JustineDevs

Compatibility visual-delivery runtime for Roblox creator UI, HUD, and plugin work; the canonical completion owner is now Forge.

Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference boundaries. Use when a user says 'analyze', 'investigate', 'why does', 'what's causing', or needs grounded cross-file explanation before any changes are proposed.

Persistent Roblox Studio execution loop that carries an approved creator plan to verified completion

Run an anti-slop cleanup/refactor/deslop workflow

Ask Claude via local CLI and capture a reusable artifact

Ask Gemini via local CLI and capture a reusable artifact

Canonical end-to-end creator workflow surface for Roblox Creator Skills

[RCS] Strict autonomous loop: $blueprint -> $forge -> $code-review

Load when backend API work touches authentication, authorization, rate limiting, CORS, input validation, public endpoints, or security remediation in Mandate402.

Load when architecture choices, ADRs, trade-off evaluation, technical debt, or pattern selection need explicit decision records for Mandate402.

Load when designing or reviewing backend systems, APIs, auth, databases, security, performance, scalability, CI/CD, monitoring, or production runtime patterns.

Load when reviewing Mandate402 code for secrets, auth, authorization, input validation, payment safety, blockchain integration, or release security risks.

Load when testing Cloudflare Workers, Vitest worker pools, binding mocks, integration tests, coverage, or worker test failures.

Load when planning or building React/Next.js UI with CO-STAR structure, design tokens, dashboards, hero sections, or custom UI prompts.

Load when applying core engineering principles such as SOLID, OOP, encapsulation, abstraction, DRY, KISS, YAGNI, composition, or dependency design.

Load when creating or updating contributor onboarding, setup docs, README guidance, local development instructions, or new maintainer handoff material.

Write, refine, run, and QA promptfoo evaluation suites for Premortem: promptfooconfig.yaml, providers, vars, tests, assertions, and CI gates. Use for canonical prompt regression in @premortem/evals. Do not use for adversarial redteam plugin setup (see security/llm-security).

Use when the user wants to decide whether implementation is ready, what remains blocked, and what the exact next build step should be.

Use when the user wants the singular Meta-Architect in-session autonomous manager: choose the best next workflow step, manage the fixed gated workflow, and route bounded helper handoffs inside Codex.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Automated Dynamic Application Security Testing (DAST) using Playwright MCP plus standard OS pentest tooling. Performs blackbox or greybox scans on single or multiple domains with orchestrated crawling, vulnerability detection, and structured output. Trigger on requests like "scan this domain", "run DAST on these URLs", "automated pentest", or "security-test the staging app".

Comprehensive Android mobile application penetration testing with rooted-device ADB and Frida-based MCP tooling. Covers OWASP MASTG full methodology: recon, static + dynamic analysis, SSL/root bypass, IPC fuzzing, data exfiltration, crypto audit, and reporting. Triggers on requests to pentest Android apps, analyze APKs, bypass mobile security controls, or run MASVS/MASTG assessments.

Invariant Guardrails for agent trace policies, tool-call rules, and MCP/LLM proxy guardrails. Use when designing rule-based guardrails beyond @premortem/security string checks, or when scoping Invariant Gateway integration.

Premortem Langfuse integration for managed prompts, traces, and eval scores. Use when wiring LLM observability, prompt versioning, or post-eval scoring in agent pipelines.

Curated startup operating system for founders. Automatically includes startup-manager, founder-foundation, value-validation, mvp-engine, fundraising-kit, gtm-launch, growth-engine, and founder-ops. When installed, all founder modules are available together as one startup bundle, with startup-manager deciding which module should be used first across Codex, Claude, Composer, and similar agent runtimes.

Handle founder operations across legal, equity, governance, and compliance with explicit review gates. Use when the agent needs to draft or organize operating documents, pressure-test cap table and equity decisions, track compliance obligations, or prepare founder operations for diligence and scale.

Assemble an evidence-backed fundraising narrative, deck structure, financial story, and diligence materials. Use when the agent needs to prepare investor-facing materials, pressure-test market-sizing and projection claims, or package a startup into a credible fundraising kit.

Design, run, and interpret growth experiments with funnel evidence and scale discipline. Use when the agent needs to identify a growth bottleneck, prioritize experiments, analyze conversion movement, or decide whether a startup has earned the right to scale a channel or tactic.

Plan, coordinate, and iterate startup go-to-market launches using real adoption and retention evidence. Use when the agent needs to organize launch phases, coordinate channels and assets, define launch metrics, or drive toward repeatable go-to-market and early product-market-fit signals.

Scope, sequence, and verify an MVP with founder constraints, market evidence, and shipping gates. Use when the agent needs to define the smallest useful product, turn validation insights into build loops, manage iterative MVP delivery, or decide whether a feature is ready to ship.

Curated startup operating system for founders. Automatically includes startup-manager, founder-foundation, value-validation, mvp-engine, fundraising-kit, gtm-launch, growth-engine, and founder-ops. Use when the user needs end-to-end founder support across startup thesis, validation, MVP scoping, fundraising prep, launch planning, growth experiments, or founder operations as one bundled skill install. The startup-manager routes ambiguous or broad requests to the most practical module instead of forcing all modules at once.

