Autonomous Grill
Autonomous cross-model grilling with a concise decision report for human review.
Install
$ agentstack add skill-tschuehly-skill-incubator-autonomous-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-tschuehly-skill-incubator-autonomous-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
Autonomous Grill
Compose /model-orchestration and /agent-orchestration; apply /domain-modeling only to accepted outcomes. Verify both model families resolve; report a blocker if either fails.
Distill the target, facts, constraints, and unresolved decisions. One lead synthesizes while one persistent opposite-family deliberation advisor challenges the opening decision tree.
Grill autonomously, one consequential decision at a time. Resolve discoverable facts from code and supplied documents. The lead recommends; the advisor challenges assumptions, alternatives, evidence, contradictions, and dependencies; the lead revises or records dissent. Exchange compact deltas for up to three rounds, extending only when new evidence changes a proposal.
Give the same advisor the settled proposals for a closing completeness audit. Send every material gap back through the grill.
Report numbered proposals with the decision, rationale, strongest alternative, evidence, risk, and dependencies. List unresolved dissent.
Keep every proposal pending. Ask the human to accept D…, reject D…: reason, or revise D…: constraint. Ratify accepted IDs; reopen rejected or revised IDs and their dependents. Implementation requires a separate request.
Finish when the closing audit finds no material gap and every consequential branch is a supported proposal or unresolved dissent.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: tschuehly
- Source: tschuehly/skill-incubator
- 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.