# Trending

> The resources that got the most attention in the last 7 days. Heat = views + 3 × install-command copies. GitHub stars fill the list when there is not enough data; those entries carry no heat.

The ranking is cached, not real-time: this one was computed at 2026-10-17 05:28 (UTC+8).
Filter by type: append `?type=<cli|skill|plugin|mcp>` to the URL.

50 items, in ranking order.

1. [Browser Use](https://hebbmind.com/fr/cli/browser-use.md): [CLI] Heat 19. Open-source browser agent project. Its browser-use CLI lets Claude Code, Codex and other agents drive your logged-in local Chrome with Python snippets, or connect to a cloud browser; also ships a Python agent library. The cloud browser needs an API key.
2. [PostHog MCP](https://hebbmind.com/fr/mcp/posthog-mcp.md): [MCP] Heat 19. PostHog's official hosted MCP: lets agents query product analytics with HogQL, manage feature flags and A/B experiments, and investigate errors and session replays. Sign in to PostHog to authorize; tool calls are free, though a few LLM-powered tools count toward AI usage.
3. [Superpowers](https://hebbmind.com/fr/plugin/superpowers.md): [Plugin] Heat 16. A complete development methodology for coding agents: brainstorm to clarify requirements, write an implementation plan, then build with subagents, with red-green TDD, systematic debugging and code review throughout. In the official Claude Code and Codex marketplaces.
4. [MarkItDown-MCP](https://hebbmind.com/fr/mcp/markitdown-mcp.md): [MCP] Heat 16. From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP.
5. [PDF](https://hebbmind.com/fr/skill/pdf.md): [Skill] Heat 16. Extracts text and tables from PDFs; merges, splits and rotates pages, adds watermarks, fills forms and OCRs scanned documents. The official Anthropic skill behind Claude's document features; source-available, not open source.
6. [Browser Use](https://hebbmind.com/fr/skill/browser-use.md): [Skill] Heat 16. Controls your local Chrome over CDP to navigate, click, type, take screenshots and scrape data, reusing logged-in sessions. Official browser-use skill; install the browser-use CLI with uv first.
7. [Linear](https://hebbmind.com/fr/plugin/linear.md): [Plugin] Heat 16. Official Linear plugin in Anthropic's marketplace: connects the hosted Linear MCP to create and update issues, manage projects and states, and search across workspaces from chat. Needs a Linear account and OAuth authorization.
8. [Context7](https://hebbmind.com/fr/mcp/context7.md): [MCP] Heat 15. Injects up-to-date, version-specific docs and code examples for libraries and frameworks into the agent's context, so it stops using outdated or invented APIs. By Upstash; works anonymously, and a free API key raises the limits.
9. [SEO Audit](https://hebbmind.com/fr/skill/seo-audit.md): [Skill] Heat 15. Diagnoses website SEO issues: checks crawling and indexing, Core Web Vitals, metadata and on-page content, and gives prioritized, actionable fixes. From the marketingskills collection.
10. [Product Management](https://hebbmind.com/fr/plugin/product-management.md): [Plugin] Heat 14. Product management plugin: writes PRDs from a problem statement, plans and updates roadmaps, generates stakeholder updates, synthesizes user research, and runs competitive analysis and metrics reviews. Official from Anthropic.
11. [Auto-Empirical Research Skills (AERS)](https://hebbmind.com/fr/skill/auto-empirical-research-skills.md): [Skill] Heat 14. Empirical social science skills from Stanford REAP and CoPaper.AI, bundling 77 in-house and third-party collections: topic selection, literature reviews, DID/RD/IV identification, regression tables in Python, Stata or R, robustness audits and paper writing. Stata flows need Stata installed.
12. [Finance](https://hebbmind.com/fr/plugin/finance.md): [Plugin] Heat 13. Finance and accounting plugin: prepares journal entries, reconciles accounts, generates income statements, runs variance analysis, manages month-end close and supports SOX audit testing. Can pull data from ERPs and data warehouses. Official from Anthropic.
13. [LLM](https://hebbmind.com/fr/cli/llm.md): [CLI] Heat 13. Simon Willison's LLM CLI and Python library: call OpenAI, Claude, Gemini and local models from the terminal, with conversations logged to SQLite automatically, plus embeddings, structured extraction, tool calling and a plugin system.
