{"data":[{"slug":"scrimba-explain","title":"scrimba-explain","description":"Explain by Scrimba — ask your agent to explain anything as an instant narrated slideshow: a concept, a document, an architecture, a codebase, a git branch or PR. Built live with animations, diagrams, maths, and code, at a shareable scrimba.com link.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-24T00:00:00.321Z","last_seen_at":"2026-11-11T12:00:00.266Z","last_changed_at":"2026-10-24T00:00:00.321Z","platform":"claude","sources":["Claude Marketplace"],"works_with":[],"marketplace_url":"https://claude.com/marketplace/plugins/scrimba-explain","repository_url":null},{"slug":"dart-and-flutter","title":"Dart and Flutter","description":"Official Claude plugin for Dart and Flutter that installs Flutter/Dart Skills and Dart MCP server for building natively compiled, visually stunning applications for mobile, web, desktop, and embedded devices from a single codebase","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-24T00:00:00.321Z","last_seen_at":"2026-11-11T12:00:00.266Z","last_changed_at":"2026-10-24T00:00:00.321Z","platform":"claude","sources":["Claude Marketplace"],"works_with":[],"marketplace_url":"https://claude.com/marketplace/plugins/dart-and-flutter","repository_url":null},{"slug":"product-tracking-skills--knowledge-work","title":"Product Tracking","description":"AI agent skills that make SaaS products data-ready for product analytics — from codebase scan to tracking plan to working instrumentation code.","developer":"Accoil","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","last_changed_at":"2026-10-16T06:00:02.125Z","platform":"claude","sources":["Knowledge Work"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Accoil/product-tracking-skills.git"},{"slug":"privacy-audit","title":"privacy-audit","description":"Audits your app's Privacy Policy, ToS, Cookie Policy and DPA against its actual codebase. Scans your dependencies, DB schema, and API routes to find undisclosed data collection, missing subprocessors, and GDPR compliance gaps automatically.","developer":null,"category":"development","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/bellu/privacy-audit.git"},{"slug":"consistent-ui","title":"consistent-ui","description":"Enforce UI consistency across an entire codebase — detects drift in spacing, typography, colors, components, iconography, and interaction patterns across web, native mobile, and server-rendered templates. Generates a P0-P3 report and remediation plan.","developer":"Vadym Rusin","category":"development","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/thevrus/consistent-ui.git"},{"slug":"zero-trust-audit-team","title":"zero-trust-audit-team","description":"Eight specialized agents and seven slash commands transform your existing codebase into a fully tracked improvement pipeline.\n\nThe code auditor verifies one file at a time with explicit evidence—no fabrication, no vague claims. Findings persist across /clear in .claude/audit-state/.\n\nCommands: /audit:init, /audit:run, /audit:continue, /audit:triage, /audit:fix, /audit:status, /audit:summary.","developer":"bradselph","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/bradselph/zero-trust-audit-team.git"},{"slug":"ws","title":"ws","description":"ws is a working set manager for Claude Code. Use /ws:map to describe a feature and Claude automatically identifies relevant files across your codebase, adding them to a focused, navigable list. Use /ws:install to set up the ws CLI on any OS. Working sets are branch-scoped and persistent — switch git branches and your context switches with you. Built for AI-assisted coding workflows where you need to track a curated set of files rather than browse your entire project tree.","developer":"Nikita Filatov","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/n-filatov/ws.git"},{"slug":"workflow-toolkit","title":"workflow-toolkit","description":"Get up to speed in any codebase, any size. Non-opinionated workflow plugin with session journaling, local task tracking, GitHub issue sync, knowledge base generation, and lifecycle hooks. All backed by SQLite, all local.","developer":"Doug Silkstone","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/dougwithseismic/workflow-toolkit.git"},{"slug":"voltaire","title":"voltaire","description":"Revenue intelligence for SaaS paywall conversion. Voltaire connects Stripe data, installs behavioral tracking into the codebase, and runs three AI agents on every /voltaire: timing analysis, cohort comparison, and churn tracking to surface where conversion is being lost and what to fix.","developer":"Voltaire","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/voltairehq/voltaire-plugin.git"},{"slug":"viv","title":"viv","description":"Turn Claude into a Viv expert. Design, develop, and debug code and content for Viv, a system for building simulated worlds where storylines emerge from character activity.