sharkitect-solutions/app-builder
skills/app-builder/SKILL.md
Use when building a new full-stack application from scratch, scaffolding a project, selecting a tech stack, or coordinating multi-agent application development. NEVER use for single-file scripts, adding features to an existing app (use feature-building.md directly), or non-application artifacts like documents or reports.
development
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add sharkitect-solutions/sharkitect-claude-toolkit app-builderInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 3:26 AM4.4s20 files scanned
SKILL.md
- name:
- app-builder
- description:
- Use when building a new full-stack application from scratch, scaffolding a project, selecting a tech stack, or coordinating multi-agent application development. NEVER use for single-file scripts, adding features to an existing app (use feature-building.md directly), or non-application artifacts like documents or reports.
- version:
- 2.0
- optimized:
- true
- optimized_date:
- 2026-03-11
App Builder
File Index
| File | Description | When to Read |
|------|-------------|--------------|
| project-detection.md | Keyword matrix, project type detection | Starting new project |
| tech-stack.md | 2025 default stack, alternatives | Choosing technologies |
| agent-coordination.md | Agent pipeline, execution order | Coordinating multi-agent work |
| scaffolding.md | Directory structure, core files | Creating project structure |
| feature-building.md | Feature analysis, error handling | Adding features to existing project |
| templates/SKILL.md | Project templates index | Scaffolding new project |
Templates (13)
| Template | Tech Stack | When to Use | |----------|------------|-------------| | nextjs-fullstack | Next.js + Prisma | Full-stack web app | | nextjs-saas | Next.js + Stripe | SaaS product | | nextjs-static | Next.js + Framer | Landing page | | nuxt-app | Nuxt 3 + Pinia | Vue full-stack app | | express-api | Express + JWT | REST API | | python-fastapi | FastAPI | Python API | | react-native-app | Expo + Zustand | Mobile app | | flutter-app | Flutter + Riverpod | Cross-platform mobile | | electron-desktop | Electron + React | Desktop app | | chrome-extension | Chrome MV3 | Browser extension | | cli-tool | Node.js + Commander | CLI app | | monorepo-turborepo | Turborepo + pnpm | Monorepo | | astro-static | Astro | Content-heavy static site |
Related Agents
| Agent | Role |
|-------|------|
| project-planner | Task breakdown, dependency graph |
| frontend-specialist | UI components, pages |
| backend-specialist | API, business logic |
| database-architect | Schema, migrations |
| devops-engineer | Deployment, preview |
Project Type Decision Matrix
Use all signals together, not just one, to select the right template.
| Signals Present | Project Type | Template | |-----------------|-------------|----------| | Auth + payments + subscriptions | SaaS product | nextjs-saas | | Auth + CRUD + database + API | Full-stack web app | nextjs-fullstack | | Marketing copy + animations + no auth | Landing page / static site | nextjs-static or astro-static | | Vue ecosystem preference or Nuxt SSR required | Vue full-stack | nuxt-app | | REST-only, no UI, JSON consumers | Backend API | express-api or python-fastapi | | iOS + Android from one codebase, no desktop | Mobile app | react-native-app or flutter-app | | Runs installed on the user's OS, accesses filesystem | Desktop app | electron-desktop | | Intercepts/modifies browser requests or DOM | Browser extension | chrome-extension | | Terminal invocation, flag parsing, local automation | CLI tool | cli-tool | | Multiple apps sharing packages in one repo | Monorepo | monorepo-turborepo |
Tiebreaker: if two templates fit, prefer the one whose tech stack the user explicitly named.
Tech Stack Override Guidance
Defaults in tech-stack.md apply unless any of these conditions are met:
| Condition | Override | |-----------|----------| | User has an existing DB (MySQL, MongoDB, etc.) | Swap Prisma adapter or ORM to match | | User names a specific auth provider (Auth0, Supabase Auth) | Replace default Clerk/NextAuth with named provider | | Team is Vue-only or React-only by policy | Route to matching template family regardless of feature set | | Mobile target is enterprise or requires heavy native modules | Prefer Flutter (Riverpod) over Expo | | Hosting is constrained (no Node, serverless-only, etc.) | Switch API layer to match hosting constraints (FastAPI, edge functions) | | Performance SLA explicitly stated | Enable SSR/ISR or move to edge runtime; note trade-offs |
When overriding, state the deviation and reason in the plan before scaffolding.
