Recently added
Plugins grouped by the day they were added to the directory, newest first.
Aug 28, 2026
- on-chain-analytics2.8kstars
Analyze on-chain metrics including whale movements, network activity, and holder distribution
Claude Code1 skill - nft-rarity-analyzer2.8kstars
Analyze NFT rarity scores and valuations across collections
Claude Code1 skill - mempool-analyzer2.8kstars
Advanced mempool analysis for MEV opportunities, pending transaction monitoring, and gas price optimization
Claude Code1 skill - market-sentiment-analyzer2.8kstars
Analyze market sentiment from social media, news, and on-chain data
Claude Code1 skill - market-price-tracker2.8kstars
Real-time market price tracking with multi-exchange feeds and advanced alerts
Claude Code1 skill - market-movers-scanner2.8kstars
Scan for top market movers - gainers, losers, volume spikes, and unusual activity
Claude Code1 skill - liquidity-pool-analyzer2.8kstars
Analyze DeFi liquidity pools for impermanent loss, APY, and optimization opportunities
Claude Code1 skill - gas-fee-optimizer2.8kstars
Optimize transaction gas fees with timing and routing recommendations
Claude Code1 skill - flash-loan-simulator2.8kstars
Simulate and analyze flash loan strategies including arbitrage, liquidations, and collateral swaps
Claude Code1 skill - dex-aggregator-router2.8kstars
Find optimal DEX routes for token swaps across multiple exchanges
Claude Code1 skill - defi-yield-optimizer2.8kstars
Optimize DeFi yield farming strategies across protocols with APY tracking and risk assessment
Claude Code1 skill - crypto-tax-calculator2.8kstars
Calculate crypto taxes with FIFO/LIFO methods and generate tax reports
Claude Code1 skill - crypto-signal-generator2.8kstars
Generate trading signals from technical indicators and market analysis
Claude Code1 skill - crypto-portfolio-tracker2.8kstars
Professional crypto portfolio tracking with real-time prices, PnL analysis, and risk metrics
Claude Code1 skill - crypto-news-aggregator2.8kstars
Aggregate and analyze crypto news from multiple sources with sentiment analysis
Claude Code1 skill - crypto-derivatives-tracker2.8kstars
Track crypto futures, options, perpetual swaps with funding rates, open interest, and derivatives market analysis
Claude Code1 skill - cross-chain-bridge-monitor2.8kstars
Monitor cross-chain bridge activity, track transfers, analyze security, and detect bridge exploits
Claude Code1 skill - blockchain-explorer-cli2.8kstars
Command-line blockchain explorer for transactions, addresses, and contracts
Claude Code1 skill - arbitrage-opportunity-finder2.8kstars
Find and analyze arbitrage opportunities across exchanges and DeFi protocols
Claude Code1 skill - repo-gate1stars
What runs between "the code works" and "it is pushed": trunk setup, conventional-commit splitting, dependency vulnerability triage, spell-check triage, and babysitting CI until it is green.
Claude Code5 skills - guard-hooks1stars
Seven defensive hooks: blocks recursive rm on $HOME, download-and-execute pipelines, secrets-file access, path-less formatter runs, credentials in the staged diff, and the two zsh quoting mistakes that fail silently; warns on stale lockfiles and shellcheck findings.
Claude Code - context-handoff1stars
Carry work across sessions and keep the context that carries it lean: hand off a session, export or log what it found, chart an effort too big for one sitting, and audit or garbage-collect your Claude Code config.
Claude Code6 skills Revises agent-facing prose — skills, agent definitions, specs, and technical docs — so an agent cannot read a sentence two ways, applying twelve conventions adapted from ASD-STE100 Simplified Technical English.
Claude Code1 skill- prompt-quality-criteria0stars
Supplies criteria groups B–G for grading a Markdown prompt that steers Claude — model-specific prompting, general prompting, hallucination guards, output consistency, injection defenses, and prompt-leak defenses. Returns the criteria; the caller scores against them.
Claude Code1 skill - frontend-toolkit0stars
A suite of frontend skills, starting with updating-dependencies: detects and categorizes outdated npm packages, researches the bumps the user selects with a dedicated subagent, and applies only the bumps the user approves — keeping each entry's existing version prefix and attributing new audit advisories to the update. Never commits.
