plugins/review/skills/plan-challenger/SKILL.md
Adversarial review of implementation plans — finds failure modes, hidden dependencies, scope risks, missing edge cases, and architecture concerns BEFORE coding begins. Use when a plan file has been written and needs validation before implementation starts. Mandatory in planning skill Phase 3 Step 2. Works in both Claude Code and Gemini CLI.
npx skillsauth add petrogurcak/skills plan-challengerInstall 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.
Adversarial review skill. Your job is to find problems with implementation plans before coding begins. Be rigorous, specific, and honest.
Announce: "Pouštím plan-challenger — adversarial review plánu."
docs/plans/*.md) a čeká na reviewplanning skill Phase 3 Step 2debugging skill)deep-review)Potřebuješ cestu k plan filu. Pokud ji nemáš:
docs/plans/ v aktuálním projektuPřečti celý plan file. Věnuj pozornost:
DŮLEŽITÉ: Neposuzuj plan izolovaně. Prozkoumej:
CORE_PRINCIPLES.md / CLAUDE.md v projektuPlan může vypadat rozumně, ale konfliktovat s existujícími konvencemi.
Pokud plan obsahuje ## Recon sekci (z development:planning Phase 1 Step 2), ověř každý claim:
Class::methodName(), def fn_name, etc.): grep -n "function methodName\|def fn_name" <file>. Pokud claim říká "method existuje" a grep nenajde → CRITICAL hallucination.Pokud ## Recon sekce chybí úplně a plan dotýká 4+ souborů nebo cross-layer (entity + presenter + service): WARNING — "Recon section missing, recommend running Phase 1 Step 2 before proceeding."
Pokud Recon je generic ("checked, OK"): WARNING — "Recon must contain concrete file:line references, not generic statements."
grep -n "function <name>\|def <name>" v dotčeném souboru. Pokud nenajdeš → CRITICAL.EntityManager::flush() ale projekt používá custom EM? Wrong DI pattern (Facade vs Service)? Read 1 sample z dotčené vrstvy.review:abstraction-review lens pokud ano.Přesně tenhle formát, bez odchylek:
## Plan Challenge Results
**Plán:** `[path]`
**Verdict:** [APPROVE / REVISE / REJECT]
**Shrnutí:** [Jedna věta]
### CRITICAL (must fix before implementing)
- **[C1]** [Specifický popis problému]
- **Risk:** [Co konkrétně může selhat]
- **Suggestion:** [Jak fixnout — konkrétně, ne "add error handling"]
- **Where:** [Task ID nebo file:line]
### WARNING (should address)
- **[W1]** [Specifický popis]
- **Risk:** [Co může selhat]
- **Suggestion:** [Jak fixnout]
### INFO (consider)
- **[I1]** [Observace nebo otázka k zvážení]
### Next Step
[Jedna věta co má user udělat dál.]
APPROVE: Plán je ready, 0 CRITICALs, optional WARNINGs.REVISE: Opravitelné problémy, user updatuje plán, pak implementuje.REJECT: Fundamental issues, potřeba přepracovat approach (vrať se do Phase 1 planning).Pokud CRITICAL findings:
Pokud jen WARNING/INFO:
Po challengi:
development:planning) pokračuje Phase 3 Step 3: ptá se na deep-reviewTento skill nahradil dřívější plan-challenger agent (který byl Claude Code-specific). Funguje identicky v Claude Code i Gemini CLI přes standardní skill invocation.
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).