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
101 anvilcline/clineSurgical implementation agent — makes focused changes, verifies correctness, and reports precise diffs. Agent ▲ +79 67k A 21
102 inquisitorcline/clineAdversarial review agent — finds bugs, challenges design decisions, and stress-tests assumptions. Agent ▲ +79 67k A 22
103 SessionStartcline/clineRuns when a session starts, executing claude-code-for-web-setup.sh. From cline/cline. Hook ▲ +79 67k A
104 clinecline/clineAgent settings declaring 1 hook event (SessionStart). Settings file ▲ +79 67k A
105 file-analyzerEgonex-AI/Understand-AnythingAnalyzes batches of source files to produce knowledge graph nodes and edges. Extracts file structure, functions, classes, and relationships using a two-phase approach: structural extraction script followed by LLM semantic analysis. Agent ▲ +76 81k A 47
106 architecture-analyzerEgonex-AI/Understand-AnythingAnalyzes a codebase's file structure, summaries, and import relationships to identify logical architectural layers and assign every file to exactly one layer. Agent ▲ +76 81k A 33
107 understand-domainEgonex-AI/Understand-AnythingExtract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing /understand knowledge graph. Skill ▲ +76 81k A 38
108 understand-dashboardEgonex-AI/Understand-AnythingLaunch the interactive web dashboard to visualize a codebase's knowledge graph. Skill ▲ +76 81k A 17
109 SessionStartEgonex-AI/Understand-AnythingRuns when a session starts, running an inline shell check. From Egonex-AI/Understand-Anything. Hook ▲ +76 81k A
110 understand-anythingEgonex-AI/Understand-AnythingAI-powered codebase understanding — analyze, visualize, and explain any project. Plugin ▲ +76 81k A
111 understand-anythingEgonex-AI/Understand-AnythingPlugin marketplace listing 1 plugin: understand-anything. Plugin ▲ +76 81k A
112 PostToolUseEgonex-AI/Understand-AnythingRuns after a tool call finishes for Bash tool calls, executing post-tool-use-auto-update.mjs via node. From Egonex-AI/Understand-Anything. Hook ▲ +76 81k A
113 Understand-Anything CLAUDE.mdEgonex-AI/Understand-AnythingClaude Code instructions for Egonex-AI/Understand-Anything, covering understand anything, project overview, prerequisites, architecture and dashboard. Instructions file ▲ +76 81k C 1,645
114 shadcnshadcn-ui/uiManages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json… Skill ▲ +74 123k A 94
115 migrate-radix-to-baseshadcn-ui/uiMigrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects. Skill ▲ +74 123k A 61
116 workflow-claude-settingsshanraisshan/claude-code-best-practiceTrack Claude Code settings report changes and find what needs updating. Command ▲ +74 65k A 11
117 development-workflowsshanraisshan/claude-code-best-practiceUpdate the DEVELOPMENT WORKFLOWS table by researching all 11 workflow repos in parallel. Command ▲ +74 65k A 17
118 vibe-to-agentic-frameworkshanraisshan/claude-code-best-practiceThe conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc. Skill ▲ +74 65k A 44
119 requirement-parsershanraisshan/claude-code-best-practiceAnalyzes feature request descriptions and extracts structured requirements, goals, constraints, and metadata for downstream planning agents. Agent ▲ +74 65k A 25
120 development-workflows-research-agentshanraisshan/claude-code-best-practiceResearch agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositories. Agent ▲ +74 65k A 33
121 time-fetchershanraisshan/claude-code-best-practiceInstructions for fetching current Dubai time via bash command. Skill ▲ +74 65k A 13
122 claude-code-best-practiceshanraisshan/claude-code-best-practiceAgent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools. Settings file ▲ +74 65k A
123 registry-bases-parityshadcn-ui/uiKeep registry base and radix trees in sync when editing shared UI. Cursor rule ▲ +74 123k A 0
124 claude-code-best-practice CLAUDE.mdshanraisshan/claude-code-best-practiceClaude Code instructions for shanraisshan/claude-code-best-practice, covering claude.md, repository overview, key components, weather system (example workflow) and skill definition structure. Instructions file ▲ +74 65k B 1,830
125 FileChangedshanraisshan/claude-code-best-practiceRuns on the FileChanged event for .envrc, .env and .env.local tool calls, executing hooks.py via python3. From shanraisshan/claude-code-best-practice. Hook ▲ +74 65k A
126 PreToolUseshanraisshan/claude-code-best-practiceRuns before the agent uses a tool, executing hooks.py via python3. From shanraisshan/claude-code-best-practice. Hook ▲ +74 65k A
127 context7shanraisshan/claude-code-best-practiceGives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package. MCP server ▲ +74 65k A