Claude Code1 skill2 MCP servers Authors Conventional-Commits commits and enforces them with a deny-hook, resolving the commit vocabulary from the host project's .brokenrobot-xyz/commits.json with vanilla Conventional Commits defaults.
Claude Code1 skill- agent-authoring-toolkit0stars
A suite for authoring Claude Code artifacts: reviewing-claude-skills and reviewing-claude-subagents each review their artifact in two passes — structure first, stopping at a structural verdict when the shape fails (fit-for-purpose leads the subagent gate), otherwise a full sweep ending in a computed verdict that honors the artifact's recorded waivers; improving-claude-skills and improving-claude-subagents loop the matching review autonomously — review → apply every blocking finding → commit → re-review — until the verdict is acceptable, the findings plateau, or the round cap is hit, asking only one question: the intent brief at kickoff. The subagent loop ends instead of converting when a review says the subagent should be a skill.
Claude Code4 skills - open-magi3stars
Magi proposal-first multi-agent deliberation loop for coding agents.
Codex1 skill1 MCP server - open-magi3stars
Magi proposal-first multi-agent deliberation loop for Claude Code.
Claude Code1 skill - designer0stars
A working UI-design practice for Claude: read the project before touching it, derive one visual stance from the brief and commit to it in writing, build on semantic tokens, use real content, and check the result against an accessibility and taste floor before calling it done. Includes an aesthetic-ingredient sampler that pulls builds away from trained defaults, thirteen in-depth reference files, and an optional Essentialist designer persona distilled from the Bauhaus, Dieter Rams, and Jonathan Ive lineage. Ships a second, independent skill, the Materialist: the Liquid Glass aesthetic as a decision function and its laws, with the measured optics of the material and a cookbook for vitrea, its web implementation. Reconstructs the workflow method observed in Figma Make; not affiliated with Figma, Inc., and not a Figma integration.
Claude Code2 skills - trace-mcp133stars
Framework-aware code intelligence MCP server. 87 framework integrations, 81 languages, semantic search with Signal Fusion (BM25 + PageRank + embeddings + identity), refactoring tools (rename/move/extract/codemod), change-impact analysis, security scanning, and decision/session memory.
CodexAgent Plugins4 skills1 MCP server - useagents0stars
Discover developer tools via the UseAgents registry — search, fetch context, and search official docs.
Agent Plugins1 skill1 MCP server - example-plugin0stars
Example Agent Plugin bundling one skill -- copy plugins/ to .agent/plugins/ to try it
Agent Plugins1 skill - deliberation137stars
GPT, Gemini, Grok, and OpenRouter as expert subagents - second opinions, cross-model consensus, and review.
Codex8 skills1 MCP server - deliberation137stars
Use when you want a delegated second opinion or implementation from GPT (Codex), Gemini, Grok (xAI), or OpenRouter (config-driven, 400+ models) - seven expert subagents (Architect, Plan Reviewer, Scope Analyst, Code Reviewer, Security Analyst, Researcher, Debugger) and bundled ask-gpt/ask-gemini/ask-grok/ask-openrouter/ask-all/consensus commands, advisory (read-only) or implementation (write; Grok and OpenRouter are advisory-only).
Claude Code5 MCP servers A persistent LinkedIn campaign workspace for research, writing, visual creation, planning, measurement, and reliable continuation.
CodexClaude Code13 skills- unslop0stars
[VERALTET – final, Nachfolger: tools] Entfernt typische KI-Muster aus Texten und gibt ihnen eine menschliche Stimme — 62 Erkennungsmerkmale von Werbesprache über Strukturschablonen bis Chatbot-Floskeln. Gilt für jede eigene Textausgabe, auch Chat- und Konsolenantworten.
CodexClaude Code1 skill - nixie0stars
NixOS-Engineer: Flake-first Configs, eigene Derivations & Overlays, Paket-Pinning, resource-aware Remote-Builds auf der schnellsten Kiste, generischer Offline-Closure-Deploy (USB/TUI), dokumentenorientiert
CodexClaude Code4 skills - it-grundschutz0stars
IT-Grundschutz-Berater (BSI): OSCAL-Korpus von Grundschutz++ (Anwenderkatalog + Methodik) lokal vorhalten, Anforderungen zitierfähig nachschlagen, Sicherheitsdokumente nach der Methodik erstellen/prüfen, IT-Grundschutz-Check (Soll-Ist-Umsetzungsprüfung) durchführen, Editionen migrieren (Crosswalk Edition 2023 <-> Grundschutz++), Bausteine für Szenarien modellieren, kryptographische Verfahren/Schlüssellängen nach BSI TR-02102 (+ NIST/FIPS-Gegenprobe) bewerten. Quelle und Logik strikt getrennt für schmerzfreie Editionswechsel.
