Carlos Eduardo Arango Gutierrez
Community@ArangoGutierrez · Bavaria, Germany
Senior Systems Software Engineer. Environmental engineer lost to distributed systems, HPC and cloud computing.
Agent Skills by Carlos Eduardo Arango Gutierrez
Showing 36 vetted skills indexed across 1 GitHub repositories.
ArangoGutierrezcreate-subagent
Create custom Cursor subagents with YAML frontmatter and system prompts.
ArangoGutierrezmigrate-to-skills
Convert Cursor rules and slash commands into Agent Skills format.
ArangoGutierrezshell
Executes user-provided text after /shell as a literal terminal command.
ArangoGutierrezstatusline
Configure a custom command-driven status line for the Cursor CLI prompt.
ArangoGutierrezcanvas
Creates standalone React canvas artifacts in Cursor IDE for analytical and data-heavy output.
ArangoGutierrezcreate-skill
Guides authoring of Cursor Agent Skills with SKILL.md structure and frontmatter conventions.
ArangoGutierrezcreate-rule
Create Cursor IDE rule files with YAML frontmatter and glob patterns.
ArangoGutierrezsdk
Guides building programmatic integrations with the Cursor SDK in TypeScript or Python.
ArangoGutierrezupdate-cursor-settings
Modify Cursor and VSCode user settings in settings.json while preserving existing configuration.
ArangoGutierrezupdate-cli-config
View and modify Cursor CLI settings in the cli-config.json configuration file.
ArangoGutierrezsplit-to-prs
Splits uncommitted or committed changes into small reviewable pull requests.
ArangoGutierrezcreate-hook
Create Cursor IDE hooks that run scripts or prompts around agent events.
ArangoGutierrezbabysit
Triages PR comments, resolves merge conflicts, and fixes CI until merge-ready.
ArangoGutierrezteam-shutdown
Tears down completed multi-agent teams by deleting agents, removing worktrees, and updating AGENTS.md.
ArangoGutierrezkickoff
Compile a rough task idea into a scoped prompt, routed skills, and verification checklist.
ArangoGutierrezpython-review
Reviews Python code for typing, async, agent-loop, and ML reproducibility issues.
ArangoGutierrezk8s-review
Reviews Kubernetes manifests, Helm charts, and RBAC for correctness, security, and best-practice issues.
ArangoGutierrezteam-plan
Plans multi-task projects by decomposing work into scored tasks for agent team execution.
ArangoGutierrezeureka
Capture technical breakthroughs as structured Markdown documents in a dated breakthroughs directory.
ArangoGutierrezpr-review-ingest
Classify GitHub PR review comments and propose rule additions for uncovered findings.
ArangoGutierrezteam-execute
Spawns a multi-agent team to implement an approved plan in isolated git worktrees.
ArangoGutierrezhandoff
Generates a structured session handoff document capturing git state, TDD phase, and decisions for session resumption.
ArangoGutierreztest-review
Review test, e2e, and CI changes to detect theater tests and workflow misconfiguration.
ArangoGutierrezk8s-debug
Diagnoses Kubernetes GPU workload failures through an ordered kubectl triage workflow.
Frequently Asked Questions About Carlos Eduardo Arango Gutierrez
FAQPage SchemaWhat tasks can I accomplish with ArangoGutierrez's skill collection?▼
You can run specialized code reviews for Go, Python, JavaScript, Kubernetes manifests, and test suites; debug GPU workloads on Kubernetes; split work into reviewable PRs; audit .claude configurations for secrets and over-broad permissions; and orchestrate multi-agent sprints with planning, execution, and handoff skills.
Who is the target audience for these skills?▼
Platform engineers, MLOps practitioners, and senior software engineers working in Cursor or Claude-based environments. The Kubernetes debugging, Helm/RBAC review, and GPU scheduling skills target infrastructure teams, while PR lifecycle and session-goal skills serve developers managing long-running agent-assisted projects.
How are these skills installed and invoked?▼
Skills are placed as SKILL.md folders under .cursor/skills/ or the Claude skills directory and triggered by slash commands like /k8s-debug, /pr-review, or /go-review, or by natural-language phrases such as 'review Helm chart'. Many are user-invocable with argument hints; some run disable-model-invocation for deterministic behavior.
What prerequisites or dependencies do these skills require?▼
Skills declare tool dependencies such as Bash, Read, Grep, Glob, Write, Edit, and Agent, so a shell-enabled agent environment is required. Kubernetes skills need cluster access, config-audit reads the local .claude directory, and validate-recommendation requires a panel configuration at ~/.claude/panel/config.yml.
Do these skills support multi-agent coordination?▼
Yes. team-plan, team-execute, team-shutdown, and cmux-sprint-orchestrator coordinate agent teams across worktrees and cmux panes, while kickoff, goal, handoff, and done manage session scoping, evidence-backed completion, and context transfer between sessions.