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
501 hephaestus-networkagentlas-ai/Agentlas-OSUse when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion. Skill ▲ +5 1.1k A 75
502 design-reviewmohitagw15856/pm-claude-skillsWorkflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills. Command ▲ +5 1.3k A 24
503 routing-card-authoringagentlas-ai/Agentlas-OSUse whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them. Skill ▲ +5 1.1k A 68
504 codegraphcontextCodeGraphContext/CodeGraphContextUse CodeGraphContext (CGC) to index a repo into a graph DB and query it via CLI or MCP. Apply when the user wants semantic/code-graph search, call graphs, indexing, or configuring the codegraphcontext MCP server. Skill ▲ +5 4.1k A 53
505 hep-browseragentlas-ai/Agentlas-OSUse the Agentlas browser hardpoint for browser-required work. Command ▲ +5 1.1k A 12
506 agentlasagentlas-ai/Agentlas-OSAgentlas commands — one entry point for network, build, storm, call, and the rest. Command ▲ +5 1.1k A 20
507 39-agent-skills-mcp-code-execution-panaversity-agentfactorymajiayu000/claude-skill-registryBuild a specification-first Digital FTE that orchestrates accumulated intelligence from Lessons 1-7. Learn to compose execution skills into production-ready agents, validate against specifications, and position for monetization. Skill ▲ +5 585 A 39
508 39-agent-skills-mcp-code-executionmajiayu000/claude-skill-registryCreate a skill that orchestrates the write-execute-analyze loop to autonomously process data. Learn to implement error recovery, iterate toward robust solutions, and test your skill across diverse input scenarios. This is where specification-driven development meets real problem-solving. Skill ▲ +5 585 A 50
509 pm-claude-skillsmohitagw15856/pm-claude-skillsPM stands for Professional, not just Product Management. 515 Claude Skills + 4 agent templates across 74 bundles covering 31 professions — engineering, security, AI/ML, customer success, legal, government & policy, finance, personal finance, HR, sales, design, Figma, marketing, social media, writers, developer… Plugin ▲ +5 1.3k A
510 interface-designDammyjay93/interface-designCraft-first interface design for dashboards, admin panels, SaaS apps, tools, settings pages, data interfaces, and interactive products. Use when designing, building, reviewing, auditing, or refining product UI where visual craft, layout hierarchy, tokens, states, visual direction, or design-system consistency matter.… Skill ▲ +5 5.6k A 78
511 firmmohitagw15856/pm-claude-skillsConvene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved. Command ▲ +5 1.3k A 24
512 pm-claude-skills AGENTS.mdmohitagw15856/pm-claude-skillsAGENTS.md instructions for mohitagw15856/pm-claude-skills, covering agents.md, what this repo is, working conventions and house prose rules (the mini standard). Instructions file ▲ +5 1.3k A 563
513 launch-captainmohitagw15856/pm-claude-skillsGo-to-market and launch partner for positioning, GTM plans, launch checklists, competitor teardowns, and press/announcements. Use to position a product, plan a launch, or analyse a competitor. Agent ▲ +5 1.3k A 48
514 pm-partnermohitagw15856/pm-claude-skillsStrategic product-management partner. Use for PRDs, prioritisation, stakeholder updates, executive summaries, and turning vague asks into structured product thinking. Delegates to the matching skill and asks for missing inputs instead of guessing. Agent ▲ +5 1.3k A 48
515 issue-briefVasiHemanth/tokentelemetryExplain a GitHub issue, discussion, or feature request in plain language before deciding whether to build it. Covers what the reporter actually wants, a numbered walkthrough of the failure using real hostnames/ports/endpoints, how the code behaves today with file:line anchors, what implementing it would take, and the… Skill ▲ +5 340 A 195