CodexClaude Code8 skills - grimm0stars
[VERALTET – final, Nachfolger: tools] Behörden-Schreibstilist (Grimm): formuliert Sachverhalte im nüchternen Verwaltungs- und Anordnungsdeutsch der öffentlichen Verwaltung — Nominalstil, Passiv- und Gebotskonstruktionen ('ist zu', 'gewährleistet, dass'), präzise Datums-/Aktenbezüge, hoheitlicher Ton. Baut Texte nach dem behördlichen Führungsschema (Lage → Kräfte → Auftrag/Absicht → Einzelaufträge → Sonstige Maßnahmen), als innerdienstliche Anordnung, Vermerk oder Konzept. Reine Formulierungs-/Redaktionsarbeit — keine fachliche Wahrheitsfindung.
CodexClaude Code2 skills - defuddle0stars
Web-Seiten zu sauberem Markdown konvertieren via Defuddle CLI — token-effizienter als WebFetch
CodexClaude Code - christian0stars
Linux-VPN- und Router-Spezialist (Christian Scheele): OpenVPN/WireGuard/IPsec-Tunnel und sichere WAN-Kopplungen nach dem Reference-first-Prinzip — Config-Syntax, Krypto-Suiten und Manpage-Defaults aus der offiziellen Doku statt aus dem Gedächtnis. Linux-Router-Appliances bauen (OpenWrt/DD-WRT-Herkunft, generisches Linux als Kern, VyOS/NixOS rudimentär), nftables/FRR, plus BSD-Firewall-Appliances pfSense/OPNsense (pf, config.xml, elementare Plugins). Opinionierte sichere Krypto-Defaults, Blast-Radius-Respekt bei WAN-/Firewall-/Routing-Changes. Kommerzielle Hardware bleibt bertrams Revier.
CodexClaude Code5 skills - bibliothekarin0stars
Wissensmanagement-Agent: Wissen einpflegen, abrufen, synthetisieren, destillieren und Vault-Pflege für Obsidian Vaults via CLI und Dateisystem. Erstellt Mermaid- und PlantUML-Diagramme reference-first (offline gespiegelte Doku, lokale Validierung) und empfiehlt die passende Diagrammart.
CodexClaude Code3 skills - bertram0stars
Netzwerk-Engineer (Bertram Fritz): vendor-agnostische Netzwerk-Diagnose und -Konfiguration nach dem Reference-first-Prinzip — CLI-Syntax und Best Practices aus der Vendor-Referenz statt aus dem Gedächtnis. L1–L7-Fehlersuche, Config erzeugen/validieren, Dialekt-Übersetzung (Cisco IOS/RouterOS/PAN-OS/Aruba/Junos), Architektur-/Segmentierungs-Design, gestufter Live-Zugriff mit Blast-Radius-Respekt.
CodexClaude Code5 skills - flyte2stars
Work with Flyte 2. Deploy Flyte on AWS or kind, author and run workflows, apps, agents, data, and ML workloads with the SDK, and operate your cluster through bundled MCP servers.
CodexClaude Code21 skills2 MCP servers - click40stars
Incremental verification for coding agents: propose complete test shards, rerun affected checks, and reuse authoritative passing evidence with optional Guarded approval boundaries.
Codex2 skills - sdd-toolkit0stars
Experimental Codex adapter for the existing SDD Toolkit skills and shared artifact workflow.
CodexClaude Code15 skills - memforks104stars
On-chain, branch-aware memory DAG for Codex. MemForks anchors decisions to Sui and proposes cross-branch merges — memory storage is handled by the MemWal MCP server.
Codex4 skills - portulan-checkpoints0stars
The supervised-build checkpoint ritual as a pack: session-open, pre-commit and milestone-close, each graded by a context that has not seen the implementation, in a fixed verdict vocabulary.
Claude Code - portulan0stars
An operating framework for agentic engineering: a small always-loaded kernel, doctrine for the loop, autonomy tiers, verification and memory, and the Workspace Definition your team's own policy layer is validated against.
Claude Code