{"data":[{"slug":"meeting-bots","title":"meeting-bots","description":"A panel of AI personas that debate your decisions inside Claude Code. 3 to 10 participants across 5 teams (dev, design, product, business, life), 3 rounds of parallel debate, and a user-centric synthesis from the Boss. The full debate is recorded to a markdown file while the console stays clean.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/karl-cta/meeting-bots.git"},{"slug":"mcp-server-guide","title":"mcp-server-guide","description":"Build apps, clone websites, and implement Figma designs through Anima Playground. Describe what you want, paste a website URL, or drop in a Figma link. Anima handles design, code generation, database, and hosting. Publish to a live URL. Crate in parallel variant creation for rapid prototyping.","developer":"Anima","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/AnimaApp/mcp-server-guide.git"},{"slug":"magician","title":"magician","description":"Comprehensive software development lifecycle plugin that takes task from the idea to merged PR autonomously. Core capabilities:\n\n1. Dynamic Project Inspector\n\nOn every session start, it scans your project files (package.json, go.mod, Cargo.toml, pom.xml, etc.) and auto-assembles targeted knowledge (\"lore\") for every detected technology — no manual stack selection needed. Polyglot stacks get full coverage automatically.\n\n2. Full Autonomous SDLC (/manifest)\n\nOne command drives the entire flow with only 4 human approval gates:\n\n* /conjure — design dialogue (with an ability to strictly use design) → approved spec\n* /blueprint — implementation plan with parallelism map\n* /portal — git worktree isolation\n* /orchestrate + /ward — parallel agents with TDD\n* /certify — tests + types + linter + browser verification\n* /scrutinize → /absorb — multi-agent code review + integration\n* /seal — PR creation, loops until merged\n\n3. Self-Learning\n\nA Stop hook (chronicle-stop.sh) captures git diffs at session end, writes entries to a chronicle, and detects repeated patterns. After 3 occurrences, it offers to codify the pattern as a reusable skill via /inscribe.\n\n4. Team Memory Workspace\n\n.workspace/shared/ (git-committed, team-visible) holds context, roadmap, specs, and post-mortems. .workspace/local/ (gitignored) holds personal prefs and session state.\n\n5. Security Infrastructure\n\n* Hard deny rules in settings.json blocking pipe-to-shell, eval, credential access\n* sentinel-guard.sh PreToolUse hook scanning every Bash command for injection patterns\n* magician-scan standalone CLI for CI pipelines\n* /sentinel skill for full OWASP Top 10 + credential + injection audits\n\nSkill Set (20 skills)\n\nCovers: debugging (/unravel), performance (/accelerate), incident analysis (/autopsy), CI/CD (/deploy), security (/sentinel), and meta-tooling (/inscribe).","developer":"Alexander Tyagunov","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/Alexander-Tyagunov/magician.git"},{"slug":"local-seo-audit-system","title":"local-seo-audit-system","description":"Complete 21-phase local business SEO audit system for Claude Code. Covers technical SEO, on-page, content strategy, local SEO & GBP, AI visibility (ChatGPT, Perplexity, Gemini, AI Overviews), competitor analysis, backlinks, reputation, and more.\n\nIncludes two proprietary scoring frameworks:\n• LOCAL-IMPACT — 60-item local presence assessment across 8 dimensions (0–100)\n• SERP-TRUST — 50-item search trust assessment across 5 dimensions (0–100)\n• SEO Health Index — weighted combination of both frameworks\n\nOutputs a professional PDF report with SVG score gauges, color-coded issue cards, competitor comparison charts, and 30/90/180/365-day action roadmaps. Zero external dependencies — works with WebSearch and WebFetch out of the box. Optional MCP integrations for Google Search Console, GA4, Google Business Profile, PageSpeed Insights, and SimilarWeb.\n\n27 skills, 40 slash commands, 6 specialized parallel sub-agents.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/mshahiddigital/local-seo-audit.git"},{"slug":"larch","title":"larch","description":"Larch is a multi-agent workflow automation plugin for Claude Code that orchestrates the full software development lifecycle — from design through merge — using collaborative AI agents. It provides six slash commands (/design, /implement, /review, /research, /loop-review, /alias) that coordinate up to 5 parallel agents (Claude subagents + Codex + Cursor) with a voting-based review system to adjudicate findings. Key features include: diverge-then-converge design planning where independent agents propose architectures before anchoring bias can set in; multi-round code review with a 3-agent voting panel (YES/NO/EXONERATE) that accepts