Second Opinion
Consult peer LLM for alternative perspectives when you need second opinion, peer review, or fresh take on technical decisions; useful for validating approaches or exploring alternative solutions
Install
$ agentstack add skill-alberduris-skills-second-opinion ✓ 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 Used
- ✓ 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-alberduris-skills-second-opinion) 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
Second Opinion Skill
Use this skill when you need an alternative perspective on technical decisions, architecture choices, or implementation approaches.
Usage
Invoke the consultation script using the base directory shown above when this skill loads:
bash /scripts/consult.sh --message "your question" --files path1,path2,path3Important:
- Replace `` with the actual "Base directory for this skill" path shown above
- The script will look for
OPENAI_API_KEYin this order:.env.local,.env, system environment variable - Default timeout is 30 minutes; match this in your Bash tool timeout parameter (1800000ms)
- Do NOT run in background—synchronous execution avoids polling overhead
Note on GPT-5 models: GPT-5 was released on August 7, 2025. Available variants: gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro (thinking model). Default is gpt-5-pro-2025-10-06. Override via SECOND_OPINION_MODEL env var.
Context Responsibility
Critical: You must pass ALL relevant context. The peer consultant has no access to this codebase, conversation history, or project context beyond what you provide.
Include:
- Complete problem description
- Relevant code files (via --files)
- Constraints, requirements, decisions made
- Specific questions or areas for review
Interpretation Authority
You retain final judgment. The peer consultant provides alternative viewpoints, but you must:
- Evaluate responses against conversation context
- Reject/question suggestions that conflict with established requirements
- Apply your understanding of the full project context
- Make final decisions based on complete information
The peer opinion is input, not directive.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: alberduris
- Source: alberduris/skills
- 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.