\n\nViv offers technical narrative designers a custom programming language affording rich specifications of character actions, as well as constructs that drive *story sifting*—the task of identifying emergent storylines in a given simulation instance, such as a videogame playthrough.\n\nThis plugin maintains a synced copy of the Viv codebase, and bundles special commands for efficiently navigating it, allowing Claude to search the full language reference, compiler source, runtime source, and other material anytime it needs to look something up.\n\nSkills include `/setup` for fully automated Viv installation and project setup, `/write` for authoring Viv code from a brief, `/fix` for diagnosing compiler and runtime errors, `/design` for worldbuilding and architecture planning, and `/build` for writing integration code.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"siftystudio/viv"},{"slug":"vitals","title":"vitals","description":"Codebase vital signs — hotspot detection, ROI-ranked diagnosis, co-change coupling, knowledge risk, and AI provenance tracking","developer":"Tejas Chopra","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/chopratejas/vitals.git"},{"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":"2026-11-11T12:00:00.266Z","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":"vibe-taker","title":"vibe-taker","description":"Move a feature between repos without copy-paste archaeology. vibe-taker captures a feature out of one codebase as a portable bundle — architecture sketch, contract surface, the AI prompts that built it, a verbatim source snapshot, and the gotchas — then plants it into another repo with stack-aware adaptation. It reads source autonomously and only asks you when the WHY can't be derived from the code; on plant it detects the target's stack and picks code-lift on a high match, spec-driven re-implementation on a low one, or declines a hard cross-language mismatch — always with a diff you confirm before anything is written. Three commands: capture, plant, list. Local-only by default; ~/.vibe-taker/library/ is the single source of truth.","developer":"626Labs LLC","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/estevanhernandez-stack-ed/vibe-taker.git"},{"slug":"vibe-doc","title":"vibe-doc","description":"Vibe Doc is an AI-powered documentation gap analyzer for any codebase. It scans your project's artifacts, classifies the project type (web app, API, data pipeline, Claude Code plugin, etc.), measures coverage against a tier-appropriate documentation matrix, and either generates the missing docs from your existing artifacts or hands you a ranked list of gaps to close. Five slash commands cover the loop: /vibe-doc:scan (analyze), /vibe-doc:generate (write missing docs), /vibe-doc:check (CI deployment-readiness gate), /vibe-doc:status (snapshot), and /vibe-doc:evolve (Level-3 self-improvement — the plugin reads its own session logs and proposes SKILL improvements). Honest about coverage: no cherry-picked denominators, no false negatives the matcher has learned to flag.","developer":"626Labs LLC","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/estevanhernandez-stack-ed/Vibe-Doc.git"},{"slug":"velt","title":"velt","description":"Add real-time collaboration to any React or Next.js app. AI-guided setup with codebase analysis, best-practice rules, and MCP-powered tooling for the Velt SDK. Includes commands for comments, presence, cursors, CRDT collaborative editing, and notifications.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/velt-js/velt-plugin.git"},{"slug":"uttero","title":"uttero","description":"Uttero is a voice channel that lets Claude Code take and make phone calls during a coding session. An incoming call arrives as a channel notification; Claude hears the caller's transcription, speaks back via TTS through the `reply` tool, and keeps editing your codebase between turns. Works like a live collaborator who happens to be on a phone line.\n\nTools exposed: reply (speak), call_user (outbound), end_call, list_calls.