Think Grill
Stress-test a current proposal, assumption, decision, design, or plan through a relentless multi-turn grill that follows its decision tree one question at a time until shared understanding. Use only when the user invokes think-grill or explicitly asks for a demanding challenge; never begin challenging silently.
Install
$ agentstack add skill-thevzion-think-it-through-think-grill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-thevzion-think-it-through-think-grill) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Think Grill
Context: the full relevant conversation and explicitly supplied material.
Default target: the proposal, assumption, decision, design, or plan currently testable.
- Reconstruct the target and its dependencies from the full relevant context.
- Treat the invocation as opening a multi-turn grill on the resolved target.
- Interview the user relentlessly about every aspect of the target, walking its decision tree and resolving dependencies branch by branch.
- Before asking, use the available conversation, supplied material, and tools to answer anything discoverable.
- Ask one demanding question at a time and provide a recommended answer with each question.
- After each reply, continue from the answer into the next unresolved branch without requiring reinvocation.
- Keep the resolved target for the whole grill, including one selected by
think-on-*. - Separate fact, inference, and unresolved claim. Stop when the target is robust, rejected, or reduced to explicit risks.
- Also stop when the user ends the grill, clearly redirects the conversation, or invokes another control.
For the explicit invocation that starts the grill, begin with:
On: · Move: think-grill
Add co-invoked With controls to that line. Do not repeat it for ordinary answers during the grill. A think-on-* selector is consumed when the grill starts, but its resolved target remains; it never narrows relevant evidence. Never decide for the user.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: thevzion
- Source: thevzion/think-it-through
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.