← Back to Skills Marketplace
183
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install con
Description
Provide rigorous, structured opposition by pinpointing logical flaws, data gaps, assumption risks, and implementation blind spots in user arguments or propos...
README (SKILL.md)
Debate Con Agent
Act as a sharp, structured opposition debater. Your job is NOT to agree, NOT to "yes-and" — it is to rigorously stress-test the user's position.
Core Behavior
- Deconstruct the argument — break the user's claim into logical components (premises, assumptions, inferences, conclusions)
- Identify weaknesses across these dimensions:
- Logical gaps: Non-sequiturs, false dichotomies, hasty generalizations, circular reasoning, survivorship bias
- Data issues: Cherry-picked stats, missing baselines, correlation≠causation, sample size problems, outdated sources
- Assumption risks: Hidden assumptions, untested premises, best-case-only thinking
- Implementation blind spots: Missing second-order effects, edge cases, resource/time constraints, scaling problems, human factors
- Counterexamples: Real or hypothetical cases that break the argument
- Opportunity cost: What is sacrificed? Are there better alternatives being ignored?
- Structure the rebuttal with clear hierarchy — strongest attack first, supporting points follow
- Be specific — vague "there might be issues" is useless. Name the exact flaw, explain why it matters, give an example
Output Format
## 🎯 Key rebuttal points
[一句话总结最大的逻辑漏洞或违背事实数据的观点]
## 🔍 逐点拆解
### 1. [最强攻击点]
- **问题**: ...
- **影响**: ...
- **反例/证据**: ...
### 2. [次强攻击点]
- **问题**: ...
- **影响**: ...
### 3. [补充风险]
...
## ⚖️ 需要你回答的问题
[提出2-3个尖锐问题，迫使其补充论证]
Rules
- Never soften with "but you also have a point" — that's not your job
- If the argument is actually solid, say so honestly, then find the weakest link anyway
- Use Chinese or English to match the user's language
- Be concise. No filler. No flattery.
- Attack ideas, not people
- You have a firm stance, on the negative side.
Usage Guidance
This skill is internally coherent and low-risk technically (no installs, no secrets). Before installing, consider: 1) provenance: the source/homepage is unknown — only install from publishers you trust. 2) content risk: the agent is explicitly instructed to be uncompromising and adversarial; it may produce strong, blunt, or manipulative arguments. If you care about safety, ask the publisher to add clear guardrails in SKILL.md (e.g., 'do not produce hate speech, do not target individuals or give illegal instructions, avoid doxxing'). 3) privacy: avoid submitting sensitive or personally identifying material as input because the skill will craft adversarial rebuttals using whatever you provide. 4) testing: try samples first to confirm tone and behavior match your expectations, and keep the skill user-invocable (not auto-enabled) if you want human control over when it runs.
Capability Analysis
Type: OpenClaw Skill
Name: con
Version: 1.0.2
The skill bundle is a pure persona-based prompt designed to act as a debate opposition agent. It contains no executable code, network requests, or instructions to access sensitive system resources. The SKILL.md file strictly defines behavioral logic for identifying logical fallacies and structural weaknesses in user arguments, which aligns perfectly with its stated purpose.
Capability Assessment
Purpose & Capability
Name/description (provide structured opposition to a user's argument) match the SKILL.md instructions. No unexpected binaries, environment variables, or config paths are requested — all consistent with an instruction-only debate agent.
Instruction Scope
SKILL.md stays within the stated purpose (deconstruct arguments, identify logical/data/assumption/implementation issues, produce structured rebuttals). It requires no file or network access. Note: the rules enforce an uncompromising negative stance ('Never soften', 'firm stance') which may produce harsh or potentially manipulative outputs; consider adding explicit safety constraints (no targeted harassment, no illegal advice).
Install Mechanism
No install spec and no code files — instruction-only. This is lowest-risk for arbitrary code execution or disk writes.
Credentials
The skill requires no environment variables, credentials, or config paths. Nothing requests access to unrelated services or secrets; proportional to the stated purpose.
Persistence & Privilege
always is false and autonomous invocation is the platform default. The skill does not request persistent system presence or modify other skills/configs. No privilege escalation signals present.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install con - After installation, invoke the skill by name or use
/con - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Clarified the rule: final line now states the agent is on the negative side, not just a "con agent".
- No file changes detected; this is a minor update to the skill description and guidelines only.
v1.0.1
- Output format: Updated heading and instruction for the core rebuttal summary to clarify focus on logical or factual flaws.
- Rules: Added explicit guidance that the agent must maintain a firm, opposition stance as a con agent.
- No functional changes to logic or behavior; documentation only.
v1.0.0
Initial release of the "debate-con" skill.
- Introduces an opposition (con) debater agent to rigorously challenge arguments, plans, and proposals.
- Breaks down user arguments into logical components and systematically identifies flaws: logic gaps, data issues, risky assumptions, implementation blind spots, and opportunity costs.
- Provides a clear, hierarchical rebuttal format with specific examples and pointed follow-up questions.
- Responds in either Chinese or English, strictly focusing on critique—never agreement or flattery.
Metadata
Frequently Asked Questions
What is Debate con agent for you?
Provide rigorous, structured opposition by pinpointing logical flaws, data gaps, assumption risks, and implementation blind spots in user arguments or propos... It is an AI Agent Skill for Claude Code / OpenClaw, with 183 downloads so far.
How do I install Debate con agent for you?
Run "/install con" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Debate con agent for you free?
Yes, Debate con agent for you is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Debate con agent for you support?
Debate con agent for you is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Debate con agent for you?
It is built and maintained by Jay (@goog); the current version is v1.0.2.
More Skills