or rejects each finding; end-to-end automation from feature design through PR creation, CI monitoring, Slack announcements, and merge; a reviewer competition scoring system that tracks finding quality; and systematic whole-repo review via partitioned slices. External tools (Codex, Cursor, Slack) are optional — the plugin degrades gracefully when they're unavailable.","developer":"Sergey Zhupanov","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/zhupanov/larch.git"},{"slug":"ido4specs","title":"ido4specs","description":"ido4specs is the bridge between a strategic spec and GitHub issues. It analyzes your codebase, decomposes capabilities into implementation tasks with effort, risk, type, and dependency metadata, and produces a structurally-validated technical spec any downstream tool can consume.\n\nKey features:\n- Code-grounded decomposition - parallel Explore subagents ground every task in concrete files, services, and patterns from your actual codebase (not fabricated from the spec)\n- Structured output enforced by a bundled zero-dependency parser - every task carries effort (S/M/L/XL), risk (low → critical), type (feature/infrastructure), AI-suitability (full/assisted/pair/human), and dependency graph\n- Two-layer validation - deterministic structural parser + independent qualitative review before handoff\n\nBuilt for tech leads, staff engineers, and founder-engineers who want to skip the manual decomposition tax.","developer":"Bogdan Coman","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/ido4-dev/ido4specs.git"},{"slug":"ido4shape","title":"ido4shape","description":"A specification discovery plugin for Cowork and Claude Code. Helps product managers, founders, and tech leads figure out what to build before writing a single line of code.\n\nUnlike tools that assume you already know what to build, ido4shape starts at \"tell me about your problem\" and guides you through creative, non-linear conversation — reading your documents, asking the questions that matter, surfacing risks you hadn't considered, and tracking understanding across multiple sessions via a persistent knowledge canvas.\n\nWhen understanding is deep enough, it synthesizes a structured strategic specification with capability groups, dependencies, priorities, risk assessments, and verifiable success conditions. Independent parallel reviewers (technical feasibility, scope alignment, dependency audit, format quality) catch issues before the spec is finalized.\n\nThe output is a standalone markdown document you can hand to your team, feed to any AI coding tool, or use as a project brief. For teams using ido4 MCP, the strategic spec can be automatically decomposed into implementation-ready technical tasks.\n\n10 skills (6 user-invocable, 4 auto-triggered), 5 sub-agents, deterministic spec validation, multi-session persistence, zero external dependencies.","developer":"Bogdan Coman","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/ido4-dev/ido4shape.git"},{"slug":"hyperflow","title":"hyperflow","description":"Hyperflow turns a Claude Code session into a structured engineering workflow through eight chained slash commands. /hyperflow:spec runs a guided design session with structured questions\n  and section-by-section approval. /hyperflow:scope decomposes the design into a batched task file. /hyperflow:dispatch runs parallel persona-stitched workers under thinking-tier review at\n   every step. Multi-level code review (L1–L5), 15 composable personas covering security, frontend, backend, database, and more, six adaptive flow profiles tuned to task complexity.\n  Project memory persists across sessions so context, decisions, and learned conventions carry forward.","developer":"Mohammed Abdelhady","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/Mohammed-Abdelhady/hyperflow.git"},{"slug":"hive","title":"hive","description":"Bio-inspired swarm orchestrator for Claude Code. Breaks tasks into parallel subtasks, coordinates agents through stigmergy, learns across sessions with pheromone scoring, and scales concurrency adaptively. 16 mechanisms from ant colonies, honeybee swarms, and AI research.","developer":"Jack Nowlan","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/CipherandRow/claude-hive-plugin.git"},{"slug":"harness-evolver","title":"harness-evolver","description":"Autonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically. Includes evaluator agent (LLM-as-judge via langsmith-cli), critic, architect, and testgen agents. No external API keys needed beyond LangSmith.","developer":"Raphael Valdetaro","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/raphaelchristi/harness-evolver.git"},{"slug":"harness-designing-plugin","title":"harness-designing-plugin","description":"Harness Designing Plugin helps design teams turn their scattered AI setup — Notion prompts, Figma comments, AGENTS.md rules, chat histories — into a five-layer design harness that compounds across sessions and rotations.