balanced
Constructive, evidence-based dialogue mode that avoids sycophancy. This skill should be used when the user wants balance
Plugin-Paket · von Gleb Kalinin
Überblick
balanced ist ein Plugin-Paket für KI-Coding-Tools von Gleb Kalinin. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-10-19 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-20.
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add glebis/claude-skills
/plugin install balanced@glebis-skillsWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz glebis/claude-skills (Quelle auf GitHub öffnen) | Gelistet | nicht angegeben | Forks (GitHub): 60 Sterne (GitHub): 395 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| glebis-skills | glebis/claude-skills | 395 |
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
AI agent debate arena: read human problems free, register_agent in 1 call, argue with our bots.
-
team-deliberation
Stress-test an idea or decision with a panel of independent specialist subagents: blind analysis, cross-examination, fact checks and a synthesis that keeps the dissent.
-
discernment-nudge
Appends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context
-
Ask a real human for perspective: social contradictions, unclear instructions, second opinions.
-
Constructively challenge ideas, test assumptions and competing explanations, and recommend a next step calibrated to the evidence.
-
Decision QC — AI Devil's Advocate
Devil's-advocate QC API for AIs: post a decision, get strongest counter-argument. 0.1 USDT/call
-
18 AI personas deliberate your hardest decisions — structured multi-round deliberation with genuine model diversity. One command: /council
-
Your AI argues before it answers — five-step decision loop built from Bezos's letters, Musk's algorithm, and Farnam Street's mental models.
-
Structured thinking and multi-perspective deliberation tools
-
Structured multi-round debate between AI tools with proposer / challenger roles and a final verdict. `/debate` orchestrates a back-and-forth between two AI CLIs (Gemini, Codex…
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Structured multi-round debate between AI tools with proposer / challenger roles and a final verdict. `/debate` orchestrates a back-and-forth between two AI CLIs (Gemini, Codex…
-
Fortytwo Prime: collective multi-agent inference for high-stakes questions. ALWAYS use when the user says "Ask Fortytwo", "Ask Prime", "Ask Fortytwo Prime", or calls…
-
Coordinate multi-agent debates across different AI platforms (Claude Code, Antigravity, Copilot, Gemini CLI, etc.) using a shared file protocol. Each agent reads one skill and…
-
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 deterministic thinking partner that challenges assumptions and applies 150+ mental models across 17 disciplines to sharpen decisions, solve problems, and think more clearly…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday.
-
Interactive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until…
-
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
-
You.com agent skills for web search, research with citations, and content extraction. Guided integrations for Vercel AI SDK, Claude Agent SDK, OpenAI Agents SDK, crewAI…
-
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers…
Gelistet auf Claude: knowledge-work-plugins (5)
-
Triage tickets, draft responses, escalate issues, and build your knowledge base. Research customer context and turn resolved issues into self-service content.
-
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers…
-
Speed up contract review, NDA triage, and compliance workflows for in-house legal teams. Draft legal briefs, organize precedent research, and manage institutional knowledge.
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
Government contracting research and capture workflows in Claude: opportunity and pipeline briefs, bid/no-bid and competitor analysis, price-to-win and proposal prep, powered by…
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Notion workflows for implementation planning, research synthesis, meeting preparation, and knowledge capture.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
The Product Design plugin is built for turning early ideas into prototypes teams can review. It starts design and build work by confirming the brief, then helps teams explore…
-
Search, create and update Linear issues, projects, and initiatives. Draft PRDs, write updates, analyze customer requests, and keep plans up to date — all from within ChatGPT
Gelistet auf Community GitHub marketplaces (5)
-
team-deliberation
Stress-test an idea or decision with a panel of independent specialist subagents: blind analysis, cross-examination, fact checks and a synthesis that keeps the dissent.
-
discernment-nudge
Appends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context
-
Constructively challenge ideas, test assumptions and competing explanations, and recommend a next step calibrated to the evidence.
-
18 AI personas deliberate your hardest decisions — structured multi-round deliberation with genuine model diversity. One command: /council
-
Your AI argues before it answers — five-step decision loop built from Bezos's letters, Musk's algorithm, and Farnam Street's mental models.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
A runtime-portable 5-agent quality gate that adjudicates text artifacts before they ship. Five role-conditioned LLM deliberators run a 2-round async protocol with cross-read…
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Maps branching Copilot conversations so parallel follow-up questions and exploration paths from complex tasks or learning can be navigated without losing context. Its visual…
-
Self-configuring status briefing generator. Learns your communication style from examples, discovers your data sources, and produces draft updates for any audience on demand.
-
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
Gelistet auf Cursor: cursor/plugins (5)
-
Search company knowledge and draft verified answers.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Generate presentations, documents, and webpages.
Gelistet auf Docker MCP Catalog (5)
-
Real-time web search, reasoning, and research through Perplexity's API
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
-
Enable fast, free real-time web search and access premium data from trusted media brands—news, financial markets, sports, entertainment, weather, and more. Build powerful AI…
-
Production-ready RAG service to search and retrieve data from your documents.
-
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers…
Gelistet auf Official MCP Registry (5)
-
AI agent debate arena: read human problems free, register_agent in 1 call, argue with our bots.
-
Ask a real human for perspective: social contradictions, unclear instructions, second opinions.
-
Decision QC — AI Devil's Advocate
Devil's-advocate QC API for AIs: post a decision, get strongest counter-argument. 0.1 USDT/call
-
Submit a dilemma for blind community verdict with reasoning to improve low confidence
-
Convene a panel of expert AI personas to debate any decision from every side.
Gelistet auf npm registry (MCP servers) (5)
-
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
-
Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor
-
AI co-pilot for Foundry VTT: runs combat, scenes, voices and audio. Requires the Familiar module.
-
Discover and load Agent Skills from configured local directories and Git sources over stdio MCP.
-
easy-notion io.github.misterwigglesworth/easy-notion
Markdown-first Notion MCP server. ~6-7x fewer response tokens vs official Notion MCP. 43 tools.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.