Product Manager's Chief Naysayer
v1.0.0Use when a user proposes a product idea, feature concept, or product plan that needs logical stress-testing. Trigger phrases: challenge this idea, stress tes...
⭐ 1· 50·0 current·0 all-time
by@trient
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and the SKILL.md all align: the skill is an instruction-only 'naysayer' whose job is to ask hard, scoped questions. It does not declare unrelated binaries, env vars, or config paths.
Instruction Scope
Instructions are narrowly focused on asking 1–2 provocative questions per round and refusing to provide answers or praise; they do not instruct the agent to read files, access environment variables, or send data externally. Note: the rules are extremely rigid (must always respond, never provide help, strict stage progression) which can cause repetitive loops, confrontational outputs, or lock the conversation into a narrow pattern if the agent or user misunderstands stage/state.
Install Mechanism
No install spec and no code files—this is instruction-only, so nothing is downloaded or written to disk.
Credentials
The skill requires no environment variables, credentials, or config paths; there is no request for secrets or unrelated service access.
Persistence & Privilege
always is false and the skill does not request unusual privileges or to modify other skills. Autonomous invocation is allowed by default, which is normal; there is no indication it needs persistent system presence.
Assessment
This skill is coherent and doesn't ask for secrets or install anything, so it's not a technical red flag. Before enabling it, consider: (1) its adversarial rules may frustrate users or create endless back-and-forth—test with a few sample prompts; (2) it 'must respond' and 'never provide help', so it can be unhelpful for users who actually want constructive suggestions; (3) because it maintains a notion of a proposition across rounds, ensure the agent maintains the right conversational context/state so the skill behaves as intended. If you expect more balanced feedback or occasional constructive suggestions, prefer a less rigid skill or limit when this one is used.Like a lobster shell, security has layers — review code before you run it.
latestvk970fnw83h1fs0t153qtnhgszh84h80x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.