Browse the marketplace
Filter by type, price, delivery, and category. Every listing is security-reviewed.
PilotStack
Your agent flies the app — you stay in the cockpit. PilotStack is an MCP server that drives iOS, Android, and web side by side: cheap semantic UI context, deep Flutter introspection, and a human approve/deny gate on every action.
Grill With Docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Grill With Docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Access Control
Detect missing or incorrect access control — missing modifiers, wrong role checks, privileged function exposure, public initializers, and role-escalation paths. Activate on any function that mutates state, transfers funds, mints tokens, sets admin parameters, upgrades implementations, or pauses/unpauses.
Flutter Build Responsive Layout
Build adaptive layouts using LayoutBuilder, MediaQuery, or Expanded/Flexible widgets to ensure the UI looks elegant across all mobile, tablet, and desktop form factors.
Flutter Animations
>-
Flutter Adaptive Ui
Build, fix, review, and validate adaptive or responsive Flutter UIs for mobile, tablet, desktop, web, large screens, foldables, and mixed input devices. Use when creating breakpoint-driven layouts, responsive navigation, adaptive dialogs/lists/grids, keyboard/mouse/touch behavior, window-size decisions with MediaQuery or LayoutBuilder, or Capability and Policy patterns for platform-specific behav…
Grill Me
A relentless interview that sharpens a plan or design before any work starts — one sharp question at a time, often 40–50 deep, until you (and Claude) actually know what you want.
Lex
Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.
Bluebook Review
Review and correct legal citations in Microsoft Word DOCX manuscripts using the current Bluebook Style — Epps Version guide and CSL implementation from danepps/bluebook. Use for law-review footnotes, citation audits, first and short forms, Id. and supra usage, pincites, source-type formatting, signals, parentheticals, typography, Zotero citation fields, and delivery of a reviewed or redlined Word…
Lawreview Research
Search and inspect an authorized OCR-backed law-review corpus stored in a compatible SQLite database. Use for passage retrieval, citation lookup, context expansion, document inspection, journal filtering, corpus statistics, and retrieval evaluation with the bundled lawcorpus CLI or MCP server. Treat OCR text and inferred metadata as provisional, and never assume the corpus is complete or current.
Legal Bibliography
Research, rank, verify, and format authoritative legal sources with the BBGpt bibliography service. Use for legal literature reviews, source collection, Bluebook-ready bibliographies, law review articles, treatises, books, working papers, cases, DOI and publication-metadata checks, citation cleanup, or finding the leading authorities on a legal doctrine. Do not treat search or LLM rankings as leg…
Inject Word Cross References
Inject, repair, inspect, and differentially validate Microsoft Word cross-references directly in DOCX packages while preserving native Word behavior, formatting, bookmarks, cached results, and untouched package parts. Use for Word footnote or endnote cross-references, NOTEREF and REF fields, "supra note" citations, heading/bookmark references, stale hard-coded note numbers, cross-reference renumb…
Readme
Create, redesign, audit, or update a repository README.md by inspecting the actual project; write accurate setup and usage guidance with a selectable brand voice, polished information architecture, evidence-based badges and claims, discoverability suggestions, and an optional editable SVG/PNG banner. Use when the user asks for a README, README refresh or audit, repository landing page, GitHub pre…
Mcp Azure Container Apps Demo
Sample MCP server built with C# and .NET, containerized with Docker, deployed to Azure Container Apps, and called from a C# MCP client.
Invalid Skill
A Claude skill from daijx66-crypto/skillwitness.
Portable Skill
Validate a synthetic Agent Skill when testing SkillWitness locally or in CI.
Youqing Laozhao Skill
Research and review manga from a title and author. Use when a user asks “这本漫画怎么样”, “有请老赵”, requests a manga recommendation or review, or wants autonomous work identification, multilingual research, fact-checking, recommendation judgment, Chinese review writing, and delivery as a finished responsive webpage plus long image.
Readypermit Mcp
ReadyPermit MCP Server — AI-powered property zoning, buildability & ADU analysis for any U.S. address. Works with Claude, ChatGPT, Cursor.
Agent Dash
Reach the human through Agent Dash — a personal push inbox. Send progress updates that land as phone notifications, and ask a question then WAIT for the answer before continuing. Use when you hit a milestone, finish a long task, hit an error the human should see, or reach a decision point where you need the human to choose (which option, approve/reject, fill in details) before proceeding.
Grafana Llmops Forge
Pilote l'observabilité IA/LLM de bout en bout sur Grafana (OSS, Cloud, Enterprise) avec un seul prérequis — une instance Grafana accessible. Auto-découverte (version, APIs, datasources), détection des signaux LLM présents (OTel GenAI gen_ai.*, LiteLLM, vLLM, TGI, GPU/DCGM), génération et déploiement automatiques de dashboards — FinOps & coûts multi-providers (US/EU/Asie), gateway, tracing agents…
BovedIA
Simple personal memory system for Claude Code — plain Markdown notes synced to cloud storage
Helios Llm Orchestrator
Local-first MCP multi-LLM orchestrator with task decomposition and benchmark-guided model routing through OpenRouter.
Ntnu Mcp
Remote MCP server for NTNU course data on Cloudflare Workers — catalog search, schedules, timetables, grade statistics, course comparison, and timetable-conflict checks
Awesome Cloudflare Id
⛅️ Kitab Cloudflare (Stack Nol Rupiah). Kumpulan alat, starter kit SaaS, AI, dan proyek open-source serverless untuk developer Indonesia.