Rationalization Table
Counter these when the reasoning surfaces during orchestration.
| Rationalization | Why It Fails | |-----------------|-------------| | "I'll just pick a template and adjust later" | Wrong template propagates into agent instructions; fixing midway doubles rework | | "The user didn't specify a stack so I'll use the most popular one" | Popularity is not a fit signal; use the decision matrix, then confirm with user | | "Feature-building.md covers this so I don't need to scaffold" | feature-building.md assumes a project already exists; scaffolding must come first | | "I can coordinate agents without reading agent-coordination.md" | Execution order and handoff contracts are non-obvious; skipping causes agent collision | | "The tech stack is standard so I don't need tech-stack.md" | Override conditions (auth provider, hosting, team policy) live there; missing them causes rework | | "I'll start coding while the user clarifies requirements" | Ambiguous project type leads to wrong template selection; clarify first, scaffold second |
Red Flags
- User asked to add a feature to an existing project but app-builder was activated instead of feature-building.md
- Scaffolding began before project type was confirmed from the decision matrix
- Agent coordination started without reading agent-coordination.md first
- Tech stack selected based on a single signal (e.g., "they said Next.js") without checking override conditions
- Template chosen by name recognition rather than matching signals in the decision matrix
- User request is a script, document, report, or automation task — not an application
- Plan was generated without stating which companion files were read
- Two templates selected for the same project with no tiebreaker reasoning given
NEVER
- NEVER scaffold before confirming the project type via the decision matrix
- NEVER skip reading agent-coordination.md before launching multi-agent pipelines
- NEVER use app-builder for adding features to an existing application — route to feature-building.md
- NEVER apply a tech stack override without stating the reason in the plan
- NEVER generate a plan that omits which templates and companion files were consulted
Related Skills
sharkitect-solutions/paid-ads
development
VerifiedTrustedCommunity
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.
SKILL.mdUpdated May 29, 2026
sharkitect-solutions/skills/using-sharkitect-methodology
testing
VerifiedTrustedCommunity
--- name: using-sharkitect-methodology description: Use when starting any conversation in a Sharkitect workspace OR before any task involving NEW pricing, positioning, proposal, strategy, plan-execution, or schema-design work — mandates invocation of Sharkitect-specific methodology skills (pricing-strategy, marketing-strategy-pmm, smb-cfo, hq-revenue-ops, executing-plans, brainstorming) under the same anti-rationalization discipline as using-superpowers. Documentation has failed 4 times across H
SKILL.mdUpdated May 13, 2026
sharkitect-solutions/end-session
testing
VerifiedTrustedCommunity
Use when user says 'end session', 'wrap up', 'stop for the day', 'done for today', 'close out', 'save session', 'wrapping up', or invokes /end-session. Runs the full 9-step end-of-session protocol: resource audit, MEMORY.md update, lessons capture, plan status, pending items, workspace checklist, .tmp/ audit, git commit+push, Supabase brain sync, session brief, summary. Final step schedules a detached self-kill of the current session ONLY (3s delay) so the window closes cleanly. Other claude.exe processes (active workspaces) are NOT touched -- orphan cleanup is handled separately by Claude-Orphan-Cleanup-Hourly with proper age safeguards. Do NOT use for: mid-session quick saves (use session-checkpoint), skill syncing (use sync-skills.py), brain memory queries (use supabase-sync.py pull), document freshness reviews (use document-lifecycle), resource gap detection (use resource-auditor).
SKILL.mdUpdated May 12, 2026
sharkitect-solutions/humanizer
testing
VerifiedTrustedCommunity
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
SKILL.mdUpdated May 7, 2026