128 deepwikishanraisshan/claude-code-best-practiceLets the agent read DeepWiki's AI-generated documentation of any public GitHub repository and ask questions about a codebase. Runs locally from the deepwiki-mcp npm package. MCP server ▲ +74 65k A
129 mcpc-testerapify/apify-mcp-serverProbe the local Apify MCP server with mcpc during development. Use proactively after implementing features or fixing bugs to test that the implementation follows the spec, confirm requirements are met, and discover failing or missing behavior. Agent ▲ +71 5.5k A 47
130 digapify/apify-mcp-serverExplore, analyze, plan, or spec features for the Apify MCP server. Adapts to what the user asks — from quick code exploration to full GitHub issue specs. Use when the user asks to explore code, understand behavior, plan a change, design a feature, or create an issue spec. Skill ▲ +71 5.5k A 64
131 apify-mcp-server AGENTS.mdapify/apify-mcp-serverAGENTS.md instructions for apify/apify-mcp-server, covering apify mcp server, communication style — mandatory, scope discipline, git: branch names, commits, pr titles and verification (mandatory). Instructions file ▲ +71 5.5k A 2,347
132 stdio-fullapify/apify-mcp-serverMCP server "stdio-full" as configured in apify/apify-mcp-server. Runs dist/stdio.js with node. Needs 2 environment variables to run. MCP server ▲ +71 5.5k A
133 stdioapify/apify-mcp-serverMCP server "stdio" as configured in apify/apify-mcp-server. Runs dist/stdio.js with node. Needs 2 environment variables to run. MCP server ▲ +71 5.5k A
134 bug-triageapify/apify-mcp-serverTriage open GitHub bug issues for Apify MCP server. Fetches issues, analyzes root causes, drafts developer-to-developer responses, and posts after user approval. Use when handling user bug reports, responding to issues, or cleaning up stale bugs. Skill ▲ +71 5.5k C 56
135 grafttrailhq/GraftThis repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files. Skill ▲ +70 5.2k A 56
136 Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion. Agent ▲ +62 39k A 11
137 AEM Front-End Specialistgithub/awesome-copilotExpert assistant for developing AEM components using HTL, Tailwind CSS, and Figma-to-code workflows with design system integration. Agent ▲ +62 39k A 31
138 awesome-copilot AGENTS.mdgithub/awesome-copilotAGENTS.md instructions for github/awesome-copilot, covering agents.md, project overview, repository structure, setup commands and install dependencies. Instructions file ▲ +62 39k A 4,119
139 create-canvas-extensiongithub/awesome-copilotCreate or register a canvas extension in the awesome-copilot repository. Use when asked to scaffold a new canvas extension, create its plugin.json, add a reusable extension to one or more plugins, or migrate extension metadata. Extensions are reusable source under extensions/; shippable plugin manifests belong under… Skill ▲ +62 39k A 66
140 awesome-copilot copilot-instructions.mdgithub/awesome-copilotCopilot instructions for github/awesome-copilot, covering readme updates, prompt file guide, instruction file guide, agent file guide and agent skills guide. Instructions file ▲ +62 39k A 829
141 load-github-action-threadastral-sh/uvDownload retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request. Skill ▲ +61 89k A 62
142 uv AGENTS.mdastral-sh/uvAGENTS.md instructions for astral-sh/uv, a project described as: An extremely fast Python package and project manager, written in Rust. Instructions file ▲ +61 89k A 445
143 uvastral-sh/uvAgent settings declaring 2 hook events (SessionStart, PostToolUse). Settings file ▲ +61 89k A
144 PostToolUseastral-sh/uvRuns after a tool call finishes for Edit, Write and MultiEdit tool calls, executing post-edit-format.py via uv with --frozen. From astral-sh/uv. Hook ▲ +61 89k A
145 SessionStartastral-sh/uvRuns when a session starts on startup, executing session-start.sh via bash. From astral-sh/uv. Hook ▲ +61 89k A
146 agent-observabilityBagelHole/DevOps-Security-Agent-SkillsInstrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging. Skill ▲ +52 932 A 26
147 platform-engineeringBagelHole/DevOps-Security-Agent-SkillsBuild internal developer platforms (IDPs) with self-service infrastructure, golden paths, and developer portals using Backstage, Crossplane, and score. Skill ▲ +52 932 A 33
148 advogado-especialistasickn33/agentic-awesome-skillsAdvogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional. Skill ▲ +51 46k A 38
149 advogado-criminalsickn33/agentic-awesome-skillsAdvogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal. Skill ▲ +51 46k A 42
150 agentic-awesome-skillssickn33/agentic-awesome-skillsPlugin marketplace listing 59 plugins: agentic-awesome-skills, agentic-bundle-essentials, agentic-bundle-security-engineer, agentic-bundle-security-developer, agentic-bundle-web-wizard. Plugin ▲ +51 46k A
