jeffersonvalente
- 72 skills
- 0 followers
- yesterday last updated
- ▌ Setup · jeffersonvalenteAdds or updates the Cardume conventions block in this project's CLAUDE.md through a deterministic script (backup, diff, only the marked block changes; AGENTS.md is imported, never edited) and suggests stack and code-intelligence plugins.
- ▌ Tasks · jeffersonvalenteBreaks an approved spec into ordered tasks in tasks.md, each with an owner and a verification command, optionally opening GitHub issues. Use after a spec is approved, before implementing level-2/3 work.
- ▌ Create · jeffersonvalenteScaffolds a brand-new application from scratch: asks clarifying questions, has project-planner write a plan, builds it with the app-builder skill and specialist agents, then starts a preview. Not for features in an existing project.
- ▌ Review · jeffersonvalenteReviews a change with parallel specialist reviewers, verifies each finding against the code and flags outdated specs. Use before merging a non-trivial change or when asked for a code review (PR, branch or diff).
- ▌ Status · jeffersonvalenteShows the current project status board: project info and tech stack, features done and pending, agent progress, file counts, and preview server health.
- ▌ Verify · jeffersonvalenteRuns every acceptance criterion of a spec and records evidence in verify.md, listing gaps. Use after implementing a spec, before calling the feature done or opening its PR.
- ▌ Enhance · jeffersonvalenteAdds or changes a feature in an existing application: loads project state, plans affected files, asks approval for major changes, applies them via the relevant agents, and refreshes the preview.
- ▌ Preview · jeffersonvalenteManages the local development preview server via cardume-auto-preview: start, stop, restart, status, or health check, with port-conflict handling.
- ▌ Release · jeffersonvalente bundlePrepares a release: checks the approved gate or explicit OK, detects existing release tooling, picks the semver bump with reasons, writes the Keep a Changelog entry and docs/release/vX.Y.Z.md (notes, rollback, honest announcement), and hands over tag/publish commands for confirmation. Use when a version is ready to ship; invoked by the user (/cardume-core:release) or the release-manager agent.
- ▌ Implement · jeffersonvalenteBuilds an approved tasks.md one task at a time, with a fresh subagent, a verification command and a separate reviewer. Use to implement level-2/3 work once its tasks are approved.
- ▌ Standards · jeffersonvalenteScans the repository and writes docs/standards.md with its real conventions, each backed by evidence. Use when starting level-2/3 work without that file, or when conventions changed.
- ▌ Review Pr · jeffersonvalenteReviews a data/analytics PR: SQL, grain, cost and DAG risks plus data evidence from a configured non-production environment, then drafts a review the user approves before anything is posted. Use when a data pipeline PR needs review.
- ▌ Bash Linux · jeffersonvalenteBash patterns and script templates for Linux and macOS. Use when writing Bash scripts or running non-trivial shell commands.
- ▌ Brainstorm · jeffersonvalenteExplores a project or feature idea before implementation: clarifies the goal and constraints, lays out at least three approaches with pros, cons, and effort, and recommends one. Produces no code.
- ▌ Clean Code · jeffersonvalenteCoding standards (SRP, DRY, KISS, YAGNI, naming) with a pre-edit dependency check and a completion self-check. Use when writing, editing or finishing code.
- ▌ Deploy · jeffersonvalenteRuns pre-flight checks and deploys to a target environment (preview, staging, or production), with rollback support. Takes an optional environment or subcommand such as check or rollback.
- ▌ Tdd Workflow · jeffersonvalenteTDD red-green-refactor workflow. Use when implementing a feature or bug fix test-first.
- ▌ Rust Pro · jeffersonvalenteRust 2024 with Tokio and axum: async, types, errors, performance. Use when writing, reviewing or optimizing Rust code.
- ▌ App Builder · jeffersonvalente bundleScaffolds a new app from a plain request: picks the stack and coordinates specialists. Use when asked to create a full-stack, mobile, desktop, CLI or extension app from scratch, or add a large feature to one.
- ▌ Orchestrate · jeffersonvalenteRuns a two-phase multi-agent workflow on the given task: project-planner writes a plan for approval, then 3+ specialist agents implement or analyze in parallel, verification scripts run, and results are merged into one Orchestration Report.
- ▌ Architecture · jeffersonvalente bundleWeighs trade-offs and picks patterns (monolith or microservices, layering, events). Use when choosing an architecture or reviewing a system design.
- ▌ Plan Writing · jeffersonvalente bundleWrites a short plan file of 5-10 verifiable tasks with dependencies. Use when breaking down a new project, feature, complex bug fix or multi-file refactor.
- ▌ Webapp Testing · jeffersonvalente bundleE2E strategy, Playwright scripts, and visual and accessibility checks. Use when testing a web app in a browser or auditing a deployed URL.
- ▌ Brainstorming · jeffersonvalente bundleAsks the clarifying questions that shape a vague idea: purpose, users, scope, trade-offs. Use before building a vague "create X" request or a change with unclear scope.