\n\nFour skills walk you through the assembly:\n• /hd:learn — Q&A about the five-layer concept (Context Engineering, Skill Curation, Workflow Orchestration, Rubric Setting, Knowledge Compounding)\n• /hd:setup — detects existing harness artifacts, pre-analyzes all five layers in parallel (5× harness-auditor + rubric-recommender), then walks you through link / critique / scaffold / skip per layer\n• /hd:maintain — captures lessons and promotes them to team rules in AGENTS.md with SHA-256 plan-hash proof-of-consent\n• /hd:review — audits harness health in a 2-batch parallel dispatch (5 layer-specialist agents + 2–3 context agents); critiques harness artifacts against quality rubrics\n\nShips 9 sub-agents and 14 starter rubrics (distilled from pbakaus/impeccable, Nielsen's 10 heuristics, Material 3, Fluent 2). Each rubric carries a Scope & Grounding section with personas, user stories, realistic scenarios, and anti-scenarios. Validated across a six-repo pilot matrix.\n\nThis plug-in is the companion toolkit to Bill Guo's Substack series on design harnessing. Structural inspiration: EveryInc/compound-engineering-plugin.","developer":"Bill Guo","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/BilLogic/harness-designing-plugin.git"},{"slug":"groundwork","title":"groundwork","description":"Groundwork is a structured development workflow plugin that guides you from product requirements through architecture, implementation, and validation. It provides 28 skills and 22 commands covering product design (EARS requirements), architecture decision-making, test-driven development, systematic debugging, and multi-agent validation. Features include worktree-isolated task execution, parallel adversarial debugging with agent swarms, 9-agent validation loops, spec synchronization, and monorepo support. Groundwork encodes development best practices into guided workflows so nothing gets skipped.","developer":"Groundwork Contributors","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/etr/groundwork.git"},{"slug":"grill","title":"grill","description":"Grill runs six specialized agents (recon, architecture, error handling, security, testing, edge cases) in parallel against a codebase, then synthesizes their findings into one report with severity tags, file:line evidence, proposed changes, effort estimates, and explicit tradeoffs. Five review styles let you tune intensity from quick scan to Paranoid Mode. Eight optional add-on pressure tests target specific failure modes (concurrency, observability, dependency hygiene, etc.). Zero-findings is reported explicitly as `[GOOD]` — no padding with manufactured issues.","developer":"xiaolai","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/xiaolai/grill-for-claude.git"},{"slug":"governance","title":"governance","description":"Engineering standards and code governance enforcement with parallel agent execution for code reviews, commits, and standards audits.","developer":"Will Smith","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/wrsmith108/governance-claude-skill.git"},{"slug":"gia-prospecting-engine","title":"gia-prospecting-engine","description":"AI-powered lead generation and outreach automation for Claude Code and Cowork. Find companies hiring in your target market, research prospects, and draft personalized cold emails — all in parallel. Powered by GIA governance.","developer":"Advanced Consulting Experts, LLC","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/knowledgepa3/gia-prospecting-engine.git"},{"slug":"gia-chief-of-staff","title":"gia-chief-of-staff","description":"AI executive operations assistant for Claude Code and Cowork. One command scans your inbox, surfaces priority items, identifies follow-ups, and drafts responses — all in parallel. Daily briefings, inbox triage, meeting prep, and pipeline tracking. Powered by GIA governance.","developer":"Advanced Consulting Experts, LLC","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/knowledgepa3/gia-chief-of-staff.git"},{"slug":"founderfocus","title":"founderfocus","description":"Behavioral operating system for solo founders managing parallel workstreams. Enforces execution discipline, captures ideas without session derailment, and ensures seamless session recovery.