{"data":[{"slug":"pulumi","title":"Pulumi","description":"Teach your agent Pulumi: infrastructure as code in TypeScript, Python, Go, C#, Java, YAML, or HCL. Skills for writing and operating cloud infrastructure, migrating from Terraform, CloudFormation, CDK, and ARM, and delegating work to Pulumi Neo, Pulumi's AI platform engineer.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-24T00:00:00.321Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-24T00:00:00.321Z","platform":"claude","sources":["Claude Marketplace"],"works_with":[],"marketplace_url":"https://claude.com/marketplace/plugins/pulumi","repository_url":null},{"slug":"probabl-skills","title":"probabl-skills","description":"Skills to support Machine Learning experimentation using the Python ecosystem.","developer":"Probabl","category":"development","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/probabl-ai/skills"},{"slug":"composing-with-pytheory","title":"composing-with-pytheory","description":"Compose music with PyTheory — progressions, melodies, drums, and full arrangements rendered to audio or MIDI from pure Python.","developer":"Kenneth Reitz","category":"development","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/kennethreitz/pytheory-skill"},{"slug":"wikipedia","title":"wikipedia","description":"Fetch Wikipedia articles and data. WebFetch returns 403 on all Wikipedia URLs due to Python user-agent blocking — this plugin provides the curl workaround.","developer":"andyrosa","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/andyrosa/claude-code-wikipedia-plugin.git"},{"slug":"wezterm-agent-cards-multipanel-sidebar-with-notifications-inspir","title":"wezterm-agent-cards-multipanel-sidebar-with-notifications-inspir","description":"A Claude Code plugin that adds a curses-based sidebar to WezTerm showing your Claude Code sessions as stacked status cards with real-time state tracking. Be notified if your agent needs you!\n\nStrongly inspired by CMUX, a native macOS terminal that surfaces AI agent status through vertical tabs and notification rings. WezTerm Agent Cards brings the same idea to Linux (and anywhere WezTerm runs) — using Claude Code hooks, a Python TUI, and a thin Lua module instead of a dedicated terminal app.","developer":"Wolfgang","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/wrock/wezterm-agent-cards.git"},{"slug":"vm-disk-cleanup","title":"vm-disk-cleanup","description":"Prevent and recover from disk-full errors in Claude's working environment — both Cowork session VMs and Claude Code sandboxes. Clears npm/pip caches, node_modules, Python bytecode, build outputs, and temp files that accumulate during long sessions.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"MSApps-Mobile/claude-plugins"},{"slug":"vibekanban","title":"vibekanban","description":"VibeKanban is a dev progress kanban board that runs entirely inside Claude Code. When you code with Claude, every task is automatically tracked — started, completed, and reported — on a local kanban board with a browser-based UI.\n\nNo cloud service, no sign-up, no npm install. Just a Python server on localhost and a single HTML file. Claude creates tasks when you ask for work, moves them through columns as progress happens, records git diff stats on completion, and writes work reports you can review later in the web UI.\n\nMulti-project support lets you manage several codebases from one board. Switch between projects with tabs, drag cards between columns, and view completed work grouped by date, category, or development phase.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/hoarchi/vibekanban.git"},{"slug":"venture-capital-intelligence","title":"venture-capital-intelligence","description":"9 skills for venture capital intelligence. 3 run on pure Claude reasoning. 6 run Claude + Python for deterministic outputs — screening startups, modeling financials, sizing markets, computing cap table waterfalls, scanning deal signals, and generating LP fund reports. Built from the best open-source VC tools.","developer":"Santhosh Gandhi","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/isanthoshgandhi/venture-capital-intelligence.git"},{"slug":"ultimate-seo-geo","title":"ultimate-seo-geo","description":"The definitive SEO + GEO skill for Claude. Run full site audits with scored findings (0-100), AI search optimization for Google AI Overviews, ChatGPT Search, and Perplexity, Schema.org JSON-LD generation, E-E-A-T assessment, CORE-EEAT 80-item content audit, CITE domain authority rating, entity optimization, and 23 Python diagnostic scripts. Three modes: Audit → Plan → Execute.","developer":"Myk Pono","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/mykpono/ultimate-seo-geo.git"},{"slug":"ty-python-lsp","title":"ty-python-lsp","description":"Wires up Astral's ty, an extremely fast Python type checker, as an LSP server for Claude Code's built-in LSP tool. On .py / .pyi / .pyw files Claude can use hover (inferred types and docstrings), go-to-definition, go-to-implementation, find-references, document and workspace symbol search, and call hierarchy.