- ▌ MCP Builder · jeffersonvalente bundleMCP server tool design, schemas, errors and security. Use when creating or reviewing an MCP server or its tool definitions.
- ▌ Red Team Tactics · jeffersonvalenteMITRE ATT&CK-based adversary tactics and reporting. Use when planning or reviewing an authorized red team engagement.
- ▌ Testing Patterns · jeffersonvalente bundleTest pyramid, mocking, fixtures and test organization. Use when designing tests, choosing what to mock or reviewing test quality.
- ▌ API Patterns · jeffersonvalente bundleChooses REST, GraphQL or tRPC and sets versioning, pagination, auth and rate limits. Use when designing an API or reviewing endpoint contracts.
- ▌ Database Design · jeffersonvalente bundlePicks a database and ORM, designs schemas and indexes, plans safe migrations. Use when designing a schema, adding indexes or planning a migration.
- ▌ Parallel Agents · jeffersonvalente bundleRuns Cardume agents singly, in sequence or in parallel and merges the results. Use when subtasks need different expertise or a review needs several perspectives.
- ▌ Design Flow · jeffersonvalente bundleDesigns and iterates on frontend UI through shape, craft, critique, audit and polish, writing production code. Use when the user wants to design, redesign, critique, polish or harden a page, dashboard or component, set a visual direction, or make it bolder or quieter. Not for backend-only tasks.
- ▌ Behavioral Modes · jeffersonvalenteWorking modes (brainstorm, implement, debug, review, teach, ship) and the output style of each. Use to pick how to respond when the kind of request is unclear.
- ▌ Lint And Validate · jeffersonvalente bundleLint, type-check and security-scan commands per ecosystem, with a fix-and-rerun loop. Use after changing code, before calling a task done, or when asked to run static analysis.
- ▌ Bigquery Patterns · jeffersonvalente bundleBigQuery SQL discipline: dry runs, byte caps, pruning, safe joins, integrity checks. Use when writing, reviewing or optimizing BigQuery SQL, or when a query is slow or expensive.
- ▌ Mobile Design · jeffersonvalente bundleMobile UX for iOS and Android: touch targets, lists, offline, navigation, platform conventions. Use when building or reviewing React Native, Expo, Flutter, SwiftUI or Kotlin screens.
- ▌ Game Development · jeffersonvalente bundleGame engine choice, game loop, input, physics, game feel, saves and shipping. Use when building, tuning or debugging a 2D or 3D game in any engine.
- ▌ Powershell Windows · jeffersonvalenteWindows PowerShell pitfalls: logical operators, ASCII output, ConvertTo-Json depth, paths, errors. Use when writing or running PowerShell on Windows.
- ▌ Intelligent Routing · jeffersonvalenteDomain-to-agent routing table. Use when a request spans several domains and it's unclear which Cardume agent should handle it.
- ▌ Frontend Design · jeffersonvalente bundleDesign principles for web UI: constraints, layout, color, typography, motion, anti-cliché checks. Use when choosing a visual direction or restyling a page or component.
- ▌ Vulnerability Scanner · jeffersonvalente bundleOWASP Top 10, supply chain and attack surface analysis with an automated scan. Use when auditing code or dependencies for vulnerabilities.
- ▌ Systematic Debugging · jeffersonvalenteFour-phase debugging: reproduce, isolate, find the root cause, fix and verify. Use when a bug's cause is unclear, an issue is intermittent or a fix didn't hold.
- ▌ Geo Fundamentals · jeffersonvalente bundleOptimizes content for citation in AI answer engines. Use when improving AI search visibility or running a GEO audit.
- ▌ SEO Fundamentals · jeffersonvalente bundleSEO essentials: E-E-A-T, technical SEO, metadata, schema markup. Use when auditing rankings, metadata, sitemaps or structured data.
- ▌ Finops Budgeting · jeffersonvalenteCloud budgets, forecasts, guardrails and unit economics with the FinOps model. Use when setting a budget, explaining a bill spike or adding cost guardrails.
- ▌ Terraform Stacks · jeffersonvalente bundleGenerates Terraform root modules from bundled GCP templates, without running apply. Use when asked for Terraform for a GCP resource, a new stack or HCP Terraform Stacks.
- ▌ Code Review Checklist · jeffersonvalenteChecklist for correctness, security, performance and tests, with severity-tagged comments. Use for a quick manual review of a diff or a self-review before merge.
- ▌ I18N Localization · jeffersonvalente bundleFinds hardcoded strings and structures locales, plurals, formats and RTL. Use when adding translations or auditing i18n coverage.
- ▌ Tailwind Patterns · jeffersonvalenteTailwind CSS v4 with @theme tokens, container queries and dark mode. Use when writing Tailwind styles, migrating from v3 or setting up a Tailwind design system.
- ▌ Server Management · jeffersonvalenteLinux server process management, monitoring, logs and scaling. Use when operating or troubleshooting servers.