\n\nAudio, transcription, and TTS are handled by Uttero's hosted backend (api.uttero.dev). The plugin itself is ~500 lines of TypeScript that speaks MCP stdio and authenticated HTTPS. Credentials are stored locally at ~/.uttero/credentials.json (mode 600) and never shared with callers. The plugin deliberately omits `capabilities.experimental['claude/channel/permission']` so voice callers cannot approve Bash/Write/Edit tool use.","developer":"Uttero","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/utterodev/uttero-plugins.git"},{"slug":"understand-anything","title":"understand-anything","description":"Understand Anything is a Claude Code plugin that analyzes your project with a multi-agent pipeline, builds a knowledge graph of every file, function, class, and dependency, then gives you an interactive dashboard to explore it all visually. Stop reading code blind. Start seeing the big picture.","developer":"Egonex","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/Lum1104/Understand-Anything.git"},{"slug":"ultraship","title":"ultraship","description":"All-in-one builder toolkit for Claude Code. 22 automatic skills, 20 tools, 5 agents. Covers the full dev lifecycle — brainstorming, planning, TDD, code review, frontend design, SEO/GEO/AEO audits, Lighthouse performance, security hardening, and deployment. Skills activate automatically based on context. Run /ship to get a full ship-readiness scorecard.","developer":"Houseofmvps","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/Houseofmvps/ultraship.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":"2026-11-11T12:00:00.266Z","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":"tldiagram-create-diagram","title":"tldiagram-create-diagram","description":"Automatic creation of codebase diagrams for use in tldiagram.com","developer":"Mert Çıkla","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/Mertcikla/tld-cli.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":"2026-11-11T12:00:00.266Z","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":"tailwind-design-system","title":"tailwind-design-system","description":"Design system builder and refactorer for Tailwind CSS + Next.js projects. Audits existing styles, defines semantic color/typography tokens, extracts shared UI components, migrates codebases, and provides ongoing compliance review.","developer":"seungboshim","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/seungboshim/skills.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":"2026-11-11T12:00:00.266Z","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":"sync-docs","title":"sync-docs","description":"Detect outdated documentation by comparing docs against actual code state — broken references, version mismatches, stale code examples, and missing CHANGELOG entries. Documentation drifts from code silently: a function gets renamed, an import path changes, a version bumps, but the README and CHANGELOG still reference the old state. `/sync-docs` compares documentation files against the current codebase, finds the gaps, and auto-applies safe fixes (version updates, CHANGELOG entries) while flagging ambiguous cases (removed exports referenced in docs, code examples needing context) for manual review. Plug into /next-task and /prepare-delivery as the pre-ship docs gate.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/agent-sh/sync-docs.git"},{"slug":"superfast","title":"superfast","description":"You know that moment when you've finally convinced your coding agent to build exactly what you want, only for it to instantly get hopelessly lost hallucinating dependencies in a 5,000-line codebase?\n\nSuperfast fixes that. It starts by establishing your Context Memory. Before any brainstorming or planning occurs, it instantly triggers the FastMemory Build-Up Skill, recursively mapping your enterprise repository into a deterministic CBFDAE graph. Once your agent's cognitive map is established, it steps back and asks you what you're really trying to do.\n\nOnce it's teased a spec out of the conversation, it shows it to you in chunks short enough to actually read and digest. After you've signed off on the design, your agent puts together an implementation plan that's clear enough for an enthusiastic junior engineer with poor taste, no judgement, no project context, and an aversion to testing to follow. It emphasizes true red/green TDD, YAGNI (You Aren't Gonna Need It), and DRY.\n\nNext up, once you say \"go\", it launches a subagent-driven-development process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. It's not uncommon for Claude to be able to work autonomously for a couple hours at a time without deviating from the plan you put together.","developer":"Jesse Vincent","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/FastBuilderAI/superfast.git"},{"slug":"supalens","title":"supalens","description":"Connect Claude Code to SupaLens to instantly generate analytics dashboards from your codebase. Claude reads your models and schema, infers business KPIs, generates SQL, and registers live widgets to your SupaLens dashboard — no setup, no manual queries. Supports any Postgres-backed project.","developer":"Streamize LLC","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/Streamize-llc/supalens-plugin.git"},{"slug":"stackpilot","title":"stackpilot","description":"Sprint orchestration for Claude Code. Describe a feature, get production-ready code through an automated design→spec→plan→code→QA\npipeline. Drives Claude Code's native Agent tool for multi-agent execution with worktree isolation.