy the chart. Star history starts when a repository is first crawled, so this list becomes meaningful after a week of runs rather than immediately.