Andersonlimahw
- 204 skills
- 0 followers
- 6 hours ago last updated
- ▌ Openapi Generate · andersonlimahw bundleGenerate OpenAPI 3.1 specs from existing code (routes, controllers, types, Zod/Joi schemas), or generate code from an existing spec. Produces valid openapi.yaml, typed client SDKs, mock servers, and Postman collections. Use when documenting an API, onboarding clients, generating typed SDKs, or migrating to spec-first development.
- ▌ Plugin Generator · andersonlimahw bundleGenerator for Lemon AI Hub plugins. Creates a new plugin directory following current standards, including plugin.json, SKILL.md, and automatically updates marketplace.json to ensure the plugin is discoverable. Use when the user asks to "create a plugin", "add a plugin", or "generate a new plugin".
- ▌ Pr Review Canvas · andersonlimahw bundleRender a PR diff review as an interactive walkthrough that groups changes by reviewer importance, separates boilerplate from core logic, and highlights tricky or unexpected code. Use when reviewing a pull request, summarizing a diff, or asking for a diff walkthrough.
- ▌ Prompts Vercel React · andersonlimahwReady-to-paste prompts for the Vercel/React family — React and Next.js best-practice audits, performance optimization, composition refactors, view transitions, React Native/Expo, and deploys.
- ▌ Secure Coding Patterns · andersonlimahwSecure coding patterns and DevSecOps best practices. Use for threat modeling, secret management, secure authentication, OWASP Top 10 prevention, and security compliance.
- ▌
- ▌ Code Review Expert 2 · andersonlimahwLaunch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for code-review-expert, double thermo review, or combined bug/security and code-quality branch audits.
- ▌ Karpathy Graph Extract · andersonlimahwStage 1 of the karpathy-graph pipeline. Turn unstructured context — documents, source files, incident timelines, chat logs, research notes — into typed entities and subject-predicate-object relations that fit the graph ontology. Use when the user asks to extract entities, pull relations out of documents, map a codebase into a graph, or when building a knowledge graph and no nodes exist yet.
- ▌ Karpathy Graph Resolve · andersonlimahwStage 2 of the karpathy-graph pipeline. Collapse duplicate surface forms into canonical entities using context as evidence, reversibly and with a recorded rationale. Use after extraction when the graph contains aliases, abbreviations, or spelling variants of the same thing, when isolated-node count is high, or when the user asks to deduplicate or merge entities.
- ▌ Prompts Catalog Index · andersonlimahwComplete A-to-Z index of every plugin in the hub with a one-line when-to-use hint, grouped by area. Use to locate the right skill fast when no cookbook track matches, or to browse the full catalog without reading raw descriptions.
- ▌
- ▌
- ▌ Karpathy Graph Evaluate · andersonlimahwStage 5 of the karpathy-graph pipeline. Score graph quality across extraction, resolution, structure, query, and operations, and run a ratchet loop that keeps only changes which improve the metric. Use when the user asks how good the graph is, wants to tune extraction prompts or the ontology, asks to measure or improve graph quality, or wants to detect resolution regressions.
- ▌ Prompts Feedback Loops · andersonlimahwReady-to-paste prompts to run continuous validation and feedback loops — API test loops, exploratory browser QA, error-fix loops, metric optimization, and completion verification gates.
- ▌ Prompts Mobile Release · andersonlimahwReady-to-paste prompts for mobile release — App Store and Google Play go/no-go audits, App Store Connect automation, Play Console API, store listing optimization, and macOS/SwiftUI validation loops.
- ▌ Karpathy Graph Visualize · andersonlimahwRender a karpathy-graph for humans — an interactive HTML explorer, a Mermaid diagram for docs and PRs, and a health report — then explain what the picture actually shows. Use when the user asks to see, visualize, draw, or open the graph, wants a diagram for documentation, or asks what the graph looks like.
- ▌ Prompts Design Frontend · andersonlimahwReady-to-paste prompts for UI and frontend design — intentional visual direction, design-system data, accessibility gates, screenshot-to-code, and redesigns. One aesthetic at a time.
- ▌
- ▌ Google Play Developer API · andersonlimahw bundleGoogle Play Developer API knowledge base and automation expert. Use when interacting with or integrating the Google Play Developer API for publishing, in-app products, subscriptions, reviews, or reporting. Note that this skill provides the API knowledge (e.g. fastlane supply, googleapis endpoints) and differs from google-play-release-agent which is for release checklists and audits.