\nConfiguration is auto-detected from pyproject.toml; no extra LSP settings required. Requires ty on PATH (uv tool install ty or\npip install ty).","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/andres-ortizl/ty-lsp-claude-code-plugin.git"},{"slug":"tula","title":"tula","description":"LLM-native code quality, security, and documentation analysis tool. Scores projects on a 1000-point scale across five categories using YAML rules, static analysis tools, and semantic review for Python, JavaScript, TypeScript, Go, Java, C/C++ and Documentation repositories.","developer":"Ramesh Ghimire","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/DaxGoon/tula.git"},{"slug":"tokalator-glossary","title":"tokalator-glossary","description":"Auto-generates a codebase glossary (symbol index) after /init or on demand. Scans Python, JavaScript, and TypeScript files using AST parsing to map every class, function, and export with file path and line number. The glossary acts as a compressed context layer , Claude can consult it instead of reading files, saving thousands of tokens per session.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/vfaraji89/tokalator-glossary.git"},{"slug":"together-ai-skills","title":"together-ai-skills","description":"A collection of skills that teach coding agents how to use the Together AI platform, including chat completions, image generation, video, audio, embeddings, fine-tuning, batch inference, evaluations, sandboxes, dedicated endpoints, containers, and GPU clusters. Includes runnable Python and TypeScript examples.","developer":"Together AI","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-26T18:00:03.196Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/togethercomputer/skills.git"},{"slug":"tinman-heartbeat-for-claude-code","title":"tinman-heartbeat-for-claude-code","description":"Adds scheduled health monitoring to Claude Code. Define a HEARTBEAT.md checklist for your project and TinMan runs it through Claude on demand or on a timer. Claude analyzes your codebase against the checklist (uncommitted changes, failing tests, stale branches, disk space, whatever you care about) and reports what needs attention. Results are logged and can forward to Telegram via C3Poh. Three security presets control autonomy: sane (notify only, default), paranoid (read-only), and chaos (Claude can act). Zero external dependencies beyond Python 3.9+ and Claude CLI.","developer":"Andy Rosic","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/andyuninvited/tinman_for_claudecode.git"},{"slug":"temporal","title":"temporal","description":"Develop reliable Temporal applications with expert guidance across Python, TypeScript, Go, Java, and more. Covers the full development lifecycle, including designing durable workflows, defining activities and workers, handling retries and timeouts, debugging workflow execution issues, implementing signals and queries, managing versioning safely, writing tests, and operating applications with Temporal CLI and Temporal Cloud.","developer":"Temporal","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/temporalio/claude-temporal-plugin.git"},{"slug":"tdd-evolutionary-loop","title":"tdd-evolutionary-loop","description":"Automate the TDD cycle with a collaborative agent team: two parallel coders and a devil's advocate, working on isolated files for rapid, safe iteration. Describe a feature or point to failing tests and the plugin handles the rest — writing tests, implementing in parallel variants, reviewing code quality, and promoting the best result.","developer":"michael","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/mblando9988/tdd-evolutionary-loop.git"},{"slug":"tdad","title":"tdad","description":"Test-driven regression guard for AI coding agents. After every code change, TDAD looks up impacted tests via a code-test dependency graph and runs only the affected tests before submitting a patch. It also enforces that every change includes a new  regression test. Supports Python, JavaScript/TypeScript, Go, Java, Rust, and Dart projects. Evaluated on SWE-bench Verified, it reduced AI-introduced regressions by 72%.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/pepealonso95/tdad-skill.git"},{"slug":"tailtest","title":"tailtest","description":"tailtest automatically generates and runs tests every time Claude Code edits a file. No commands, no configuration, no reminders needed.\n\nIt hooks into Claude's file write event, detects your language and test runner automatically, generates production-like test scenarios for the code that was just written, and runs them immediately. If everything passes, it stays silent. If something breaks, you see it in the same session while the context is still fresh.