516 bug-auditVasiHemanth/tokentelemetryWeekly multi-agent audit for serious bugs (data integrity, silent caps, staleness, timestamp math, trust boundaries). Fans out Sonnet scanners + Opus deep auditors, adversarially verifies every finding, files GitHub issues for confirmed critical/high bugs. Trigger: /bug-audit. Skill ▲ +5 340 A 0
517 agentlas-core-engine-meta-agentagentlas-ai/Agentlas-OSUse this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture. Agent ▲ +5 1.1k A 38
518 audit-deepVasiHemanth/tokentelemetryDeep single-subsystem audit that reasons about state over time (caches, upserts, migrations, concurrent scans) rather than pattern-matching lines. Used by /bug-audit on the riskiest subsystems; runs on Opus for reasoning depth. Agent ▲ +5 340 A 56
519 pm-claude-skillsmohitagw15856/pm-claude-skills1117 professional Agent Skills + workflow recipes — searchable & fetchable over MCP. Runs locally from the pm-claude-skills npm package. MCP server ▲ +5 1.3k A
520 audit-verifierVasiHemanth/tokentelemetryAdversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, where cheap, reproducing it with a throwaway script. Kills false positives before they reach the report. Runs on Opus. Agent ▲ +5 340 A 56
521 agentlas-core-engineagentlas-ai/Agentlas-OSPlugin marketplace listing 1 plugin: hephaestus. Plugin ▲ +5 1.1k A
522 claude-skill-registry AGENTS.mdmajiayu000/claude-skill-registryAGENTS.md instructions for majiayu000/claude-skill-registry, covering repository policy (core-first), repo identity map, edit routing, publish contract and case-conflict policy (core implementation). Instructions file ▲ +5 585 A 695
523 claude-skill-registry CLAUDE.mdmajiayu000/claude-skill-registryClaude Code instructions for majiayu000/claude-skill-registry, covering claude.md, repo map, how to decide where to edit, generated vs owned files in main and publish flow. Instructions file ▲ +5 585 A 555
524 interface-design:design-reviewDammyjay93/interface-designStrict, multi-pass craft and visual-hierarchy review of a UI build, with severity scoring and an explicit approval bar. The design counterpart to a deep code-quality review. Command ▲ +5 5.6k A 40
525 interface-design:design-deslopDammyjay93/interface-designStrip the signatures that make a UI look AI-generated — flat hierarchy, no focal point, monotone layout, timid palettes, generic tokens, defaulted type, missing states. The design counterpart to a code-deslop pass. Command ▲ +5 5.6k A 52
526 output-doctorAgentSystemLabs/nebulaShape every reply to the user into one fixed layout — ==== YOU ASKED ==== (the refined prompt prompt-daddy logged, verbatim), ==== OVERVIEW ==== (what happened, a few plain sentences), ==== ACTION REQUIRED ==== (present if and only if the user must do something before the work is complete: numbered steps, exact… Skill ▲ +5 100 A 192
527 prompt-daddyAgentSystemLabs/nebulaBefore starting any new task, rewrite the user's prompt once into the best fully specified version of it — the ambiguous words closed, the unstated "keep X as-is" named, the why and the evidence in place, the user's aliases replaced by the ALL-CAPS TERMS from TERMS.md — asking the user only for the context the work… Skill ▲ +5 100 A 154
528 interface-designDammyjay93/interface-designPlugin marketplace listing 1 plugin: interface-design. Plugin ▲ +5 5.6k A
529 interface-designDammyjay93/interface-designDesign engineering for Claude Code. Build production-grade interfaces with strong visual hierarchy, review craft against an approval bar, and strip AI design slop. Self-contained — direction, hierarchy, tokens, polish, and motion in one skill. Plugin ▲ +5 5.6k A