- ▌ Google Play Release Agent · andersonlimahw bundleAI release agent for Google Play Store. Audits Android/Expo/React Native/Firebase/RevenueCat apps before submission — build readiness (app.json, eas.json, AAB, versionCode), Play Console metadata, Data Safety Form, Android permissions, RevenueCat/IAP, i18n parity (PT/EN/ES), policy-risk copy, internal/closed testing and staged rollout. Generates reports and a GO/NO-GO checklist. NEVER publishes or rolls out without explicit human approval. Use when preparing an Android app for Google Play, auditing a submission, generating release notes, validating Data Safety or permissions, or running a release go/no-go. Triggers on "prepara meu app para Google Play", "audita minha submissão Android", "gera checklist Google Play Review", "valida Data Safety", "valida permissões Android", "valida RevenueCat/IAP Android", "gera release notes para Google Play", "faz go/no-go de release Android", "prepara internal testing/closed testing", "audita risco de rejeição por policy".
- ▌ Agy CLI · andersonlimahwWrapped access to Agy CLI (Antigravity). Captures agy --help, caches subcommands, validates flags, post-processes output. Use for ANY Agy CLI invocation from Claude Code or other harnesses. Saves ~85% tokens vs raw agy output.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Typed Decision Engineering · andersonlimahw bundleDesign model-agnostic workflows using narrow typed decisions, deterministic composition, uncertainty routing, and measured token/cost comparisons. Use for typed AI decisions, bounded choice/score/binary-probability questions, structured-output routing, token-efficiency benchmarks, or replacing fragile LM parsing.
- ▌ CLI For Agent · andersonlimahw bundleDesign or review CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agent-friendly CLIs.
- ▌ CLI Generator · andersonlimahw bundleGenerate a complete, production-ready CLI in Bun from a SPEC (OpenAPI, JSON Schema, markdown contract, or natural-language description). Outputs a runnable binary with commander-style arg parsing, shell autocomplete, --help generation, man page, and token-aware output formatting. Use when you need to turn an API spec or feature description into a working CLI in minutes.
- ▌ Create Plugin · andersonlimahw bundleScaffold a new AI agent plugin directory with valid manifest, component directories, and marketplace wiring. Use when starting a new plugin, adding a plugin to a multi-plugin repository, or reviewing a plugin before submission.
- ▌ Design Expert · andersonlimahw bundleCreate, redesign, critique, and ship distinctive production frontend pages and components. Orchestrates design, design-taste-frontend, frontend-design, impeccable, revenue-centric-design, scroll-world, and ui-ux-pro-max in lexical order. Use for UI structure, visual systems, responsive layouts, interaction, motion, and visual QA; skip backend-only work.
- ▌ Feature Flags · andersonlimahw bundleFeature flag registry management. Scans codebase for all flags, tracks age and rollout state, generates cleanup reports, and creates removal PRs for stale flags. Use when managing technical debt from old flags or auditing flag hygiene across the repo.
- ▌ Feature Purge · andersonlimahw bundleSafely remove an entire feature and every dead reference it leaves behind — not just the folder you point at, but the sibling folders in other architecture layers, the imports/registries/routes/i18n keys that point to it, and any newly-orphaned code. Verifies the quality gate stays 100% green and writes a Markdown removal report. Use when deleting a feature, screen, module, or directory and you need it gone WITHOUT leaving dead files or dead code. Triggers on /feature-purge <path>, "remove this feature", "delete this folder safely", "apaga essa feature sem deixar código morto", "limpa essa screen e as camadas".
- ▌ Heygen Expert · andersonlimahw bundleCanonical HeyGen orchestrator. Routes any request touching HeyGen — AI avatars, presenter videos, video translation/dubbing, lipsync, or HyperFrames HTML-based video composition (motion graphics, captions, slideshows, Remotion ports, faceless explainers, product launch videos, PR-to-video, music-to-video, talking-head recuts) — to the correct skill and CLI (`heygen`, `npx hyperframes`) instead of guessing or reimplementing what those skills already do. Use when the user says "create an avatar", "make a HeyGen video", "translate/dub this video", "lipsync", "clone my voice into another language", "generate a talking head video", "make a promo/explainer/motion graphic", "hyperframes", "render a composition", or names any heygen-* / hyperframes-* skill directly. Decides HeyGen API vs HyperFrames vs CLI-only, and how to bridge a HeyGen-generated clip into a HyperFrames composition.