14. [PubMed](https://hebbmind.com/fr/plugin/pubmed.md): [Plugin] Heat 13. PubMed plugin from Anthropic's life sciences marketplace: connects to the US National Library of Medicine's remote MCP to search biomedical literature and research papers. No account needed.
15. [mattpocock/skills](https://hebbmind.com/fr/plugin/mattpocock-skills.md): [Plugin] Heat 12. Matt Pocock's engineering skills: /grill-me interrogates requirements to align on intent, then a spec-and-ticket flow, TDD, code review and domain modeling. Small, composable skills, listed in the official Claude Code plugin marketplace.
16. [Frontend Design](https://hebbmind.com/fr/skill/frontend-design.md): [Skill] Heat 12. Has the agent commit to a visual direction before building or redesigning an interface, making deliberate choices on color, type and layout instead of generic, templated AI UI. Official Anthropic skill.
17. [PPTX](https://hebbmind.com/fr/skill/pptx.md): [Skill] Heat 12. Creates, reads and edits PowerPoint decks: applies templates and layouts, handles speaker notes and comments, and merges or splits slides. The official Anthropic skill behind Claude's document features; source-available, not open source.
18. [Docling](https://hebbmind.com/fr/cli/docling.md): [CLI] Heat 12. Parses PDF, DOCX, PPTX, XLSX, HTML, images and audio, recovering layout, reading order, tables and formulas, and exports Markdown, HTML or lossless JSON. Started by IBM Research, now hosted by the LF AI & Data Foundation; runs fully locally.
19. [Brag](https://hebbmind.com/fr/skill/brag.md): [Skill] Heat 12. Turns the current project into a 15-25 second shareable launch video: reads the code, plans a concept and storyboard, hands a composition brief to Hyperframes to render with music and sound effects, and writes share copy. Supports tone, format and duration options plus optional Kokoro voiceover.
20. [PaperQA2](https://hebbmind.com/fr/cli/paper-qa.md): [CLI] Heat 12. High-accuracy retrieval-augmented Q&A over paper PDFs, text and Office documents, filling in citation metadata, checking retractions and attaching traceable sources to answers. Provides the pqa CLI and a Python library. Needs an LLM API key by default; local models can be configured.
21. [Google Search Console MCP Server](https://hebbmind.com/fr/mcp/mcp-gsc.md): [MCP] Heat 12. Connects Google Search Console so agents can analyze queries, clicks and rankings, compare periods, check URL indexing status and manage sitemaps. Not an official Google project; you need your own Google Cloud OAuth credentials or a service account.
22. [Test-Driven Development](https://hebbmind.com/fr/skill/test-driven-development.md): [Skill] Heat 11. Forces red-green-refactor: write a test and watch it fail, then write the minimum code to pass. Any code written without a verified failing test gets deleted and redone. From the Superpowers workflow.
23. [OpenMontage](https://hebbmind.com/fr/skill/openmontage.md): [Skill] Heat 11. Open-source agentic video production: open Claude Code or Codex in the cloned repo, describe the video, and the agent handles research, script, voiceover, footage, subtitles and editing, confirming storyboard and cost first. Needs Python, Node.js and FFmpeg; free assets work without API keys.
24. [HyperFrames](https://hebbmind.com/fr/plugin/hyperframes.md): [Plugin] Heat 11. HeyGen's official video plugin: compose scenes with HTML, CSS and animation and render deterministic MP4s, with skills for promo videos, captions, voiceover and music, and PR walkthrough videos. Needs Node.js 22+ and FFmpeg.
25. [Qlib](https://hebbmind.com/fr/cli/qlib.md): [CLI] Heat 11. Microsoft's open-source AI quant investment research platform: the qrun command runs dataset building, model training, backtesting and evaluation from a YAML config, with many benchmark models. The official dataset is paused, so prepare market data per the README first.
26. [Quantitative Trading](https://hebbmind.com/fr/plugin/quantitative-trading.md): [Plugin] Heat 11. Quant trading plugin from the wshobson/agents marketplace: quant analyst and risk manager subagents plus backtesting and risk metrics skills for strategy backtests, portfolio optimization and risk measures like VaR, Sharpe ratio and max drawdown. Needs local Python; not investment advice.