530 tokentelemetryVasiHemanth/tokentelemetryAgent settings declaring 1 hook event (PreToolUse). Settings file ▲ +5 340 A
531 tokentelemetry AGENTS.mdVasiHemanth/tokentelemetryAGENTS.md instructions for VasiHemanth/tokentelemetry, covering agents.md, project, common commands and project layout. Instructions file ▲ +5 340 A 91
532 eval-skew-reviewer7xuanlu/wenlanReviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew — verifies the feature is wired into the ONE canonical ingest path AND the eval seed AND the seed liveness contract, so it can't ship "merged-but-inert". Use after changes touching ingest enrichment, a new… Agent ▲ +5 60 A 90
533 run-wenlan-app7xuanlu/wenlanBuild, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS. Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it. Skill ▲ +5 60 A 60
534 rust-async-safety-reviewer7xuanlu/wenlanReviews Rust async code for tokio + libsql + axum concurrency hazards. Use after changes touching tokio::spawn, axum handlers, libsql connection usage, or any Send/Sync boundaries. Read-only — produces findings, does not edit. Agent ▲ +5 60 A 59
535 curate7xuanlu/wenlanReview pending Wenlan captures, revisions, or daemon refinements from Codex. Use for explicit audit walks after /brief or /handoff surfaces pending work. Invoked as /curate captures, /curate revisions, or /curate refinements. Skill ▲ +5 60 A 55
536 mcp-fiscal-brasilDeHor-Labs/mcp-fiscal-brasilMCP fiscal brasileiro - 44 ferramentas, zero API key. CNPJ, NF-e, Reforma Tributaria IBS/CBS, ICMS, Simples Nacional, NCM/CFOP, indexadores BCB. Runs locally from the mcp-fiscal-brasil Python package. MCP server ▲ +5 281 A
537 nebula CLAUDE.mdAgentSystemLabs/nebulaClaude Code instructions for AgentSystemLabs/nebula. Instructions file ▲ +5 100 A 385
538 nebulaAgentSystemLabs/nebulaAgent settings declaring 2 hook events (UserPromptSubmit, PreToolUse). Settings file ▲ +5 100 A
539 nebula-titleAgentSystemLabs/nebulaNebula session auto-title (managed by nebula — edits are overwritten). Cursor rule ▲ +5 100 A 149
540 wenlan AGENTS.md7xuanlu/wenlanAGENTS.md instructions for 7xuanlu/wenlan, covering agents.md, start here, build and verification, repository invariants and git and release. Instructions file ▲ +5 60 A 1,347
541 Aperant CLAUDE.mdAndyMik90/AperantClaude Code instructions for AndyMik90/Aperant, covering claude.md, product overview, critical rules, work approach: orchestrator-first and context management. Instructions file ▲ +5 15k A 4,672
542 UserPromptSubmitAgentSystemLabs/nebulaRuns when you submit a prompt, before the agent sees it, executing recall.py via python3. From AgentSystemLabs/nebula. Hook ▲ +5 100 A
543 PreToolUseAgentSystemLabs/nebulaRuns before the agent uses a tool for Bash tool calls, executing guard.py via python3. From AgentSystemLabs/nebula. Hook ▲ +5 100 A
544 settings7xuanlu/wenlanAgent settings declaring 2 hook events (PreToolUse, Stop). Settings file ▲ +5 60 A
545 PreToolUse7xuanlu/wenlanRuns before the agent uses a tool for Bash, Edit, Write and MultiEdit tool calls, executing block-no-verify.sh and block-release-please-files.sh via bash with --show-toplevel and --is-inside-work-tree (2 commands). From 7xuanlu/wenlan. Hook ▲ +5 60 A
546 design-motion-principleskylezantos/design-motion-principlesMotion and interaction design expert based on Emil Kowalski, Jakub Krehel, and Jhey Tompkins' techniques. Two modes — build interactive components with purposeful motion, or audit existing animations to catch AI-slop motion patterns (audit emits a branded HTML report with looping demos). Use when creating, adding… Skill ▲ +5 1.0k A 119