- ▌ Karpathy Loop · andersonlimahw bundleExecutes autonomous Loop Engineering cycles for continuous software engineering optimization — performance, build time, bundle size, test coverage, correctness — against any measurable metric.
- ▌ Smart Handoff · andersonlimahw bundleSave a resumable handoff when a session's context/usage budget is nearly exhausted, so any AI runtime (Claude Code, Codex, Antigravity/Agy, OpenCode, Gemini CLI) can pick the work up with zero lost context. Use proactively when approaching ~90-95% context or usage limits.
- ▌ Spotify Squad · andersonlimahw bundlespotify-squad plugin. Routes to its sub-skills: adversary-review, agile-ceremonies, backend-patterns, data-pipeline, devops-pipeline, frontend-patterns, mobile-patterns, new-db-schema, new-feature, new-repository, new-screen, product-discovery, qa-strategy, secure-coding-patterns, squad-coordination, ui-design-system, ux-research. Use when the task matches any of the capabilities listed below.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Git Hooks · andersonlimahwManage Git hooks for automating pre-commit, pre-push, and other lifecycle events.
- ▌
- ▌
- ▌
- ▌ Codex CLI · andersonlimahwWrapped access to Codex CLI (OpenAI). Captures codex --help, caches subcommands, validates flags, post-processes output. Use for ANY Codex CLI invocation from Claude Code or other harnesses. Saves ~85% tokens vs raw codex output.
- ▌
- ▌ Git Branch · andersonlimahwManage git branches with listing, creation, deletion, and rename operations.
- ▌
- ▌ Continual Learning · andersonlimahw bundleOrchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.
- ▌ Teaching Workspace · andersonlimahw bundleEnsina habilidades ou conceitos ao usuário em workspace stateful. Missões, lições HTML, referências, registros de aprendizado.
- ▌ Agentic Value Loops · andersonlimahw bundleagentic-value-loops plugin. Routes to its sub-skills: ai-tuning-loop, documentation-sync-loop, feature-development-loop, loop-invariants, maintenance-security-loop. Use when the task matches any of the capabilities listed below.
- ▌ Code Smell Detector · andersonlimahw bundlePR-level code smell gating and trend tracking. Detects new smells introduced in a PR, blocks merge if smell density exceeds threshold, tracks file-level smell trends over time, and generates weekly maintainability reports. Use when enforcing code quality standards in CI or monitoring technical debt accumulation.
- ▌ Doc Driven Grilling · andersonlimahw bundleInterrogatório implacável para planos e designs que cria documentação (CONTEXT.md/glossário, ADRs) durante o processo, enquanto grilla. Combina grilling de decisão com domain-modeling — desafia a linguagem vaga contra o glossário existente, stress-testa cenários concretos, e captura termos e decisões inline conforme cristalizam. Use when user wants to stress-test a plan against their project's language and documented decisions, mentions "grill me", "grilling", or needs to sharpen terminology while deciding.
- ▌ Karpathy Guidelines · andersonlimahw bundleInjects Lemon AI Hub's standard AGENTS.md and CLAUDE.md guidelines into the current workspace. Enforces Andrej Karpathy's surgical coding style, simplicity, and goal-driven execution.
- ▌ Logo Creator Expert · andersonlimahw bundleDesign a minimalist, single-gesture brand mark the way Jony Ive would — one idea, no ornament, tested small before it's called done. Use when the user asks to create/redesign a logo, favicon, or app icon, wants a "minimalist" or "Apple-style" mark, or says a logo feels generic/cluttered/AI-slop.
- ▌ App Store Connect API · andersonlimahw bundleExpert agent for the Apple Store Connect API. Use when the user asks questions about the App Store Connect API or needs to automate tasks involving TestFlight, In-App Purchases, Provisioning, App Metadata, Reporting, or Game Center.
- ▌ Architecture Deepener · andersonlimahw bundleSurface opportunities to deepen a codebase. Finds modules that are shallow (thin pass-throughs, anemic types, missing domain modeling) and proposes how to make them deep (rich domain types, co-located behavior, testable seams). Outputs a visual HTML report and then runs an interactive grilling loop that pressure-tests each opportunity. Use when the codebase feels "flat", domain logic leaks into controllers/UI, types carry no behavior, or AI agents struggle to navigate the module boundaries. Integrates with domain-modeling, codebase-design, and ADR workflows.