27. [accrual-schedule](https://hebbmind.com/fr/skill/accrual-schedule.md): [Skill] Heat 11. Builds the month-end accrual schedule: calculates each accrual for the period under company policy, notes the basis and drafts journal entries; drafts only, never posts, for controller review. A skill in Anthropic's official fund-admin plugin; supply your accrual policy list and GL data.
28. [Lightpanda Browser](https://hebbmind.com/fr/cli/browser.md): [CLI] Heat 11. Headless browser written from scratch in Zig for AI agents and automation, using less memory and running faster than headless Chrome in official benchmarks. fetch turns pages into Markdown, and it can serve CDP or MCP. Telemetry is on by default (an env var disables it); Windows needs WSL.
29. [Web Design Guidelines](https://hebbmind.com/fr/skill/web-design-guidelines.md): [Skill] Heat 11. Reviews UI code against Vercel's Web Interface Guidelines, covering accessibility, focus, forms, animation, typography, dark mode and more, listing issues as file:line. Fetches the latest rules before each review. Maintained by Vercel.
30. [Bio Research](https://hebbmind.com/fr/plugin/bio-research.md): [Plugin] Heat 11. For preclinical life sciences research: bundles MCP connectors for PubMed, bioRxiv, ChEMBL, Open Targets, ClinicalTrials and more, plus analysis skills for single-cell RNA QC, scvi-tools and nf-core pipelines. Official from Anthropic; some data sources need accounts.
31. [write-spec](https://hebbmind.com/fr/skill/write-spec.md): [Skill] Heat 11. Turns a feature idea or problem statement into a structured spec or PRD with goals and non-goals, user stories, success metrics and acceptance criteria, and can split large requests into phases. From Anthropic's official product-management plugin.
32. [Task Master](https://hebbmind.com/fr/mcp/claude-task-master.md): [MCP] Heat 11. Parses a PRD into a dependency-aware task list so Cursor, Claude Code and other coding agents break it down, implement it and track progress; also works as a CLI. Needs at least one model API key, or reuse a Claude Code or Codex CLI login.
33. [Anthropic Sandbox Runtime (srt)](https://hebbmind.com/fr/cli/sandbox-runtime.md): [CLI] Heat 11. Anthropic's official OS-level sandbox CLI: restricts file and network access for agents, MCP servers and any command without containers, using sandbox-exec on macOS and bubblewrap on Linux. Currently a research preview.
34. [Atlassian MCP](https://hebbmind.com/fr/plugin/atlassian-mcp-server.md): [Plugin] Heat 11. Atlassian's official plugin: connects the cloud Atlassian MCP to search and create Jira issues, read and write Confluence pages and manage sprints, with skills that turn meeting notes into tasks and generate status reports. Needs an Atlassian Cloud account with OAuth or an API token.
35. [K-12 Lesson Differentiation](https://hebbmind.com/fr/skill/k12-lesson-differentiation.md): [Skill] Heat 11. Adapts an existing K-12 lesson into below, at and above grade-level versions, producing a teacher differentiation plan and three student handouts as Word documents; can use the Learning Commons Knowledge Graph. Official Anthropic skill.
36. [Diagnosing Bugs](https://hebbmind.com/fr/skill/diagnosing-bugs.md): [Skill] Heat 10. A disciplined process for hard bugs and performance regressions: build a reliable reproduction loop, reproduce and minimize, form hypotheses, instrument to verify, then fix and add a regression test, redacting secrets in output. By Matt Pocock.
37. [MarkItDown](https://hebbmind.com/fr/cli/markitdown.md): [CLI] Heat 10. Converts PDF, Word, Excel, PowerPoint, HTML, images, audio and more into Markdown that keeps headings, lists and tables, ready for LLMs to read and analyze. Maintained by Microsoft; requires Python 3.10+.
38. [XLSX](https://hebbmind.com/fr/skill/xlsx.md): [Skill] Heat 10. Creates, edits and analyzes Excel spreadsheets: formulas, formatting, charts and data cleaning, plus conversion between CSV, TSV and other tabular formats. The official Anthropic skill behind Claude's document features; source-available, not open source.