Validate startup value propositions, market demand, customer pain, and business-model options with explicit evidence and invalidation logic. Use when the agent needs to assess problem-solution fit, compare business models, synthesize user and market evidence, or plan validation experiments before building or fundraising.

Use when the user wants architecture-first product and system design with explicit stack rationale, boundaries, tradeoffs, data model choices, and phased delivery planning.

Use when the user wants to decide whether implementation is ready, what remains blocked, and what the exact next build step should be.

Use when the user wants logic validation: states, transitions, invariants, edge cases, dead ends, and blockers before implementation.

Use when the user wants evidence-backed technology choices, OSS evaluation, and source-grounded validation of the stack proposed in `$arch`.

Use when the user wants a security and trust-boundary review of the current design before implementation or release.

Use when the user wants a DX and UX review of the planned workflow before implementation proceeds.

Use when the user needs scope alignment, shared language, or docs clarity before or between gated lanes.

Use when the user wants contract-preserving simplification, anti-slop cleanup, or a final-pass polish after the main decision is made.

Runs and scopes automated tests for this Turborepo (unit, package filters, Medusa stress, E2E, release gate). Use when the user asks to run tests, verify CI locally, debug failing tests, or choose the right test command for a changed package.

Plug-and-play orchestration skill. User states a goal in natural language; the model runs commands/agent-hub.md (dispatcher), classifies work via agent/operating-model.md, then opens only the matching command or architecture doc (map, architect, memory, recovery, verify, next-pass, or one NN-layer). Layered docs for intent, policy, context, planning, routing, delegation, execution, MCP/tool boundaries, verification, memory, recovery, observability, human gates, release. Use for repo orchestration reviews, boundary work, memory/recovery design, permission-sensitive refactors.

Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability.

CO-STAR UI Creator for React/Next.js: structured prompting to build or integrate UI (components, pages, design systems) or to create custom CO-STAR prompts. Use when the user wants to add hero sections, dashboards, design tokens, shadcn/Magic UI/Aceternity integration, Newsprint design system, or to draft their own CO-STAR prompt (Context, Objective, Style, Tone, Audience, Response). Always run discovery questions first, then plan, then implementation.

Context Engineering patterns for AI development and prompting. Use when the user wants to reduce tokens, avoid lost-in-the-middle, and structure prompts using Skeleton-of-Thought, token-efficient diff updates, XML tagging, symbolic variables, negative constraints, or LLMBundle-style context packaging.

Object-oriented design and Core Engineering principles for AI agents and developers. Use when the user asks about OOP (four pillars), SOLID, encapsulation, abstraction, inheritance, polymorphism, Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, Dependency Inversion, composition over inheritance, DRY, KISS, YAGNI, Law of Demeter, or association vs aggregation vs composition. Includes how each principle looks and example code.

Apply the "Family Values" design philosophy to every UI you build. Use this skill whenever creating frontends, components, apps, landing pages, dashboards, or any user-facing interface. Enforces three core principles (Simplicity, gradual revelation; Fluidity, seamless transitions; Delight, selective emphasis) so that every output feels crafted, intentional, and alive. Prevents generic, static, lifeless UI. Works alongside other skills like frontend-design, web-animation-design, and more.

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

Complete project planning and execution framework. Automatically includes all 14 planning sections (planning/0-Master-Index.md through planning/13-Lessons-Learned-Continuous-Improvement.md) plus all 9 Claude Skills (tech-stack-selector, architecture-decisions, code-standards-enforcer, ci-cd-pipeline-builder, agile-executor, project-risk-identifier, automation-orchestrator, webapp-testing, web-artifacts-builder). All files are located within this skill directory. When installed, all planning templates and execution skills are immediately available.

Complete project planning and execution framework. Automatically includes all 14 planning sections (.claude/skills/blueprintkit/planning/0-Master-Index.md through .claude/skills/blueprintkit/planning/13-Lessons-Learned-Continuous-Improvement.md) plus all 9 Claude Skills (tech-stack-selector, architecture-decisions, code-standards-enforcer, ci-cd-pipeline-builder, agile-executor, project-risk-identifier, automation-orchestrator, webapp-testing, web-artifacts-builder). When installed, all planning templates and execution skills are immediately available.

BlueprintKit Plugin - Complete planning framework automatically including all 14 planning sections (.claude/skills/blueprintkit/planning/0-Master-Index.md through .claude/skills/blueprintkit/planning/13-Lessons-Learned-Continuous-Improvement.md) plus all 9 Claude Skills (tech-stack-selector, architecture-decisions, code-standards-enforcer, ci-cd-pipeline-builder, agile-executor, project-risk-identifier, automation-orchestrator, webapp-testing, web-artifacts-builder). When installed, all files are immediately available.

Complete project planning and execution framework. Automatically includes all 14 planning sections (planning/0-Master-Index.md through planning/13-Lessons-Learned-Continuous-Improvement.md) plus all 9 Claude Skills (tech-stack-selector, architecture-decisions, code-standards-enforcer, ci-cd-pipeline-builder, agile-executor, project-risk-identifier, automation-orchestrator, webapp-testing, web-artifacts-builder). When installed, all planning templates and execution skills are immediately available.