- ▌ Learning Output Style · andersonlimahw bundleEngage in active learning by requesting meaningful code contributions at decision points and providing educational insights. Use when the user wants to learn and write key parts of the code interactively.
- ▌
- ▌
- ▌
- ▌ Graph Feature Architect · andersonlimahw bundlePlan new feature implementations grounded in the project's existing knowledge graph (graphify-out/ or a karpathy-graph output) instead of ad-hoc grepping. Use when a graph already exists for the target codebase and the user wants to plan, scope, or architect a feature that plausibly touches more than one module — surfaces god nodes, community boundaries, and cross-file relationships before any code is written. If no graph exists yet, this skill says so and defers to building one (graphify update . or the karpathy-graph plugin) rather than guessing relationships.
- ▌
- ▌
- ▌
- ▌ AI Workspace Orchestrator · andersonlimahw bundleai-workspace-orchestrator plugin. Routes to its sub-skills: adversarial-setup-review, build-agent-orchestrator, context-handoff, setup-ai-workspace, workspace-contract, write-project-skill. Use when the task matches any of the capabilities listed below.
- ▌ Apple Store Release Agent · andersonlimahw bundleAI release agent for the Apple App Store. Audits Expo/React Native iOS builds, App Store metadata, App Privacy readiness, TestFlight, RevenueCat/IAP, Firebase, i18n parity, screenshots, and review notes, then emits a GO / GO_WITH_WARNINGS / NO_GO decision. Generic core with presets for Expo/RN/Firebase/RevenueCat apps. Never submits, never pays, never alters the store without explicit human approval.
- ▌
- ▌
- ▌
- ▌
- ▌ Orchestrate · andersonlimahw bundleFan a large task out across parallel AI agents. Planners scope and publish tasks, workers execute, and a script reconciles the tree from disk. Use when explicitly invoking /orchestrate with a large goal that benefits from parallel decomposition.
- ▌ Token Saver · andersonlimahw bundleConfigures token-saving tools (rtk, caveman, graphify, context-mode) globally or per project. Allows auditing and calculating the token savings obtained.
- ▌ Brand Naming · andersonlimahw bundleRun an adversarial naming sprint to find a defensible brand name for a company or product. Use when the user says "naming sprint", "find a name", "name my company", "name this product", "rebrand", "brand name", "escolher nome", "nomear a empresa", or asks to validate a shortlist of candidate names. Generates a large longlist, funnels it down with an explicit scorecard, then tries to destroy every survivor with collision research across software, dev ecosystems, companies, app stores, domains and trademarks before recommending anything. Refuses to recommend a name that has not been researched.
- ▌ Bundle Watch · andersonlimahw bundleBundle size CI gate and trend tracking. Compares bundle size of current branch vs main, posts PR comment with size diff, and blocks merge if budget is exceeded. Use when setting up bundle size enforcement or investigating a sudden size increase in CI.
- ▌ Chaos Runner · andersonlimahw bundleChaos experiment orchestration and scheduling. Runs predefined chaos scenarios (latency injection, pod kill, dependency outage), records results, and tracks resilience score over time. Use when scheduling a game day, setting up weekly chaos tests, or verifying that a new circuit breaker works under fault conditions.
- ▌ Feature Flag · andersonlimahw bundleFeature flag implementation, management, and cleanup. Handles flag creation, gradual rollout strategies, A/B testing wiring, stale flag detection, and safe flag removal. Supports LaunchDarkly, Unleash, GrowthBook, Statsig, custom env-var flags, and database-backed toggles. Use when adding gated features, rolling out gradually, or cleaning up old flags.
- ▌ Scroll World · andersonlimahw bundleBuild an immersive scroll-scrubbed "fly through the world" landing page for any industry or brand using Higgsfield. As the visitor scrolls, a pre-rendered camera flies from outside each scene into its interior, then flows on to the next scene with NO cuts — one continuous connected flight (Emons-style isometric diorama world, or any art direction you pick). The skill interviews the user for the topic, the story beats/sections, and brand kit, then generates cohesive scenes + seamless camera clips with Higgsfield and wires a portable, framework-agnostic scroll-scrub engine. Use when the user wants a "3D world" / "browse-through-the-industry" hero, a scroll cinematic, a diorama landing, or to turn a business into a scrollable world.