151 paddleocr-doc-parsingPaddlePaddle/PaddleOCRUse this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表… Skill ▲ +51 89k A 140
152 paddleocr-text-recognitionPaddlePaddle/PaddleOCRUse this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字… Skill ▲ +51 89k A 125
153 agentic-awesome-skills AGENTS.mdsickn33/agentic-awesome-skillsAGENTS.md instructions for sickn33/agentic-awesome-skills, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines. Instructions file ▲ +51 46k A 1,425
154 api-mockwshobson/agentsYou are an API mocking expert specializing in creating realistic mock services for development, testing, and demonstration purposes. Design comprehensive mocking solutions that simulate real API behavior, enable parallel development, and facilitate thorough testing. Command ▲ +48 39k A 0
155 performance-optimizationwshobson/agentsOrchestrate end-to-end application performance optimization from profiling to monitoring. Command ▲ +48 39k A 13
156 arm-cortex-expertwshobson/agentsSenior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and… Agent ▲ +48 39k A 72
157 parallel-feature-developmentwshobson/agentsCoordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system… Skill ▲ +48 39k A 105
158 team-communication-protocolswshobson/agentsStructured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing communication norms for a newly spawned team, when deciding whether to send a direct message or a broadcast, when a team-lead… Skill ▲ +48 39k A 101
159 agents AGENTS.mdwshobson/agentsAGENTS.md instructions for wshobson/agents, covering claude-agents — multi-harness agentic plugin marketplace, map, working in this repo, quality gates (run these before pushing) and regenerating per-harness artifacts. Instructions file ▲ +48 39k A 1,462
160 team-reviewerwshobson/agentsMulti-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions. Agent ▲ +48 39k A 43
161 claude-code-workflowswshobson/agentsPlugin marketplace listing 93 plugins: documentation-standards, code-documentation, debugging-toolkit, git-pr-workflows, operating-kit. Plugin ▲ +48 39k A
162 000-project-conventionswshobson/agentsThis is a multi-harness plugin marketplace. Source lives under plugins/; per-harness artifacts (.codex/, .cursor-plugin/, .opencode/, commands/) are generated. Cursor rule ▲ +48 39k A 322
163 010-python-toolingwshobson/agentsPython tooling and dependency conventions for plugin-eval and tools/. Cursor rule ▲ +48 39k A 0
164 avoid-ai-writingwshobson/agentsAudit and rewrite prose that reads as machine-generated, across READMEs, changelogs, PR descriptions, docs, and blog copy, with detect-only, rewrite, and edit-in-place modes. Plugin ▲ +48 39k A
165 code-revieweranthropics/claude-cookbooksPerforms thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts. Agent ▲ +47 52k A 52
166 review-issueanthropics/claude-cookbooksReview and respond to a GitHub issue. Command ▲ +47 52k A 8
167 review-pr-cianthropics/claude-cookbooksReview a pull request and post the review to GitHub (CI/automated use). Command ▲ +47 52k A 18
168 claude-cookbooks CLAUDE.mdanthropics/claude-cookbooksClaude Code instructions for anthropics/claude-cookbooks, covering claude cookbooks, quick start, install dependencies, install pre-commit hooks and set up api key. Instructions file ▲ +47 52k A 914
169 financial-analystanthropics/claude-cookbooksFinancial analysis expert specializing in startup metrics, burn rate, runway calculations, and investment decisions. Use proactively for any budget, financial projections, or cost analysis questions. Agent ▲ +47 52k A 37
170 cookbook-auditanthropics/claude-cookbooksAudit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested. Skill ▲ +47 52k A 26
171 applying-brand-guidelinesanthropics/claude-cookbooksThis skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging. Skill ▲ +47 52k A 27
172 claude-cookbooksanthropics/claude-cookbooksAgent settings declaring 2 hook events (SessionStart, PreToolUse). Settings file ▲ +47 52k A
173 PreToolUseanthropics/claude-cookbooksRuns before the agent uses a tool, executing pre-write.sh and pre-bash.sh (2 commands). From anthropics/claude-cookbooks. Hook ▲ +47 52k A
174 SessionStartanthropics/claude-cookbooksRuns when a session starts, executing session-start.sh. From anthropics/claude-cookbooks. Hook ▲ +47 52k A
175 auto-review-loopwanshuiyin/Auto-claude-code-research-in-sleepAutonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or… Skill ▲ +43 16k A 65
176 proof-checkerwanshuiyin/Auto-claude-code-research-in-sleepRigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明"… Skill ▲ +43 16k A 87