547 7xuanlu-wenlan7xuanlu/wenlanPlugin marketplace listing 1 plugin: wenlan. Plugin ▲ +5 60 A
548 Stop7xuanlu/wenlanRuns when the agent finishes a response, executing pre-stop-gate.sh via bash with --show-toplevel and --is-inside-work-tree. From 7xuanlu/wenlan. Hook ▲ +5 60 A
549 setup-statuslineAndyMik90/AperantConfigure ccstatusline to display real-time auto-claude progress in your Claude Code status bar. Command ▲ +5 15k A 0
550 wenlan7xuanlu/wenlanA living knowledge base your agents build as they work. What they learn becomes source-cited wiki pages that refresh between sessions, so each new thread starts from your latest work. Plugin ▲ +5 60 A
551 wenlan CLAUDE.md7xuanlu/wenlanClaude Code instructions for 7xuanlu/wenlan, a project described as: Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust. Instructions file ▲ +5 60 A 99
552 wenlan7xuanlu/wenlanMCP server "wenlan" as configured in 7xuanlu/wenlan. Launched with ./bin/wenlan-mcp-runner.sh. MCP server ▲ +5 60 A
553 nebula AGENTS.mdAgentSystemLabs/nebulaAGENTS.md instructions for AgentSystemLabs/nebula, covering nebula, the shared memory and vocabulary, before you start a task, speak in the terms and after you finish a task. Instructions file ▲ +5 100 B 1,263
554 nebula-memoryAgentSystemLabs/nebulaNebula shared work log — read before a task, append after. Cursor rule ▲ +5 100 B 350
555 review-prsgoogleapis/mcp-toolboxReview a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks… Skill ▲ +4 16k A 162
556 fix-failing-testsgoogleapis/mcp-toolboxDiagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a… Skill ▲ +4 16k A 87
557 mindshub CLAUDE.mdmindsdb/mindshubClaude Code instructions for mindsdb/mindshub, covering minds platform, submodules, clone (fresh), initialize after cloning without submodules and pull — sync to what the parent repo pins (default). Instructions file ▲ +4 40k A 1,908
558 sc:recommendSuperClaude-Org/SuperClaude_FrameworkUltra-intelligent command recommendation engine - recommends the most suitable SuperClaude commands for any user input. Command ▲ +4 24k A 22
559 pmSuperClaude-Org/SuperClaude_FrameworkProject Manager Agent - Default orchestration agent that coordinates all sub-agents and manages workflows seamlessly. Command ▲ +4 24k A 20
560 SuperClaude_Framework CLAUDE.mdSuperClaude-Org/SuperClaude_FrameworkClaude Code instructions for SuperClaude-Org/SuperClaude_Framework, covering claude.md, 🐍 python environment rules, required commands, all python operations must use uv and 📂 project structure. Instructions file ▲ +4 24k A 3,144
561 socratic-mentorSuperClaude-Org/SuperClaude_FrameworkEducational guide specializing in Socratic method for programming knowledge with focus on discovery learning through strategic questioning. Agent ▲ +4 24k A 24
562 pm-agent-guideSuperClaude-Org/SuperClaude_FrameworkDetailed philosophy, examples, and quality standards for the PM Agent. Agent ▲ +4 24k A 0
563 mcp-toolbox GEMINI.mdgoogleapis/mcp-toolboxGemini CLI instructions for googleapis/mcp-toolbox, covering mcp toolbox context & style guide, project overview, tech stack, key directories and development workflow. Instructions file ▲ +4 16k A 3,611
564 Confidence CheckSuperClaude-Org/SuperClaude_FrameworkPre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification. Skill ▲ +4 24k A 41
565 brainstormSuperClaude-Org/SuperClaude_FrameworkActivate brainstorming mode for collaborative discovery and creative problem-solving. Use when users have vague requests, want to explore ideas, or need requirements discovery. Skill ▲ +4 24k A 31
566 xbergxberg-io/xbergExtract text, tables, metadata, and images from 106 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format)… Skill ▲ +4 9.2k A 87
