autodecision
Iterative decision simulation with a 5-persona council, adversarial red-teaming, and mechanical convergence. Applies Karpathy's autoresearch + LLM Council patterns to high-stakes…
Plugin-Paket · von Harshil Mathur
Überblick
autodecision ist ein Plugin-Paket für KI-Coding-Tools von Harshil Mathur. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Die letzte erfasste Änderung war am 2026-10-22. Stand unseres Marktplatz-Durchlaufs vom 2026-10-24.
Iterative decision simulation with a 5-persona council, adversarial red-teaming, and mechanical convergence. Applies Karpathy's autoresearch + LLM Council patterns to high-stakes business and strategy decisions.
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 harshilmathur/autodecision
/plugin install autodecision@autodecisionWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz harshilmathur/autodecision (Quelle auf GitHub öffnen) | Gelistet | 0.5.2 | Forks (GitHub): 9 Sterne (GitHub): 103 |
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) |
|---|---|---|
| autodecision | harshilmathur/autodecision | 103 |
Wie sich die Zahlen entwickelt haben
- 2026-10-22103
- 2026-10-24103
Jeder Punkt ist ein Tag, an dem wir eine andere Zahl gelesen haben; flache Abschnitte sind Tage ohne Veränderung. Zahlen verschiedener Marktplätze werden nie addiert.
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Skills: 1
autodecision
Befehle: 11
autodecisionchallengecomparedeckexportplanpublishquickreviewrevisesummarize
Agenten: 5
council-competitorcouncil-customercouncil-optimistcouncil-pessimistcouncil-regulator
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.
-
18 AI personas deliberate your hardest decisions — structured multi-round deliberation with genuine model diversity. One command: /council
-
AI advisory panel for decisions that matter. Decision Council assembles a panel of independent AI advisors to debate your decision from multiple angles, cross-examine each other's…
-
Generate structured decision-making tools — step-by-step guides, bias checkers, scenario explorers, and interactive dash
-
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.
-
Apply 20+ classical decision-making frameworks (cost-benefit, pre-mortem, MCDA, decision tree, reversibility, regret minimization, OODA, Eisenhower, SWOT, second-order…
-
Structured thinking and multi-perspective deliberation tools
-
Adversarial thinking partner for founders and executives. Stress-tests plans, prepares for board meetings, navigates hard calls, runs postmortems. 5 sub-skills with slash commands.
-
council-consult dk.humanified/council-consult
Stress-test a decision through named thinkers' lenses: assumptions, counter-arguments, receipt.
-
Constructively challenge ideas, test assumptions and competing explanations, and recommend a next step calibrated to the evidence.
-
Your AI argues before it answers — five-step decision loop built from Bezos's letters, Musk's algorithm, and Farnam Street's mental models.
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)
-
AI advisory panel for decisions that matter. Decision Council assembles a panel of independent AI advisors to debate your decision from multiple angles, cross-examine each other's…
-
Executive intelligence layer for solo founders — adversarial plan review, structured market research, and professional external-facing document production across an AI-powered…
-
A deterministic thinking partner that challenges assumptions and applies 150+ mental models across 17 disciplines to sharpen decisions, solve problems, and think more clearly…
-
A 5-voice weighted think tank for founders, as a Claude Code plugin. Drop any idea, product, strategy, or decision on it; get a brutally honest 3-round debate across three model…
-
Convene a team of specialist agents out of a 20-agent roster in a 3-round deliberation council on your hardest engineering decisions. Walk away with a unified design and a phased…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Analyze business data and build custom Pigment models, metrics, and boards through natural language.
-
Bring Pendo product analytics into Claude Code: account health, feature adoption, session replay lookup and triage, feedback analysis, and data-informed planning grounded in real…
-
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…
-
Seven skills for financial advisors built on Zocks meeting intelligence: client behavioral profiles, attrition-risk ranking, held-away asset radar, client journey dossiers…
-
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…
Gelistet auf Claude: knowledge-work-plugins (5)
-
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
-
Bring Pendo product analytics into Claude Code: account health, feature adoption, session replay lookup and triage, feedback analysis, and data-informed planning grounded in real…
-
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…
-
Seven skills for financial advisors built on Zocks meeting intelligence: client behavioral profiles, attrition-risk ranking, held-away asset radar, client journey dossiers…
-
Write SQL, explore datasets, and generate insights faster. Build visualizations and dashboards, and turn raw data into clear stories for stakeholders.
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Answer product and business questions with data
-
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…
-
Notion workflows for implementation planning, research synthesis, meeting preparation, and knowledge capture.
-
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
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
Gelistet auf Community GitHub marketplaces (5)
-
18 AI personas deliberate your hardest decisions — structured multi-round deliberation with genuine model diversity. One command: /council
-
Generate structured decision-making tools — step-by-step guides, bias checkers, scenario explorers, and interactive dash
-
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.
-
Apply 20+ classical decision-making frameworks (cost-benefit, pre-mortem, MCDA, decision tree, reversibility, regret minimization, OODA, Eisenhower, SWOT, second-order…
-
Structured thinking and multi-perspective deliberation tools
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…
-
MCP server and 12 skills for product analysis, specification writing, strategy, narrative, and stakeholder alignment. Run competitive analyses, write zero-question specs, design…
-
Explore grouped customer feedback signals by impact and drill into a theme to guide product next steps.
-
Turn your Copilot sessions into proof of impact — research-grounded HTML reports with effort estimation, skills analysis, and ROI metrics from local session logs.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Gelistet auf Cursor: cursor/plugins (5)
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Search company knowledge and draft verified answers.
-
Track AI visibility, sentiment, and citations.
-
Enrich people and companies, run AI research agents.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
Gelistet auf Docker MCP Catalog (5)
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
-
A Model Context Protocol (MCP) server that empowers LLMs to use some of Open Srategy Partners' core writing and product marketing techniques.
-
Real-time web search, reasoning, and research through Perplexity's API
-
A Model Context Protocol (MCP) server for querying deals and evaluations from the Opine CRM API.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
Gelistet auf Official MCP Registry (5)
-
council-consult dk.humanified/council-consult
Stress-test a decision through named thinkers' lenses: assumptions, counter-arguments, receipt.
-
AI agent for business strategy and business design — run strategy missions and 15 analyses.
-
Five AI models debate your decision blind, then give one recommendation and the strongest objection.
-
AI advisory board (MCP): quotes verified word-for-word against public-domain texts, fail-closed
-
Convene a panel of expert AI personas to debate any decision from every side.
Gelistet auf PyPI (MCP servers) (5)
-
Forecast questions about the future, including the outcome under each option.
-
Connect AI assistants to Outline for document search, reading, and management
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
csoai-governance-crosswalk-mcp
Csoai Governance Crosswalk MCP server. Tools: query crosswalk, crosswalk bridge, compliance gap anal
-
air-blackbox-mcp io.github.airblackbox/air-blackbox-mcp
EU AI Act compliance scanner for Python AI agents. 14 tools across 6 articles.
Gelistet auf npm registry (MCP servers) (5)
-
Revenue intelligence for complex B2B growth.
-
Evidence-backed crypto due diligence with sources, freshness, and a runtime receipt on every call.
-
MCP server for prospectapis.com: funding rounds and cited prospect research briefs.
-
Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
-
redash-mcp io.github.seob717/redash-mcp
Connect Redash to Claude -- query data, manage dashboards, and run SQL with natural language.
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.
Im direkten Vergleich
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.