39. [Playwright](https://hebbmind.com/fr/cli/playwright.md): [CLI] Heat 10. Microsoft's cross-browser end-to-end testing framework: one API drives Chromium, Firefox and WebKit, npx playwright test runs tests in parallel and isolation, with auto-waiting and trace replay for debugging failures.
40. [Impeccable](https://hebbmind.com/fr/skill/impeccable.md): [Skill] Heat 10. Frontend design polish skill: one skill with 24 commands such as polish, audit, critique and typeset, plus 61 deterministic rules that catch typical AI-generated UI problems, with live iteration in the browser. Works with Claude Code, Codex, Cursor and others.
41. [FFmpeg](https://hebbmind.com/fr/cli/ffmpeg.md): [CLI] Heat 10. Command-line toolkit for transcoding, cutting, joining, frame extraction and streaming of audio and video, including ffmpeg, ffprobe and ffplay. A core dependency for agents handling media. The GitHub repo is the official mirror.
42. [Copy Editing](https://hebbmind.com/fr/skill/copy-editing.md): [Skill] Heat 10. Edits and refreshes existing marketing copy in seven sweeps: clarity, voice, value, proof, specificity, emotion and objection handling, keeping the meaning and author's voice. Can also audit and update stale pages. Complements the copywriting skill; from marketingskills.
43. [AI SEO](https://hebbmind.com/fr/skill/ai-seo.md): [Skill] Heat 10. AI search optimization (AEO/GEO) skill from the marketingskills collection: checks whether ChatGPT, Perplexity and Google AI Overviews cite your content and suggests rewrites and structure that AI can extract and cite more easily, including llms.txt and structured data.
44. [agent-browser](https://hebbmind.com/fr/cli/agent-browser.md): [CLI] Heat 10. Browser automation CLI built for AI agents in native Rust: open pages, click and fill forms by refs from accessibility tree snapshots, read text and take screenshots, with compact snapshots and output limits to save context. From Vercel Labs; reuses local Chrome or installs one.
45. [DuckDB](https://hebbmind.com/fr/cli/duckdb.md): [CLI] Heat 10. In-process analytical SQL database. Its CLI queries CSV, Parquet and JSON files directly with SQL, no import or server needed, so agents can sample and aggregate large files. Officially maintained.
46. [OCRmyPDF](https://hebbmind.com/fr/cli/ocrmypdf.md): [CLI] Heat 10. Adds a searchable, copyable text layer to scanned PDFs, with automatic deskew, rotation and size optimization, outputting PDF/A by default. Built on Tesseract, supports 100+ languages and runs fully locally.
47. [gws (Google Workspace CLI)](https://hebbmind.com/fr/cli/googleworkspace-cli.md): [CLI] Heat 10. One CLI for Gmail, Drive, Calendar, Docs, Sheets and other Google Workspace APIs, with commands generated from the Discovery service, JSON output and 100+ Agent Skills. From the googleworkspace org but not officially supported; needs OAuth via a Google Cloud project.
48. [synthesize-research](https://hebbmind.com/fr/skill/synthesize-research.md): [Skill] Heat 10. Synthesizes user feedback from interview notes, surveys and support tickets into themes ranked by frequency and impact, and outputs structured insights and roadmap recommendations. Can pull data from knowledge bases or meeting transcripts. From Anthropic's official product-management plugin.
49. [Legal Risk Assessment](https://hebbmind.com/fr/skill/legal-risk-assessment.md): [Skill] Heat 10. Helps in-house legal score and rank risks in contracts, deals and disputes on a severity-by-likelihood matrix, write risk memos, and know when to escalate to senior or outside counsel. No other tools needed. From Anthropic's legal plugin; not legal advice, have a lawyer review.
50. [Knowledge Work Plugins](https://hebbmind.com/fr/skill/knowledge-work-plugins.md): [Skill] Heat 10. Anthropic's role-based skill collection covering sales, finance, legal, HR, support, marketing, product, design, operations and data analysis: over a hundred skills you can install one at a time. Works best with CRM, data warehouse and other connectors.