- ▌ A11Y Guardian · andersonlimahw bundleContinuous accessibility monitoring. Runs WCAG 2.1 audit on every PR, blocks merge on CRITICAL violations, and posts inline PR comments with fixes. Use when setting up CI accessibility gates or reviewing PR for a11y regressions.
- ▌ Agent Sdk Dev · andersonlimahw bundleagent-sdk-dev plugin. Routes to its sub-skills: agent-sdk-dev, agent-sdk-verifier-py. Use when the task matches any of the capabilities listed below.
- ▌ API Test Loop · andersonlimahw bundleExecutes a continuous validation loop for backend REST APIs using CURL commands. Records findings (REST standards, path, HTTP verbs, inputs, outputs, documentation, security gaps, performance) and applies minimal surgical fixes in routers, controllers, validation schemas, or middleware.
- ▌ Async Advisor · andersonlimahw bundleAsync pattern CI gate and PR review. Detects promise pitfalls, race conditions, and unbounded parallelism in changed files. Posts inline PR comments with corrected code. Use when setting up async quality gates or reviewing a PR with complex async logic.
- ▌ Gh Expert · andersonlimahw bundleExpert GitHub CLI plugin containing multiple skills for PR management, issue tracking, and GitHub workflows automation.
- ▌ I18N Sync · andersonlimahw bundleLocale file synchronization and CI enforcement. Detects missing keys added to base locale, auto-stubs them in all other locales, blocks PRs with hardcoded strings, and generates a translation completeness badge. Use when onboarding a new locale or enforcing translation discipline in CI.
- ▌ Load Test · andersonlimahw bundleLoad testing setup, execution, and analysis with k6, Artillery, or Locust. Generates test scripts, defines VU ramp-up scenarios, interprets p99 latency and error rate results, and suggests infrastructure fixes. Use when user wants to load test an API, check throughput limits, validate SLO headroom, or diagnose performance under traffic.
- ▌ A11Y Audit · andersonlimahw bundleWCAG 2.1 AA/AAA accessibility audit for web components, pages, and apps. Detects contrast failures, missing ARIA labels, keyboard trap issues, focus order problems, and screen-reader gotchas. Use when user wants to audit accessibility, fix a11y warnings, prepare for compliance review, or validate UI against WCAG standards.
- ▌ Chaos Test · andersonlimahw bundleChaos engineering scenarios for resilience testing. Designs fault injection experiments (network partitions, latency injection, dependency failures, disk pressure, memory leaks) and verifies circuit breakers, retries, and fallbacks work correctly. Use when building resilience features, verifying SLO under failure conditions, or preparing for production chaos days.
- ▌ Code Smell · andersonlimahw bundleCode smell detection and remediation. Identifies long methods, god classes, feature envy, primitive obsession, shotgun surgery, dead code, magic numbers, and other structural anti-patterns. Goes beyond linters — understands semantic coupling and design intent. Use when code is hard to change, PRs are consistently risky, or technical debt is growing faster than features.
- ▌ DB Advisor · andersonlimahw bundleAutomated database query monitoring and N+1 detection. Analyzes ORM query logs, detects repeated queries (N+1 pattern), suggests eager loading or batching fixes, and tracks query count per request. Use when adding DB monitoring, investigating slow endpoints, or reviewing ORM query patterns in a PR.
- ▌ Git Expert · andersonlimahw bundleExpert git plugin containing multiple skills for advanced version control, semantic commits, and bisect automation.
- ▌ I18N Audit · andersonlimahw bundleInternationalization completeness audit and key synchronization. Finds missing translation keys, hardcoded strings, pluralization bugs, RTL layout issues, date/number formatting gaps, and untranslated copy. Supports i18next, react-intl, vue-i18n, next-intl, and custom JSON locale files. Use when adding a new language, auditing translation completeness, or debugging locale mismatch errors.
- ▌ CLI Wrapper · andersonlimahw bundleWraps any external CLI so the AI harness can invoke it without context bloat. Captures --help output, documents every subcommand/flag in a compact digest, saves token metrics (raw vs wrapped), and exposes a standardized interface (invoke, explain, audit). Use before calling an unfamiliar CLI or when the harness needs to interact with a CLI repeatedly.