\n\nSupports Python (pytest), TypeScript and JavaScript (vitest, jest), Go, Rust, Ruby, Java, and PHP. Works on new projects and existing codebases. On first run, a ramp-up scan queues your existing untested files for gradual background coverage.","developer":"AvanSaber Inc.","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/avansaber/tailtest.git"},{"slug":"supertool","title":"supertool","description":"Batch multiple file operations (read, grep, glob, ls, tail, head) into a single Bash round-trip. Instead of N separate Read/Grep/Glob tool calls — each re-paying the cached context prefix — one ./supertool call handles them all. Includes auto-promote (concrete glob becomes read, single-file grep includes full file), enforcement mode that blocks redundant built-in tools, and per-call logging with caller tracking. Python 3.6+, stdlib-only, 80 tests.","developer":"Digital Process Tools","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Digital-Process-Tools/claude-supertool.git"},{"slug":"statsclaw","title":"statsclaw","description":"StatsClaw orchestrates 9 specialized AI agents (leader, planner, builder, tester, scriber, simulator, distiller, reviewer, shipper) through 13 workflows — from simple code changes to Monte Carlo simulation studies. Features include two-pipeline isolation for adversarial verification, automatic credential detection, shared knowledge brain system, and workspace-synced audit logs. Users just describe what they want in plain language; the leader agent handles the rest.","developer":"StatsClaw","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/statsclaw/statsclaw.git"},{"slug":"srclight","title":"srclight","description":"Deep code indexing for AI agents. Gives Claude Code structural understanding of entire codebases — symbol search, call graphs, type hierarchies, git blame/hotspots, dead code detection, and semantic search. 28 MCP tools across 11 languages (Python, JS/TS, C, C++, C#, Java, Kotlin, Go, Swift, Dart, PHP). Fully local, zero telemetry, MIT licensed.","developer":"srclight","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/srclight/claude-code-plugin.git"},{"slug":"spc-tools","title":"spc-tools","description":"SPC Tools gives Claude a calibrated, comprehensive statistical process control toolkit with pure-JavaScript visualization. Covers standard techniques (control charts, Cpk, Gage R&R) as well as Bayesian and distribution-free methods. No dependencies required; computation is pure Python, charts are zero-dependency ChartSpec JSON rendered client-side.","developer":"Eric Wolters","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/ewolters/spc-tools.git"},{"slug":"sklearn-to-ts","title":"sklearn-to-ts","description":"Train sklearn models (MLP, Random Forest, Linear Regression), export weights to JSON, and generate pure TypeScript inference code with zero npm dependencies. Handles the full pipeline: feature engineering, synthetic data generation, model training, weight export, and TypeScript codegen. The resulting model runs server-side (Node.js/Next.js) or client-side (browser) in <1ms with a ~10-50 KB weights file. No Python runtime, no ONNX, no TensorFlow.js needed at runtime.","developer":"Thomas Meissner","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/TGKMeissner/sklearn-to-typescript-inference.git"},{"slug":"shieldcode","title":"shieldcode","description":"Security hardening and production-grade error handling expertise for Claude Code. Prevents OWASP Top 10 vulnerabilities (SQL injection, XSS,\nbroken auth, secrets exposure) and enforces structured error handling, secure logging, and proper HTTP status codes. Auto-activates when\nwriting code that handles user input, database queries, authentication, API endpoints, or error handling. 991 lines of battle-tested security\npatterns with BAD vs SAFE examples in TypeScript and Python.","developer":"Nikolas de Hor","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/nikolasdehor/shieldcode.git"},{"slug":"security-sweep","title":"security-sweep","description":"Comprehensive security scanner for codebases. Scans for hardcoded secrets (30+ API key formats), injection flaws (SQLi, XSS, command injection, SSRF), authentication issues (JWT misuse, weak password hashing)misconfigurations  (CORS, debug mode, insecure TLS, Docker/K8s), dependency risks, AI-specific vulnerabilities (prompt injection, API key exposure, excessive agent  permissions), mobile security issues (Android/iOS), and data exposure (PII in logs, weak crypto). Covers OWASP Top 10 (2025), Mobile Top 10 (2024), and LLM Top 10 (2025). Supports Python, JavaScript/TypeScript, Java/Kotlin, Go, Ruby, PHP, C#, Swift, and Dart with framework-aware checks that reduce false\npositives.","developer":"onomeaj","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Onome-AJ/security-sweep-plugin.git"},{"slug":"sciagent-skills","title":"sciagent-skills","description":"197 ready-to-use life sciences skills that turn Claude into a domain expert for genomics, proteomics, drug discovery, biostatistics, scientific computing, and scientific writing. Each skill provides runnable code examples, key parameters with defaults, and troubleshooting guides for tools like Scanpy, RDKit, BioPython, PyMC, AutoDock Vina, and 190+ more. Scored 92.0% on BixBench-Verified-50 benchmark (+26.7%p over base Claude). Skills are auto-discovered — just describe your task and Claude finds the relevant skill.","developer":"jaechang-hits","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/jaechang-hits/SciAgent-Skills.git"},{"slug":"scan-modules","title":"scan-modules","description":"Scan and cache project module structure for fast Claude context loading. Use /scan-modules:scan-modules to index your codebase, then Claude auto-loads