smart-blog-skills
claudeAnti-hallucination blog engine with triple-layer verification
35 skills · 8 agents · hooks
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Anti-hallucination blog engine with triple-layer verification
35 skills · 8 agents · hooks
AI Pilot workflow: APEX methodology (auto-detects Laravel/Next.js/React/Swift), sniper (7-phase code quality + DRY detection), research-expert, explore-codebase
18 skills · 12 commands · 9 agents · hooks
Full dev lifecycle: idea → prompt → plan → run → site audit → deep research. Multi-agent task executor with bd integration.
6 skills · 13 commands · 16 agents · hooks
34 открытых AI-скилла для малого бизнеса РФ: налоги УСН, деньги, проверка контрагента по ИНН. Числа считаются кодом, данные из реальных реестров. | 34 open AI skills for Russian small business: taxes, cash flow, counterparty checks. The numbers are computed in code, not guessed.
34 skills
SEO/GEO 2026 plugin: technical SEO, schema markup, E-E-A-T, AI Overviews/ChatGPT/Perplexity optimization, local SEO, sitemaps, hreflang, internal linking, semantic clustering, search experience. Local-first, zero third-party APIs.
21 skills · 9 agents · hooks
The engine-agnostic foundation of the gamestack framework — the design/discipline brain, organized into four tiers: universal craft (game-design fundamentals, game feel & juice, level design, onboarding, UI/UX, difficulty & balancing, pacing, art direction), technical craft (3D graphics & rendering, shaders & VFX, animation systems, procedural geometry), genre lenses (open-world, RPG, combat, narrative, worldbuilding, permadeath), and technique modules (procgen, AI-authored coherence, systemic/emergent), plus the headless concept→generate→self-review process pipeline, including the iteration-loop reference→diff→prioritize→generate→verify procedure for visual/systemic/narrative fidelity. Pairs with the curated engine packs in the gamestack marketplace (Godot, Unity, Unreal): design here, implement there.
26 skills
Expert Laravel 13 + PHP 8.3+ with SOLID principles, first-class PHP Attributes, Laravel AI SDK, JSON:API Resources, native vector search (pgvector), Eloquent, Livewire, queues with routing, and comprehensive documentation
23 skills · 1 agent · hooks
QA testing pipeline with 5 personas (smoke, UX, adversarial, performance, mobile) — generate workflows, convert to Playwright tests, run interactively or in CI. Quantified UX scoring with binary scorecards, Next.js performance profiling, and mobile UX auditing against iOS HIG and Material Design 3.
14 skills · 2 commands · 7 agents
Work with Postman from your agent: bootstrap a repo's Postman setup, mock an API before it's implemented, run collection and governance checks in CI, monitor a live endpoint, deploy and debug Postman Flows, and publish generated API documentation.
21 skills · hooks · app connector
Microsoft 365, Intune, and Entra admin skills with Greybeard MCP server wiring.
18 skills · 2 MCP servers
Persistent memory for AI coding agents via the memini memory service. 7 hooks, MCP tools, and skills that capture tool usage and inject prior context at session start.
10 skills · 9 commands · 1 MCP server
khive for AI agents — knowledge graph, GTD, memory, inter-agent comm, scheduling, and domain knowledge over one MCP server. One pattern skill per pack, plus the kg stewardship agents.
11 skills · 6 agents
Seventeen skills that teach an AI coding agent to use the Azure SQL Database container correctly: start the engine, connect, migrate schemas, import data, scaffold apps, build local RAG, wire CI, run as a sidecar, go local-to-cloud, build no-code REST/GraphQL APIs with Data API Builder, build serverless and event-driven Azure Functions, seed realistic test data, integration-test with Testcontainers, add connection pooling and retry, connect securely with a least-privilege user and the right auth per environment, answer FAQs, and report issues.
17 skills
FHIR AI agent guardrails with 29 MCP tools including Compiled Truth (current state + evidence timeline) and Wearables (Garmin, Oura, Polar, Suunto, Whoop, Fitbit, Strava via Open Wearables). PHI redaction on every read, step-up auth for writes, immutable audit, tenant isolation, Curatr data quality, Fasten Connect EHR ingestion. FHIR R4 US Core v9 + R6 ballot3.
14 skills · 2 MCP servers
The Upstash MCP server plus agent skills for every Upstash SDK and CLI — Redis, QStash, Workflow, Box, Blob, Ratelimit, Vector, and Search.
15 skills · 1 MCP server
Multi-Agent Driven Development for Claude Code (formerly Claude Memory Kit): you talk to one main agent, it orchestrates three full sessions and their subagents through brief, report and acceptance files; memory as plain dated files in your repository (nothing becomes a rule without your yes) lets any session be cleared without losing the work; guards for git, secrets and tests.
10 skills · 4 agents · hooks
Project-scoped research vault with ingestion, compilation, grounded queries, optional academic MCP sources, and Obsidian-compatible Markdown.
1 skill · 13 commands
Spec-driven development: from discovery to shipping. Analyze codebases, generate grounded specs, create self-contained prompt packs, and audit implementations.
10 skills · 3 agents
AI-powered pitch analysis, fundraising strategy, and investor relations for startup founders -- a Claude Code plugin grounded in first principles from Sequoia, a16z, Benchmark, and YC
2 skills · 6 commands · 5 agents
Guided Kubernetes operator creator with CRD, webhook, and Tilt fast dev loop.
4 skills · 7 commands · hooks
ego lite skills: pinterest-download, instagram-saved-download, wechat-channels-video, wechat-article-ego, kuaishou-video, bilibili-video, youtube-video, douyin-video, teambition-ego, x-post, and xiaohongshu-ego. Requires ego-browser.
12 skills
Claude Code skills for Unity MCP Server. Provides workflow-oriented guidance for C# editing, Scene/GameObject management, PlayMode testing, and Asset management using 108+ Unity automation tools.
8 skills · 2 commands · 1 agent
Go TUI kanban board backed by beads-lite — hooks, agents, and lifecycle management for Claude Code sessions
9 skills · 1 command · hooks
Skills that guide an AI assistant through designing autonomous experiments with gpCAM — kernels, acquisition, prior mean, noise, cost, gp2Scale, and multi-task GPs.
11 skills
Generate sprites, cohesive UI kits, textures, and short animations in Claude with SpriteCook's guided game-art workflows.
10 skills · 1 MCP server
Agentic AI plugin that transforms a dashboard request into a Tableau specification — with interactive HTML mock, implementation blueprint, and experimental .twbx generation. Works with Claude Code, Cursor, and other AI coding tools
10 skills
Multi-platform content creation system for Chinese content - from research and image sourcing to writing, humanizing, and platform-specific formatting for Zhihu, Xiaohongshu, and WeChat.
9 skills
LinkedIn prospect intelligence inside Claude. Automates the research behind outreach, not the sending: classifies what people and companies post about, mines comment threads for warm leads, surfaces uncommon commonalities, and learns which hooks earn replies. 18 MCP tools plus 8 skills, all local.
8 skills · 1 MCP server
Turn screen recordings into ready-to-file bug drafts, specs, backlogs and meeting actions — local Whisper transcript + keyframes + OCR + wall-clock evidence via the talkthrough MCP server.
1 skill · 6 commands · 1 agent · 1 MCP server
Blocks name-based kills, port collisions, whole-disk and parallel scans, long foreground sleeps, and git commands that would move, sweep up or delete another session's tree; budgets RAM for heavy commands; stops what exited sessions leave running; and replays your past transcripts with bulkhead scan.
1 skill · 6 commands · hooks