conProvide rigorous, structured opposition by pinpointing logical flaws, data gaps, assumption risks, and implementation blind spots in user arguments or propos...
Install via ClawdBot CLI:
clawdbot install goog/conGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Sep 30, 2026
A founder preparing a Series A pitch asks the skill to challenge their market sizing, growth assumptions, and unit economics. The agent deconstructs the TAM calculation, identifies survivorship bias in comparable exits, and surfaces hidden churn assumptions. It outputs the strongest logical attack first, with specific counterexamples and 2-3 pointed questions the founder must answer before the investor meeting.
A product manager proposes a new feature with advantages like increased engagement and low engineering cost. The skill challenges second-order effects, scaling limits, and opportunity cost against other roadmap items. It forces the PM to defend the feature against edge cases and resource constraints before committing sprint capacity.
A research team presents a study design with expected efficacy advantages. The agent probes sample size adequacy, missing baselines, correlation-causation confounds, and best-case-only optimism in the power analysis. It delivers a structured rebuttal hierarchy and sharp questions about generalizability and ethical blind spots before IRB submission.
An investment analyst outlines a long thesis on a stock or asset with supporting data. The skill attacks cherry-picked statistics, outdated sources, and ignored bear-case scenarios. It identifies the weakest link in the thesis even if the argument is largely solid, and pushes the analyst to quantify downside risks and alternative allocations.
A policy advisor drafts a regulation with stated societal benefits. The agent finds logical gaps, hidden assumptions about compliance costs, implementation blind spots in enforcement, and real-world counterexamples from similar policies. It produces a prioritized rebuttal and 2-3 questions forcing the advisor to strengthen or abandon weak premises.
A web or chat app where users get a limited number of debate-con sessions per month for free, with paid tiers for unlimited sessions, saved transcripts, and team workspaces. The skill acts as a persistent devil's advocate for individuals and small teams. Upsell to advanced analytics on argument quality over time.
Sold to product, strategy, and investment teams as an embedded 'red team' tool that integrates with docs, pitch decks, and spreadsheets. Each review generates a structured rebuttal report with logical gaps and counterexamples, stored in a searchable decision log. Priced per user or per review volume for departments.
Expose the debate-con logic as an API that other platforms (e.g., ideation tools, grant review systems, educational platforms) can call to automatically challenge user submissions. Charge per API call or via tiered usage buckets. White-label the structured output format for their own UIs.
💬 Integration Tip
Pair with a document or chat interface so users can paste arguments directly; the skill needs only text input and returns structured rebuttals, making it easy to embed in existing note-taking or AI assistant workflows.
Scored Jun 29, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...
AI agent for finance search agent tasks