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/MartelGPT10/founderfocus.git"},{"slug":"forge-skills--community","title":"forge-skills","description":"Agentic Engineering toolkit with 12 structured workflow skills, 5 specialist agent personas, and 7 slash commands. Covers the full development lifecycle from idea to production. Each pipeline stage produces .forge/ artifacts that the next stage consume; enabling parallel implementation with interface contracts. Inspired by Andrej Karpathy's Agentic Engineering concept.","developer":"Sahil Aneja","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/aneja5/forge-skills.git"},{"slug":"flow","title":"flow","description":"Flow turns Claude into a project partner who manages your backlog. Say \"park this for later,\" and it queues the idea. Say \"what's next?\" and it finds the highest-priority ready item and offers to start, handling the bookkeeping so you stay in flow.\n\nIt works as a lightweight scrum board with three ways to interact: talk to Claude conversationally, drag cards on the built-in Kanban board, or run multiple agents in parallel, each with filtered views. All three read and write the same backlog.json, no sync step, no drift.\n\nLanes are fully configurable. Start with the default agile flow (Backlog → Refined → Ready → In Progress → Code Review → Done) or define your own columns and gate rules. The board, the API, and the agent all enforce them consistently.\n\nConversational management: Add, reorder, refine, and complete items by talking naturally; no commands to memorize.\nBuilt-in Kanban board: Drag-and-drop web UI that syncs with the agent in real time; launch with one command.\nMulti-agent support: Leader agents assign work, worker agents get filtered views of only their items, plus unassigned ready work.\nAgent-initiated items: Claude adds bugs, tech debt, and follow-ups he discovers while working, linking them back to the source task.\nLinked items: Connect related items with typed links (blocks, follow-up, discovered-during, related) and a reason.\nConfigurable lanes: Define your own workflow columns and gate rules; the board, REST API, and agent all enforce them at every layer.\nThreaded refinement: Structured Q&A threads on items keep discussions organized; tag @Agent for async responses\nConcurrency safe: Optimistic versioning and atomic writes prevent data loss when board and agent write simultaneously","developer":"Prajyot Bankade","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/prajyotbankade/Flow.git"},{"slug":"envoy","title":"envoy","description":"Spawn Claude Code agents that operate inside any local or remote project directory. Each agent runs as its own Claude CLI instance rooted in the target folder, with full access to that project's codebase and context. Supports parallel dispatch across multiple projects, SSH remote execution, model selection, and configurable timeouts.","developer":"Michael Slain","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/michaelslain/claude-envoy.git"},{"slug":"enhance","title":"enhance","description":"Master enhancement orchestrator: 7 specialized analyzers run in parallel and produce a unified report with certainty-graded findings. `/enhance:agent` analyzes agent frontmatter and tool restrictions; `/enhance:prompt` general prompt patterns; `/enhance:docs` RAG-readiness; `/enhance:plugin` MCP/security patterns; `/enhance:claudemd` project-memory files; `/enhance:hooks` hook safety; `/enhance:skills` SKILL.md trigger quality. HIGH-certainty issues are auto-fixable with `--fix`. Per-analyzer model selection (Opus for quality-critical analysis, Sonnet for pattern-matching) keeps token costs predictable. Designed to plug into /next-task and /prepare-delivery as a pre-ship gate.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/enhance.git"},{"slug":"eight-eyes","title":"eight-eyes","description":"Multi-agent code review with 8 hook-enforced roles. Each role targets a different failure surface — the skeptic reviews blind without the implementer's narrative, the security auditor can only run approved scan commands, the test writer cannot touch source code, and the implementer cannot run Bash. Scope boundaries are enforced through deterministic Python hooks at the PreToolUse layer, not through prompt instructions.\n\nThe 8 roles: implementer (scoped writes, no Bash), test-writer (test directories only), skeptic (blind read-only review), security auditor (read-only + approved scan commands), performance profiler (benchmarks in isolated worktree), accessibility checker (a11y tools + WCAG 2.1 checks), docs writer (doc paths only), and verifier (approved verification commands only).\n\nFeatures include parallel audit phase (4 review agents run concurrently), TDD mode (hook-level test-first enforcement), custom roles via manifest (--custom-role), REVIEW.md injection for project-specific review criteria, mission timeout and failure tracking.\n\n96 tests. 