\n\nIncludes 3 portable methodology skills usable standalone:\n• TDD Development — RED-GREEN-REFACTOR cycle with 4-phase root cause investigation\n• QA 12 Dimensions — two-stage code review + 12-dimension scenario test coverage\n• Architecture Review — codebase pattern analysis → decisive choice → implementation blueprint","developer":"9aoyang","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/9aoyang/stackpilot.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":"2026-11-11T12:00:00.266Z","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":"socraticode","title":"socraticode","description":"Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local Claude Plugin: managed indexing, hybrid semantic search, polyglot code dependency graphs, and DB/API/infra knowledge. Benchmark: 61% less tokens, 84% fewer calls, 37x faster than standard AI grep.","developer":"Giancarlo Erra","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/giancarloerra/SocratiCode.git"},{"slug":"slm-agent","title":"slm-agent","description":"SLM Agent scans your codebase for AI API calls and generates a structured migration plan showing exactly where you can swap frontier LLM calls (Opus) for Small Language Models API calls like Haiku or Sonnet.\n\nIt performs deep cross-file analysis: tracing prompts to their construction site, following callers across files, and classifying each call by what it actually does. Each finding includes a complexity score, confidence level, estimated savings, and for multi-task calls, a step-by-step decomposition. The output is a saved report.md in your project with a full API reference, so you can migrate.\n\nNo source code or codebase data is sent to any external server (except Claude) during analysis.","developer":"ScaleDown","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/scaledown-team/SLM_Agent.git"},{"slug":"skills-lab","title":"skills-lab","description":"skills-lab is a meta-skill plugin for engineers who build and maintain agent operating systems. It packages\nreusable, gated protocols for high-stakes operations on agent codebases — the kind of work where a single\nsloppy edit corrupts a whole skill graph. The first skill, skill-transplant, grafts a feature from a source\nrepo into a target repo via a 5-phase gated protocol (survey → plan → graft → verify → integrate), with\nexplicit checkpoints so a human can intercept before any irreversible step.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/SujinHwang27/agent-os-lab.git"},{"slug":"shazam","title":"shazam","description":"A skill-based workflow plugin for planning, architecture,    and bug triage. 18 skills covering the full development cycle: write PRDs, break them into plans and issues, improve    codebase architecture, triage bugs, and more. Just shout out SHAZAM! for a navigation guide that suggests what to do    next based on your current context. Soft suggestions, no   forced workflows — you stay in control.","developer":"Danny Huang","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/qhuang20/shazam.git"},{"slug":"sextant","title":"sextant","description":"Sextant provides systematic, tiered workflows for common coding tasks — bug fixes, new features, refactoring, code review, test writing, and requirements refinement. Like a nautical sextant that helps navigators fix their exact position before charting a course, it helps Claude understand where it is in the codebase before making changes.","developer":"hellotern","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/hellotern/Sextant.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":"2026-11-11T12:00:00.266Z","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":"searchfit-seo--community","title":"searchfit-seo","description":"Free AI-powered SEO toolkit — audit websites, plan content strategy, optimize pages, generate schema markup, cluster keywords, and track AI visibility. Works with any website or codebase.","developer":"SearchFit.ai","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community","Knowledge Work"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/searchfit/searchfit-seo.git"},{"slug":"searchfit","title":"searchfit","description":"Free AI-powered SEO toolkit — audit websites, plan content strategy, optimize pages, generate schema markup, cluster keywords, and track AI visibility. Includes 11 skills, 3 autonomous agents, and 6 slash commands. Works with any website or codebase.","developer":"SearchFit.ai","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-11T12:00:00.266Z","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/searchfit/searchfit-seo.git"}],"total":125,"page":1,"per_page":36,"observed_at":"2026-11-11T12:00:00.266Z","source_counts":{"web":530,"demo":12,"skills":5,"official":317,"community":2283,"knowledge-work":123}}