567 claude-agent-sdk-python CLAUDE.mdanthropics/claude-agent-sdk-pythonClaude Code instructions for anthropics/claude-agent-sdk-python, covering workflow, lint and style, check for issues and fix automatically, typecheck and run all tests. Instructions file ▲ +4 8.0k A 180
568 plugin-architecture-patternsxberg-io/xbergDesign, implement, or diagnose Xberg plugin traits, typed registries, priority collisions, lifecycle, native extractors, and Alef-generated Python plugin bridges. Load for plugin-system work, not ordinary extractor parsing. Skill ▲ +4 9.2k A 49
569 mcp-toolboxgoogleapis/mcp-toolboxMCP server "mcp-toolbox" as configured in googleapis/mcp-toolbox. Runs in Docker (us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:1.9.0). MCP server ▲ +4 16k A
570 azure-kusto-graphmicrosoft/skillsBuild and query Kusto graphs from natural language. Covers transient graphs (make-graph), persistent graph models/snapshots, pattern matching (graph-match), shortest paths, connected components, and graph-to-table export. Generates the edges-first thinking: define edges, define node lookups, union, make-graph. WHEN… Skill ▲ +4 3.0k A 131
571 azure-kusto-irql-graphmicrosoft/skillsApply IRQL graph functions to KQL or IRQL query results for Kusto Explorer visualization. Generates LiftToGraph mappings and composes GraphRenderView, GraphFoldByProperty, ExtractNode, EnrichNode, and EnrichGraph calls. Accepts a supplied query or limited basic natural-language source request; it is not a general… Skill ▲ +4 3.0k A 155
572 garak AGENTS.mdNVIDIA/garakAGENTS.md instructions for NVIDIA/garak, covering issue policy, contribution policy, duplicate-work checks, issues to avoid and accountability. Instructions file ▲ +4 9.1k A 1,415
573 skills copilot-instructions.mdmicrosoft/skillsCopilot instructions for microsoft/skills, covering copilot instructions for agent skills, project overview, ⚠️ fresh information first, core principles and 1. think before coding. Instructions file ▲ +4 3.0k A 2,575
574 Project Scaffoldermicrosoft/skillsFull-stack Azure AI Foundry application scaffolder for React + FastAPI + azd projects. Agent ▲ +4 3.0k A 23
575 Backend Developermicrosoft/skillsFastAPI/Python specialist for CoreAI DIY backend development with Pydantic, Cosmos DB, and Azure services. Agent ▲ +4 3.0k A 25
576 SuperClaude_Framework AGENTS.mdSuperClaude-Org/SuperClaude_FrameworkAGENTS.md instructions for SuperClaude-Org/SuperClaude_Framework, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines. Instructions file ▲ +4 24k A 651
577 connect-required-verification-informationstripe/aiUse this skill when the user asks what information a Stripe Connect connected account must provide for verification, onboarding, KYC, or account requirements; when they need to compare requirements between connected-account setups; or when they ask which verification fields, documents, or business details are required… Skill ▲ +4 1.8k A 80
578 superclaudeSuperClaude-Org/SuperClaude_FrameworkAI-enhanced development framework for Claude Code — 30 commands, 20 agents, 7 modes, confidence checks, parallel execution, and reflexion-based learning. Plugin ▲ +4 24k A
579 connect-recommendstripe/aiUse this skill when the user asks about Stripe Connect configuration, charge patterns, Dashboard access, or how to get started with Connect, is building a marketplace, platform, multi-vendor store, gig platform, or subscription platform, needs to pay out sellers, vendors, or providers, mentions split payments, revenue… Skill ▲ +4 1.8k A 151
580 commitanthropics/claude-agent-sdk-pythonBased on the above changes, create a single git commit. Command ▲ +4 8.0k A 4
