← Back to Skills Marketplace
94
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install objection
Description
Activate this skill whenever the user asks you to "find problems," "poke holes," "stress test," "play devil's advocate," "be critical," "challenge this," "fi...
Usage Guidance
This is an instruction-only 'dissent' skill whose goal is legitimate (find problems) and which has no install or credential requests — but its runtime mandates are absolutist and underspecified. Before installing or enabling it broadly, consider: 1) Fix the naming mismatch (objection vs dissent) and ask the author to clarify allowed verification actions. 2) Require explicit boundaries in SKILL.md: what the agent is permitted to run, what paths/services are off-limits, and whether it may request credentials. 3) If you let it run, use it in a controlled context (non-production data/sandboxed execution) so any suggested 'run' or 'test' steps cannot accidentally leak secrets or modify systems. 4) Be prepared for the agent to ask for additional permissions (access to repos, test accounts, or API keys) to perform the verifications it demands — only grant those on a case-by-case, minimal-needed basis. If you need stricter guarantees, ask the skill author to add explicit verification procedures and allowed tools rather than leaving them to agent discretion.
Capability Analysis
Type: OpenClaw Skill
Name: objection
Version: 1.0.0
The 'dissent' skill bundle (slug: objection) is a set of behavioral instructions designed to make the AI agent act as a critical reviewer or 'devil's advocate.' It provides a structured framework for identifying flaws, edge cases, and logical gaps in user-provided artifacts. While it uses strong language to override default helpfulness biases and ignore time constraints, these instructions are aligned with the stated purpose of adversarial review and do not contain any indicators of data exfiltration, malicious execution, or unauthorized access.
Capability Assessment
Purpose & Capability
Name/description (registry: 'objection') and the SKILL.md's internal name ('dissent') differ, but both describe the same adversarial-review intent. The required capabilities declared (none) are plausible for a purely rhetorical adversarial-review skill. Minor incoherence: package name vs internal name — likely benign but should be fixed for clarity.
Instruction Scope
The SKILL.md mandates exhaustive verification (e.g., "Run it. Test it. Trace the logic step by step.") and forbids hedging. However it gives no bounds or mechanism for execution, and does not explicitly constrain what resources the agent may access to perform those verifications. That ambiguity could cause the agent to attempt actions beyond the user's intent (running code, contacting external services, reading files) or to request credentials without explicit justification.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest installation risk. Nothing is written to disk by the skill bundle itself.
Credentials
The skill declares no environment variables or credentials (proportional). However, the instructions demand active verification that in practice may require credentials, binaries, or filesystem access (e.g., to run tests against real systems). The lack of declared required resources leaves a gap: the skill may prompt the agent to request extra access at runtime.
Persistence & Privilege
always is false and the skill is user-invocable only. It does not request persistent system presence or modify other skills. No privilege escalation indicators in metadata.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install objection - After installation, invoke the skill by name or use
/objection - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the "dissent" skill, focusing on adversarial, problem-seeking review.
- Activates when the user explicitly requests critical analysis (e.g., "play devil's advocate", "find flaws", "challenge this", or "/dissent").
- Prioritizes surfacing all possible flaws, risks, assumptions, gaps, and failure modes in any artifact (code, arguments, plans, etc.), without balancing for politeness or affirmation.
- Outlines strict non-negotiable rules: never assume something is correct without verifying, never outsource responsibility, and never skip thoroughness to save time.
- Provides a multi-layered approach for identifying logical, empirical, edge case, risk, assumption, verification gap, and adversarial issues.
- Specifies a structured output for findings and unverified claims.
- Establishes a mindset centered on maximum problem discovery and thorough critical review.
Metadata
Frequently Asked Questions
What is objection?
Activate this skill whenever the user asks you to "find problems," "poke holes," "stress test," "play devil's advocate," "be critical," "challenge this," "fi... It is an AI Agent Skill for Claude Code / OpenClaw, with 94 downloads so far.
How do I install objection?
Run "/install objection" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is objection free?
Yes, objection is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does objection support?
objection is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created objection?
It is built and maintained by 马龙 (@long1973m); the current version is v1.0.0.
More Skills