Dianpo
点破一段技术机制背后不明显的心智模型——角色是谁、token/凭证/密钥/证书归谁所有、谁在向谁证明什么、为什么设计成这个形状。资深工程师一句话能点明的东西("这个 token 是 OpenAI 的"),这个 skill 负责替用户点明。Use this whenever the user pastes a config, endpoint, protocol description, PR/work note, or auth flow and wants to understand it — trigger on "帮我理解", "点破", "这是谁的 token/key", "谁验证谁", "为什么要这么设计", "为什么非要这样/绕一圈", "没看懂这个流程", "who owns this token", "whose cert/key is this", "who signs…
Opencode Starter
Opinionated OpenCode configuration with reusable agents, document skills, MCP integrations, custom tooling, and cross-platform workstation bootstrap.
Prove It
Require concrete, task-relevant evidence before declaring coding work complete. Use when implementing, fixing, refactoring, migrating, reviewing, or preparing software for release; when a user asks to verify, validate, test, prove, double-check, or show that a change works; or when completion claims should be backed by tests, builds, static checks, runtime checks, screenshots, or other observable…
Parallel Ship
Ship 3+ related PRs in one session by fanning out background agents from the session that holds the analysis context - instead of writing a plan, generating a handoff prompt, and spinning up fresh sessions. Use when one piece of analysis or design work produces several independently shippable PRs across disjoint files, in any repo. For a single PR use ship-pr; for sequential dependent phases use…
Epic Ship
Execute a multi-phase epic end to end - one worktree and PR per phase, verified before merge, merged and cleaned up immediately, moving straight to the next phase without stalling for a prompt. Use when asked to run, ship, drive, or execute an epic (a phased plan doc), or "ship the epic", "run phase M", "continue the epic". For a single change use ship-pr; for independent parallel PRs use paralle…
Ship Pr
Ship a single change through a worktree -> branch -> PR -> squash-merge -> cleanup workflow - pick the right branch type (feat/fix/chore/docs/hotfix), implement, verify with this repo's real build/typecheck/test commands, open the PR, check CI, merge, and clean up. Use for any single PR-sized change in any git repo with a GitHub remote - a bug fix, a small feature, a doc edit, a dependency bump.…
Critic
Use when someone asks to critique, challenge, tear apart, stress-test, review, or find flaws in positioning, messaging, outreach, landing pages, USP, competitive positioning, GTM strategy, or any customer-facing work.
Telegram Mcp Server
Telegram MCP server — personal Telegram bridge over MCP protocol
Shoppingscraper Cli
Price scraper CLI for Amazon, Google Shopping, Bol.com, and Coolblue — scrape prices, offers, buy-box, variants, reviews. Agent-friendly JSON envelope, MCP server mode, ships with SKILL.md for Claude Desktop / Cursor / Code.
Ctoskill
帮助不会编程或刚开始 Vibe Coding 的用户，把软件想法问清楚，提前发现真正需要处理的风险，再把确认好的内容交给 Superpowers 完成设计和开发计划。仅在用户明确要求使用 CTO Skill 或 ctoskill 时使用；不要自动开始开发。
Screenshots
Generate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation.
Favicon
Generate favicons from a source image
Chat Widget
A Claude skill from VALL-dikss/skills.
Rams
Run accessibility and visual design review
Repo Standard
Use when working in a RepoKit-compliant repo — about to commit or open a PR, adding a learning / ADR, or asking "where does X go" or "what's the convention here". Loads the RepoKit conventions and the pre-commit / pre-PR checklists.
New Repo
Use when you want to scaffold, create, or start a new repository to the RepoKit standard — "/new-repo", "scaffold a new repo", "set up a new module / plugin / project repo". Stamps a type x tier-compliant repo from bundled templates, then stops at local review.
Viva Prep
Prepare and conduct an evidence-based oral defense or project viva using the student's own code, report, rubric, and runtime behavior. Use when a student wants realistic viva questions, interactive mock questioning, feedback on answers, concept checks, code-tracing practice, or help identifying parts of a submitted project they cannot yet explain.
Carryctx Core
Core CarryCtx capability. Persistent project context and continuity manager for coding agents. Helps agents manage structured tasks, track progress, save checkpoints, maintain context across sessions and Git worktrees. Use when starting work, tracking task progress, creating checkpoints, switching worktrees, or restoring project state.
Carryctx Personas
Allows the agent to adopt specific personas and roles (e.g., Code Reviewer, Architect) defined in .carryctx/personas/. Modifies agent behavior, strictness, and code style output based on the active role.
Carryctx Rules
Dynamic context-aware rule loader for CarryCtx. Teaches the agent to automatically load and apply domain-specific rules and guidelines from the project's .carryctx/rules/ directory depending on the task at hand. Use to enforce project guidelines and improve accuracy.
Carryctx Workflows
Parses workflow blueprints from .carryctx/workflows/ and automatically generates structured task steps. Helps agents translate high-level tasks into detailed standard operating procedures (SOPs).
Unfork
Reconcile a long-diverged fork with its upstream. Use when a fork has drifted for months or years and the user wants to catch up to upstream while keeping only the local changes that still matter — rebuilt as a clean, minimal patch set.
Human Comments
Write code comments the way a senior engineer would — almost none, and the few that survive are short human fragments, not sentences. The code documents itself; a comment is a last resort for what the code genuinely cannot say. Use this WHENEVER writing or editing code in any language, and especially when the user complains that comments are too verbose, too long, noisy, "AI-sounding", essay-like…