the cache each session. Supports incremental updates via git diff and auto-update via post-commit hook. Works with Swift, TypeScript, Python, Go, and Rust.","developer":"fengzhyuan","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/fengzhyuan/scan-modules-plugin.git"},{"slug":"rex","title":"rex","description":"Rex provides sub-second Python symbol search across all installed .venv packages. Three tools — rex_find, rex_show, rex_members — let Claude look up function signatures, docstrings, class members, and file locations instantly, without web search or grepping through source files. Results are grounded in the actually installed version — no outdated docs, no hallucinated parameters. Auto-indexes on first use and re-indexes incrementally when packages change. Read-only by design.","developer":"Anton Vykhovanets","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/vykhovanets/rex.git"},{"slug":"revit-bim","title":"revit-bim","description":"Connect Claude to Autodesk Revit and Dynamo. Generate ready-to-run Dynamo Python scripts, query model data, detect clashes, audit model health, manage parameters, create schedules, export IFC, and save .dyn files — all from plain language. Includes 12 skills covering the full BIM workflow.\n\nCreated by Manas Bhatia (Architect and Design Technologist)","developer":"Manas Bhatia","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Utopia5327/revit-bim.git"},{"slug":"relay","title":"relay","description":"An output style + Python hooks that make Claude Code listen before it codes. Asks the right questions, recommends with reasoning, and writes only after you say go. Captures decisions to your repo so your next session — and your teammates — pick up with the reasoning intact. MIT, ~50 lines of Python, no telemetry.","developer":"Basegraph","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/basegraphhq/relay-plugin.git"},{"slug":"recall","title":"recall","description":"Persistent conversation recall for Claude Code. Indexes every exchange into a local SQLite database so you can search, browse, and recover context at any time. Survives /clear commands and context compaction. Search across all sessions in a project or globally across every project. Auto-tags technical terms for discovery. Shares findings between parallel sessions via opt-in highlight connections. Includes a PostCompact nudge that automatically re-orients Claude after context loss. Optional proactive skill teaches Claude to detect context loss and suggest recall commands. Zero external dependencies, pure Python stdlib with FTS5 full-text search and WAL mode for concurrent session safety.","developer":"bledden","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/bledden/claude-recall-plugin.git"},{"slug":"python-remote-debug-skill","title":"python-remote-debug-skill","description":"Python 3.14+ remote debugging with sys.remote_exec() for inspecting running processes, including gevent/Celery workers","developer":"promptromp","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/promptromp/python-remote-debug-skill.git"},{"slug":"python-clean-architecture","title":"python-clean-architecture","description":"Scaffold, review, and refactor Python projects with clean code and architecture. Design principles and patterns implemented the Pythonic way — using Protocol, Callable, functools.partial, and closures instead of heavy class hierarchies. Includes a /review-architecture command, layered FastAPI project scaffolding, and reference guides for 7 design principles, 17 code quality rules, and 10 Pythonic pattern recipes. Inspired by Arjan Codes.","developer":"MKToronto","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/MKToronto/python-clean-architecture.git"},{"slug":"py-pit","title":"py-pit","description":"A Claude Code plugin for Python development","developer":"robhowley","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/robhowley/claude-py-pit.git"},{"slug":"promptfoo-evals","title":"promptfoo-evals","description":"Teaches AI coding agents to create and maintain promptfoo eval suites. Encodes best practices like deterministic assertions first, file-based test organization, correct  environment variable syntax, and proper hallucination/faithfulness checks. Includes a cheatsheet covering 30+ assertion types, provider patterns for OpenAI/Anthropic/Google/Bedrock/HTTP/Python/JS, and test patterns for JSON validation, dataset-driven scaling, and CI-friendly runs.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/promptfoo/promptfoo.git"},{"slug":"project-setup","title":"project-setup","description":"Automatically configures .claude/ by reading your existing project files. Detects Python venvs, Node.js,  Rust, and Go toolchains, plus linters, test runners, and IDE settings (VSCode, PyCharm, Vim, Emacs). No manual setup required.","developer":"len","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-08T00:00:01.297Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/lambdao-dev/claude-project-setup-plugin.git"}],"total":112,"page":1,"per_page":36,"observed_at":"2026-11-08T00:00:01.297Z","source_counts":{"web":529,"demo":12,"skills":5,"official":317,"community":2283,"knowledge-work":123}}