100% Python stdlib. Zero external dependencies.","developer":"AgentBuildersApp","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/AgentBuildersApp/eight-eyes.git"},{"slug":"e2e-runner","title":"e2e-runner","description":"JSON-driven E2E browser test runner — no JavaScript test files needed. Parallel execution against a Chrome pool, 28+ built-in actions, visual verification, network debugging, flaky test detection, reusable modules, and a real-time dashboard. Includes 3 specialized agents, 4 slash commands, and 16 MCP tools.","developer":"Matware","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/fastslack/mtw-e2e-runner.git"},{"slug":"dreamforge-audit","title":"dreamforge-audit","description":"Comprehensive application auditor — runs parallel agents to check code quality, workflow gaps, security (OWASP), help docs, and performance. Produces timestamped reports with severity ratings, fix instructions, and effort estimates. Works on any project.","developer":"Emile du Toit","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/brainit-consulting/DreamForgeSoftwareAgentSkills.git"},{"slug":"dominion-flow","title":"dominion-flow","description":"Research-backed orchestration for Claude Code. Structured workflow from idea\n\n    to production with parallel execution, session memory, 70-point validation, autonomous\n    mode, and adversarial review. 49 commands, 51 agents across 7 departments.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/ThierryN/fire-flow.git"},{"slug":"distill","title":"distill","description":"distill analyzes your codebase and generates structured context files in .claude/docs/. Instead of Claude reading source files to orient itself every session, it reads concise, pre-built docs on demand — testing.md when working on tests, api.md when working on endpoints, nothing when the task doesn't need it. Token cost becomes proportional to task relevance, not project size.\n\nSupports incremental updates (--update only regenerates stale docs), depth profiles (--lean for 30-line summaries, --deep for comprehensive reference), parallel generation for large doc sets, monorepo detection, team configuration via .distill.yml, and a pre-push hook that warns when docs drift.","developer":"Utkarsh Jain","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/UtkarshJain98/distill.git"},{"slug":"dataslayer-marketing-skills","title":"dataslayer-marketing-skills","description":"Marketing analysis suite with 7 skills and 4 parallel agents — audit paid campaigns, find SEO opportunities, detect churn signals, and generate branded PDF reports. Powered by a tested analysis engine (ds_utils.py, 113 functions). Works automatically with Dataslayer MCP or manually with CSV/JSON data.","developer":"Dataslayer S.L.","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/Dataslayer-AI/Marketing-skills.git"},{"slug":"csitrep-generator","title":"csitrep-generator","description":"Multi-agent Situation Report (SitRep) generator for any project type. Drops 25 specialist AI agents across 5 domains to read your project documents in parallel and synthesizes findings into a structured status report — with critical issues, watch items, and recommended actions classified by urgency. Supports six project types out of the box: Construction (schedule, cost, safety, contracts, site), Software/IT (sprint, budget, quality, blockers, infra), Development Programs (workplan, budget/grants, M&E, stakeholders, field), Product/Manufacturing (timeline, cost, quality, supply chain, ops), Consulting (deliverables, billing, client satisfaction, resources, risks), and Custom (define your own 5 domains). Optional Slack delivery, interactive HTML dashboard, change-tracking across reports, and team-setup automation for recurring delivery.","developer":"Bruno Chikeka","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/chiKeka/csitrep-generator.git"},{"slug":"codesmith","title":"codesmith","description":"Codesmith is a Claude Code plugin that enforces the full dev lifecycle: spec refinement → TDD → implementation → parallel multi-agent review → clean PR. Branch management.\nAll you need to use claude like a senior engineer.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/nexteralabs/ne-claude-plugins.git"},{"slug":"claude-train-prep","title":"claude-train-prep","description":"Claude Code plugin: AI consulting training material workflow (Word report + HTML slides) with multi-agent parallelism","developer":"leeon","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/gzleeon/claude-train-prep.git"},{"slug":"claude-seo","title":"claude-seo","description":"Comprehensive SEO analysis plugin for Claude Code. Performs full site audits with 11 parallel subagents and 0-100 health scoring across technical SEO (crawlability, indexability, Core Web Vitals, security), content quality (E-E-A-T framework), schema markup (JSON-LD detection, validation, generation), image optimization, XML sitemap\nanalysis, AI search optimization (GEO for AI Overviews, ChatGPT, Perplexity), local SEO  (GBP, NAP, citations, reviews, map pack), maps intelligence (geo-grid ranking, competitor radius), hreflang/i18n, programmatic SEO, and strategic planning. 