plugins/development/skills/second-opinion/SKILL.md
Gemini second opinion on any document — specs, plans, designs. Provides a DIFFERENT perspective, not validation. Use after writing a design spec or plan — provides Gemini's perspective before user review. Use when user says 'second opinion', 'druhy nazor', 'co na to Gemini', 'over to Gemini'. Always uses Gemini (different AI = different blind spots).
npx skillsauth add petrogurcak/skills second-opinionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Announce: "Používám second-opinion skill — pošlu dokument Gemini na review."
Use when:
Do NOT use when:
review:deep-reviewdevelopment:planning (plan-challenger)team:team-briefingRequired:
Optional:
If called standalone: Ask the user for all three inputs before proceeding.
If called from another skill: File is already provided. Ask:
Construct the review prompt by combining:
Skill loading: Read SKILL.md from the plugin directory.
Examples:
plugins/ux/skills/ux-optimization/SKILL.mdplugins/review/skills/security-review/SKILL.mdplugins/seo/skills/seo-orchestrator/SKILL.mdIf a skill file is not found, skip it silently and continue without it.
Review prompt template:
You are reviewing this document as a second opinion.
Your role: provide a DIFFERENT perspective, not validate.
Document:
{file content}
Domain expertise (apply this lens):
{skill content, if provided — omit this section entirely if none}
Focus:
{question, if provided — omit this section entirely if none}
Respond with:
## Co vidim jinak
- Where you disagree or see blind spots. Reference exact sections.
## Jak bych to udelal ja
- Your alternative approach with reasoning. Say "I would do X because Y."
## Sources
- If you used web grounding.
Rules: Be opinionated. Be specific. No generic praise. Max 1 page.
If document is solid, say so briefly and focus on 1-2 things you'd change.
Use a temp file to avoid shell escaping issues:
cat > /tmp/second-opinion-prompt.md << 'PROMPT_EOF'
[combined prompt with document content and skill content substituted in]
PROMPT_EOF
cat /tmp/second-opinion-prompt.md | gemini -y -p "Review the document above as instructed."
Error handling: If gemini exits non-zero or is not available:
"Gemini neni dostupny. Chces zkusit znovu, nebo pokracujem bez second opinion?"
Never block the workflow. If Gemini is unavailable, let the user decide whether to retry or continue without review.
mkdir -p docs/reviews
Save to: docs/reviews/YYYY-MM-DD-<topic-slug>-gemini-review.md
Derive <topic-slug> from the reviewed file name (e.g., user-auth-spec from user-auth-spec.md).
Output file format:
# Gemini Review: {topic}
**Date:** YYYY-MM-DD
**Reviewed file:** {path}
**Skills applied:** {comma-separated list or "none"}
**Focus:** {question or "general review"}
## Co vidim jinak
{Gemini output}
## Jak bych to udelal ja
{Gemini output}
## Sources
{Gemini output or "none"}
Display the full review inline.
If called from another skill: Present review inline, then ask:
"Chces neco z toho zapracovat?"
User decides. Do not automatically apply any changes.
Claude reviewing its own output is inherently biased. Claude wrote the document — it will tend to confirm its own reasoning, miss its own blind spots, and validate its own assumptions.
Gemini has different training data, different reasoning patterns, and web grounding. It will disagree on different things, notice different gaps, and approach problems from a different angle.
That difference is the value. The goal is not a second validation — it's a genuinely different perspective.
development
Builds a pre-launch social proof strategy through structured beta programs using D'Souza Brain Audit interviews. Use when launching new products/services and need compelling testimonials, planning a beta cohort, designing interview questions to harvest objection-busting social proof, improving video testimonials for landing pages, or designing case studies with metrics. Trigger phrases include "beta tester program for testimonials", "pre-launch social proof", "Brain Audit testimonial framework", "case study harvest", "reverse testimonial", "video testimonial mechanics", "social proof landing page", "sběr referencí", "beta tester program", "testimonial pro landing page", "social proof před launchem", "rozhovor s klientem", "case study sběr", "reference před spuštěním". NOT for ongoing case study production (use growth-hacking case-study approach), offer design (use offer-creation), or conversion optimization (use ux-optimization).
development
Use when planning a product launch and the product type is unclear or could be either generic (SaaS/app/physical) or info-product. Routes between marketing:launch-strategy (generic launches) and marketing:info-product-launch (courses, memberships, ebooks, cohorts, communities). Trigger phrases - "launch", "spuštění", "go-to-market", "product launch", "release strategy", "uvedení na trh", "launch plan", "spuštění produktu", "launch sequence", "launch strategy". Do NOT trigger when product type is already clear (use specific skill directly).
testing
Specialized 8-week launch cadence for info-products — online courses, cohort programs, memberships, communities, ebooks, masterminds. Combines Jeff Walker's Product Launch Formula (Seed/Internal/JV variants, PLC sequence, open-cart day-by-day) with Stu McLaren's membership mechanics (closed cart, Success Path) and Hormozi Grand Slam Offer stacking. Use when planning "launch online kurzu", "info-product launch", "PLF launch", "course launch", "membership launch", "cohort launch", "ebook launch", "open cart close cart", "8-week launch of online course", "beta cohort to launch sequence", "spuštění kurzu", "launch členské sekce", "open cart strategie". Differentiates from marketing:launch-strategy (generic SaaS/app launches) — info-product-specific. NOT for SaaS launches, physical products, or services.
development
Use when releasing an Expo/React Native mobile app to App Store and Google Play - covers eas submit, ASC "Submit for Review", Play promote Internal→Production, OTA update, and decoding common silent failures (Apple agreement expiry, missing English locale, Background Location declaration, web bundle failure on react-native-maps).