581 generate-changeloganthropics/claude-agent-sdk-pythonGenerate changelog for a new release version. Command ▲ +4 8.0k A 8
582 settingsanthropics/claude-agent-sdk-pythonAgent settings declaring 1 hook event (PostToolUse) and 5 allowed tools. Settings file ▲ +4 8.0k A
583 hyperledger-fabric-developerdavepoon/buildwithclaudeDevelop enterprise blockchain solutions with Hyperledger Fabric v2.5 LTS and v3.x. Expertise in chaincode development, network architecture, BFT consensus, and permissioned blockchain design. Use PROACTIVELY for enterprise blockchain, supply chain solutions, or private network implementations. Agent ▲ +4 3.4k A 63
584 PostToolUseanthropics/claude-agent-sdk-pythonRuns after a tool call finishes for Edit, Write and MultiEdit tool calls, running an inline shell check. From anthropics/claude-agent-sdk-python. Hook ▲ +4 8.0k A
585 ag2-architectdavepoon/buildwithclaudeAG2 architecture advisor that recommends agent patterns and orchestration strategies. Invoke when designing a multi-agent system, choosing between group chat, pipeline, swarm, or nested chat patterns. Agent ▲ +4 3.4k A 40
586 Company Researcherstripe/aiResearch a company from its URL or description to infer Stripe Connect integration shape. Agent ▲ +4 1.8k A 18
587 SessionStartSuperClaude-Org/SuperClaude_FrameworkRuns when a session starts, executing session-init.sh. From SuperClaude-Org/SuperClaude_Framework. Hook ▲ +4 24k A
588 connector-tooldavepoon/buildwithclaudeCreate API connector tools for AG2 agents with auth handling, pagination, rate limiting, and error mapping. Command ▲ +4 3.4k A 20
589 dart-migrate-to-checks-packageflutter/agent-pluginsReplace the usage of expect and similar functions from package:matcher to package:checks equivalents. Skill ▲ +4 2.9k A 32
590 sequential-thinkingSuperClaude-Org/SuperClaude_FrameworkAdds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package. MCP server ▲ +4 24k A
591 group-chatdavepoon/buildwithclaudeCreate a multi-agent group chat with AG2 using configurable speaker selection patterns. Command ▲ +4 3.4k A 14
592 pentestagent CLAUDE.mdGH05TCREW/pentestagentClaude Code instructions for GH05TCREW/pentestagent, covering pentestagent — claude.md, project overview, tech stack, repository layout and configuration. Instructions file ▲ +4 3.0k A 2,345
593 dart-use-ffigenflutter/agent-pluginsGuide agents to use package:ffigen to automatically generate FFI bindings instead of writing them manually. Use this skill when a task involves writing new FFI bindings, extending C/Objective-C/Swift integrations, or replacing hand-crafted dart:ffi setups. Skill ▲ +4 2.9k A 61
594 code-healthdavepoon/buildwithclaudeScans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Delegates to the Centinela (QA) agent. Skill ▲ +4 3.4k A 35
595 feature-specdavepoon/buildwithclaudeCreates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent. Skill ▲ +4 3.4k A 32
596 xberg-developerxberg-io/xbergRoute cross-cutting Xberg work to the repository's task-specific architecture and workflow skills. Agent ▲ +4 9.2k A 22
597 extraction-engineerxberg-io/xbergRoute document extraction work to format, MIME, pipeline, PDF, safety, corpus, and benchmark guidance. Agent ▲ +4 9.2k A 25
598 xbergxberg-io/xbergLocal document extraction: text, tables, metadata, images from 106 formats with optional OCR. Plugin ▲ +4 9.2k A
599 skillsmicrosoft/skillsPlugin marketplace listing 7 plugins: deep-wiki, azure-skills, azure-sdk-python, azure-sdk-dotnet, azure-sdk-typescript. Plugin ▲ +4 3.0k A
600 xbergxberg-io/xbergDocument intelligence for coding agents, by Kreuzberg, Inc. Plugin ▲ +4 9.2k 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.