17 skills,  11 agents. Auto-detects industry type (SaaS, e-commerce, local, publisher, agency). Optional DataForSEO MCP extension for live SERP and keyword data.","developer":"AgriciDaniel","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/AgriciDaniel/claude-seo.git"},{"slug":"claude-ops","title":"claude-ops","description":"Business operations command center for Claude Code. One command (/ops-go) gives a complete morning briefing: infrastructure health, CI status, unified inbox across WhatsApp/Slack/Email/Telegram, open PRs, Linear sprint state, and revenue snapshot. Includes autonomous PR merge pipeline (/ops:merge), production incident dashboard, cross-platform issue triage, and YOLO mode where 4 parallel AI agents analyze and run your business operations. 13 skills, 9 specialized agents, zero-config setup wizard.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/Lifecycle-Innovations-Limited/claude-ops.git"},{"slug":"claude-deep-review","title":"claude-deep-review","description":"A research-backed code review plugin for Claude Code that orchestrates parallel concern-specialized agents, cross-validates findings with deterministic verification, and produces unified review reports.","developer":"Lee Hopper","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/liatrio-labs/claude-deep-review.git"},{"slug":"claude-code-tab-title","title":"claude-code-tab-title","description":"Terminal tab and window titles that show what each Claude Code session is working on, with a busy/idle marker. When you run multiple claude sessions in parallel, every tab title normally collapses to the binary name, so you can't tell which session is doing what. This plugin renames each tab to \"* <topic>\" while Claude is working and \"· <topic>\" when it's idle. The topic is auto-extracted from the first prompt of the session and stays sticky until the session ends. Works in VS Code's integrated terminal, iTerm2, Terminal.app, and any terminal that honors standard OSC title sequences. macOS only. Hooks into UserPromptSubmit, Stop, and SessionStart with no external dependencies.","developer":"franzvill","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/franzvill/claude-code-tab-title.git"},{"slug":"claude-code-survival-kit","title":"claude-code-survival-kit","description":"10 slash commands and 3 agent definitions distilled from 6 months of daily Claude Code use. Not a framework -- just the patterns that survived: multi-agent build pipelines, parallel task dispatch, security audits, session handoffs, and more.","developer":"Rob Spence","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/rjspence3/claude-code-toolkit.git"},{"slug":"cc-orchestrador-subagents","title":"cc-orchestrador-subagents","description":"O cc-orchestrador-subagents transforma o Claude Code em um gerente técnico de execução, não em \"mais um agente que programa\". A skill assume que toda mudança relevante de software passa por:\n\nespecificação clara (via OpenSpec);\nplano técnico feito pelo próprio orquestrador antes de codar;\nrevisão crítica do plano por outro modelo;\ndecomposição em tasks com contratos API/UI antes do paralelismo;\nexecução paralela de duplas back-end/front-end (Codex + Gemini) em background;\nmonitoramento sem polling contínuo, com check-ins leves para tasks lentas, integração e revisão pós-implementação;\ncontexto consolidado de todos os subagentes executados;\nrelatório final em Markdown com instruções de negócio para o usuário.\nO orquestrador (Claude Sonnet 4.6 Medium) coordena o fluxo, mas não executa subagentes Claude Code. As únicas delegações do workflow são para Codex e Gemini via plugins:\n\nPapel\tModelo\tSubagente\nOrquestrador/planejador/finalizador\tClaude Sonnet 4.6 Medium\t—\nRevisor de plano\tCodex gpt-5.5 High\tcodex:codex-rescue\nExecutor back-end\tCodex gpt-5.4 Medium\tcodex:codex-rescue\nExecutor front-end\tGemini 3 ou Gemini 3 Flash\tcc-gemini-plugin:gemini-agent\nReview pós-implementação\tCodex gpt-5.5 High\tcodex:codex-rescue\nO fluxo completo está descrito em skills/orchestrator-multi-agent-development/SKILL.md.","developer":"allanharlen","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T12:00:01.430Z","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/AllanHarlen/cc-orchestrador-subagents.git"}],"total":82,"page":2,"per_page":36,"observed_at":"2026-11-07T12:00:01.430Z","source_counts":{"web":529,"demo":12,"skills":5,"official":317,"community":2283,"knowledge-work":123}}