JairoTorregrosa

JairoTorregrosa/jaiskills

Plugin Claude Code

Jairo's agent skills for Claude Code — orchestration, verification, prompting, and OpenAI tooling in one plugin.

JairoTorregrosa/jaiskills

Plugin Claude Code

Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.

JairoTorregrosa/jaiskills

MCP server Claude CodeCodexCursor +2

MCP server "codex" as configured in JairoTorregrosa/jaiskills. Launched with codex mcp-server.

JairoTorregrosa/jaiskills

Agent

Knowledge search agent for insistir multi-agent orchestration. Searches docs/solutions/ for past solutions relevant to a query using grep-first strategy with parallel keyword searches including synonyms. Read-only — cannot edit, write, or execute commands. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills

Agent

Research agent for insistir orchestration. Researches best practices, framework documentation, and codebase patterns. Read-only — cannot edit or write files. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills

Agent

Cross-review agent for insistir multi-agent orchestration. Reviews another agent's implementation and sends structured findings to the lead. Read-only — cannot edit or write files. Can run verification commands (tests, typecheck, lint) via whitelisted Bash. Enforces quality without gatekeeping. Do NOT use directly …

JairoTorregrosa/jaiskills

Agent

Implementation agent for insistir multi-agent orchestration. Implements a task or applies review fixes, commits, reports to lead. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills

Command

Get a second opinion from Codex (GPT-5) on your current plan, diff, or a specific question.

JairoTorregrosa/jaiskills

Command

Document a solved problem to compound team knowledge.

JairoTorregrosa/jaiskills

Command

Audit a constatar run — conformance, health trends, cost.

JairoTorregrosa/jaiskills

Command

Execute a constatar plan.toml and report grounded results.

JairoTorregrosa/jaiskills

Command

Verify a unit of work with grounded evidence via constatar.

JairoTorregrosa/jaiskills

Command

Enhance a plan with parallel research agents for each section.

JairoTorregrosa/jaiskills

Command

Loop-engineering goal loop: agent factory + gradient descent — forward → loss → backward → update until the goal is provably met.

JairoTorregrosa/jaiskills

Command

Generate a complete, ready-to-use prompt engineered for a specific model and harness.

JairoTorregrosa/jaiskills

Command

Orchestrate a task across remote headless agents on the Jetson (spawn, wait, collect, cross-review).

JairoTorregrosa/jaiskills

Command

Show the remote agent fleet: host health and all jobs with their states.

JairoTorregrosa/jaiskills

Command

Resolve approved TODOs in parallel using worker agents — one agent per TODO.

JairoTorregrosa/jaiskills

Command

Triage review findings one by one — present pending TODOs for user decision (approve, skip, modify).

JairoTorregrosa/jaiskills

Hook

Runs before the agent uses a tool for Bash tool calls, executing reviewer_bash_filter.py via python3. From JairoTorregrosa/jaiskills.

JairoTorregrosa/jaiskills

Hook

Runs when a task is marked completed, executing task_completed.py via python3. From JairoTorregrosa/jaiskills.

JairoTorregrosa/jaiskills

Skill Claude CodeCodex

Document a solved problem to compound team knowledge. Triggered by phrases like "that worked", "it's fixed", "problem solved", or explicitly via the /jaiskills:compound command. Orchestrates parallel sub-agents to analyze the problem, extract the solution, and suggest prevention — then assembles a single searchable…

JairoTorregrosa/jaiskills

Skill Claude CodeCodex

File-based TODO lifecycle for tracking review findings, managing technical debt, and organizing work items. Each TODO is a standalone markdown file with YAML frontmatter, named by convention: {id}-{status}-{priority}-{description}.md. Status transitions drive the lifecycle: pending (created from review) -> ready…

JairoTorregrosa/jaiskills

Skill Claude CodeCodex

Use OpenAI's GPT-5.x and image models from the command line with the askcodex binary: ask or complete text, generate or edit images, list models, check quota/plan. Trigger whenever the user wants an OpenAI model from the terminal — "pregúntale a gpt-5", "haz una imagen", "qué modelos tengo", "cuánta cuota me queda"…