- ▌ Lakehouse Architecture · jeffersonvalente bundleMedallion lakehouse on BigQuery: layers, naming, dimensional modeling, lineage. Use when designing, extending or reviewing pipelines, dimensions or fact tables.
- ▌ Java Spring Patterns · jeffersonvalente bundleJava 17+ and Spring Boot 3/4 architecture, idioms, transactions and testing. Use when building or reviewing Java or Spring Boot services.
- ▌ Documentation Templates · jeffersonvalenteStructure templates for READMEs, API docs, code comments, changelogs and llms.txt. Use when writing or restructuring project documentation.
- ▌ React Native Skills · jeffersonvalente bundleReact Native and Expo rules for lists, animations, navigation, images and native modules. Use when building or optimizing React Native apps.
- ▌ Nodejs Best Practices · jeffersonvalentePicks Node.js frameworks and async, error and security patterns. Use when starting or reviewing a Node.js backend.
- ▌ Generator Pr Description · jeffersonvalente bundleDrafts a PR title and body from the branch's full diff, then creates or updates the PR after confirmation. Use when asked to create a PR or write a PR description (criar PR, descrição de PR).
- ▌ React Best Practices · jeffersonvalente bundleReact and Next.js performance rules: waterfalls, bundle size, server rendering, re-renders. Use when building or reviewing React components or optimizing a Next.js app.
- ▌ Performance Profiling · jeffersonvalente bundleMeasures before optimizing: Core Web Vitals, Lighthouse, bundle, runtime and memory profiling. Use when diagnosing a slow page or app.
- ▌ Web Design Guidelines · jeffersonvalente bundleReviews UI code against the Web Interface Guidelines. Use when asked to review UI or UX, check accessibility or audit a design.
- ▌ Deployment Procedures · jeffersonvalenteSafe rollout, pre-deploy checks, rollback and post-deploy verification. Use when planning a release, choosing a rollout strategy or preparing a rollback.
- ▌ Kubernetes Operations · jeffersonvalente bundleWorks on live clusters with kubectl: triage, review and careful changes, read-only by default. Use when diagnosing pods, nodes, rollouts or networking, or changing a running cluster.
- ▌ GCP Observability Patterns · jeffersonvalente bundleRead-only GCP investigation: Composer failures, BigQuery job errors, slot and cost spikes, missing files, audit logs. Use when diagnosing a GCP data platform from telemetry.
- ▌ Observability Patterns · jeffersonvalente bundleVendor-neutral OpenTelemetry, SLOs, burn-rate alerts, dashboards and cardinality cost. Use when instrumenting a service, defining SLOs or alerts, or debugging latency or error spikes.
- ▌ Cloud Platform Assessment · jeffersonvalente bundleRead-only, risk-based Well-Architected review of a whole cloud estate with a 30/60/90-day plan. Use when asked for a platform health check, maturity or hardening review.
- ▌ Project Bootstrap Assistant · jeffersonvalente bundlePlans the platform foundation of a new or inherited system, ending in a charter and 90-day backlog. Use when preparing the technical foundation for a kickoff (not the PRD).
- ▌ Cloud Architecture Best Practices · jeffersonvalenteReviews or proposes cloud workload designs as short decision records weighing cost and reliability on AWS, GCP and Azure. Use when choosing services, sizing, resiliency or network design, or cutting cost.
- ▌ Adr · jeffersonvalenteRecords a decision in docs/adr/ with options and consequences, and updates the index. Use when a technical decision is made or changed, even in a small task: database, framework, integration, data model or a notable trade-off.
- ▌ Prd · jeffersonvalenteWrites a PRD in docs/prd/ with metrics, acceptance criteria, no-gos, risks and blockers. Use for level-3 work: a new system or product phase, or when the user asks for a PRD; feature-level work uses spec.
- ▌ Gate · jeffersonvalenteChecks every acceptance criterion against executed evidence and writes a report in docs/gates/ with an APPROVE/REJECT recommendation. Use when a level-3 phase or milestone ends or the user asks if something is ready to release.
- ▌ Help · jeffersonvalenteReads the project state and suggests the next Cardume command or skill for the request at hand. Use when you don't know what to run next, or automatic routing picked nothing.
- ▌ Plan · jeffersonvalenteCreates a project plan file (docs/PLAN-{task-slug}.md) for the given request using the project-planner agent: clarifying questions, task breakdown, agent assignments, and a verification checklist. Writes no code.
- ▌ Spec · jeffersonvalenteAsks the questions that change the design, then writes a spec in docs/specs/ with testable requirements and non-goals. Use for level-2 work (a new feature, or a change to more than ~5 files or more than one area) before any code; not for level 0-1 edits.
- ▌ Debug · jeffersonvalenteInvestigates the given symptom or error systematically: gathers evidence, ranks hypotheses, tests them one by one, fixes the root cause, and reports it in a structured Debug format with prevention steps.