177 aris-reviewer-claudewanshuiyin/Auto-claude-code-research-in-sleepARIS reviewer agent using Anthropic Claude Sonnet 4.5 for cross-family review. Agent ▲ +43 16k A 18
178 compare-tasksaaif-goose/gooseCompare how two harbor benchmark runs performed on a single shared task. Skill ▲ +42 54k A 16
179 goose AGENTS.mdaaif-goose/gooseAGENTS.md instructions for aaif-goose/goose, covering agents instructions, contribution workflow, github communication, agent loop migration and setup. Instructions file ▲ +42 54k A 1,230
180 goose copilot-instructions.mdaaif-goose/gooseCopilot instructions for aaif-goose/goose, covering github copilot code review instructions, review philosophy, priority areas (review these), security & safety and correctness issues. Instructions file ▲ +42 54k A 1,077
181 PostToolUseaaif-goose/gooseRuns after a tool call finishes for developer__shell and developer__text_editor tool calls, executing announce.sh. From aaif-goose/goose. Hook ▲ +42 54k A
182 SessionStartaaif-goose/gooseRuns when a session starts, executing announce.sh. From aaif-goose/goose. Hook ▲ +42 54k A
183 google-workspace-setupOpen-Curiosity/gini-agentOne-time setup for gws: install, OAuth, scopes, auto-approve. Skill ▲ +35 1.8k A 23
184 gini-agent AGENTS.mdOpen-Curiosity/gini-agentAGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches. Instructions file ▲ +35 1.8k A 3,639
185 gini-bug-reportOpen-Curiosity/gini-agentFile a locally-captured, already-redacted Gini crash report as a GitHub issue, with the user's consent. Reads the pending crash queue and delegates the actual filing to the github-issues skill. Skill ▲ +35 1.8k A 47
186 OpenSandbox AGENTS.mdopensandbox-group/OpenSandboxAGENTS.md instructions for opensandbox-group/OpenSandbox, covering opensandbox agents, repository map, routing, working principles and guardrails. Instructions file ▲ +34 15k A 1,693
187 troubleshoot-sandboxopensandbox-group/OpenSandboxTroubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc. Skill ▲ +34 15k A 48
188 build-dashboardanthropics/knowledge-work-pluginsBuild an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file. Skill ▲ +32 24k A 56
189 audit-supportanthropics/knowledge-work-pluginsSupport SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits. Skill ▲ +32 24k A 45
190 knowledge-work-pluginsanthropics/knowledge-work-pluginsPlugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales. Plugin ▲ +32 24k A
191 add-memory-kindEverMind-AI/EverOSAdd a new business memory kind end-to-end. Pick the storage combination (Markdown / SQLite / LanceDB), pick the markdown strategy (daily-log / skill-named / single-file), then wire up the schema(s), repo(s), and writer(s). Skill ▲ +32 13k A 55
192 financeanthropics/knowledge-work-pluginsStreamline finance and accounting workflows, from journal entries and reconciliation to financial statements and variance analysis. Speed up audit prep, month-end close, and keeping your books clean. Plugin ▲ +32 24k A
193 releaseEverMind-AI/EverOSCut a versioned release and publish everos to PyPI via the tag-triggered workflow. Skill ▲ +32 13k A 20
194 EverOS CLAUDE.mdEverMind-AI/EverOSClaude Code instructions for EverMind-AI/EverOS, covering everos — md-first memory extraction framework, quick commands, architecture, engineering practices and branch strategy. Instructions file ▲ +32 13k A 1,056
195 biorenderanthropics/knowledge-work-pluginsBioRender's hosted server: lets the agent create and edit scientific figures and diagrams in BioRender. Remote server at mcp.services.biorender.com. MCP server ▲ +32 24k A
196 biorxivanthropics/knowledge-work-pluginsOne of Anthropic's hosted health and life-sciences servers (bioRxiv/medRxiv preprints, ClinicalTrials.gov, ChEMBL and others): lets the agent search and read that source directly. Remote server at hcls.mcp.claude.com. MCP server ▲ +32 24k A
197 projectsEverMind-AI/EverOSView your Claude Code projects tracked by EverMem. Command ▲ +32 13k A 9
198 askEverMind-AI/EverOSAsk a question about past work. Searches memories and combines with current context to answer. Command ▲ +32 13k A 17
199 gc-minimal-zine-poster-v0-3LiamGvchi/gc-minimal-zine-posterGenerate or analyze poetic paper-texture minimal zine posters with large negative space, a small editorial collage or focal element, experimental typography, and one clear color accent. Use when the user gives a theme, sentence, article, mood, object, photo, content brief, reference images, or an image folder and… Skill ▲ +32 6.8k A 100
200 settingsEverMind-AI/EverOSAgent settings declaring 13 allowed tools. Settings file ▲ +32 13k A

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.